docs(website): add essay on reverse engineering models

Add an English review draft connecting Touhou reconstruction evidence with model specialization, repository knowledge and feedback-driven learning. Preserve model attribution and historical verification scope in supporting notes, and translate the new Blog listing for all existing editions.

Validation: website.py check, focused formatting checks, and 32 Chromium cases covering both preview paths, light/dark themes, responsive layouts, translated indexes and no-JavaScript reading.
This commit is contained in:
N0zoM1z0 authored and Ysopwnable committed 2026-10-13 18:21:09 +08:00
1 parent f8e95799f9
commit fe496bd1cf
23 files changed
+1688 -212

No files matched your search

+1
View File
@@ -131,6 +131,7 @@ describe its recorded investigation; update them only when repeating that work.
- `public/showcase/index.html`: the case-study index.
- `public/blog/index.html`: articles about reconstruction methods, ports, mods and reverse engineering.
- `public/blog/touhou-reconstruction/index.html`: a personal essay about agent autonomy, oracle quality, knowledge carried between TH08 and TH095, PC-98 TH04, and the path from exact reconstruction to readable source and modern ports.
- `public/blog/reverse-engineering-models/index.html`: an English draft on general models, compiler specialization and learning useful reconstruction experiments, with historical evidence from TH08, TH095, TH04 and TH09. Model attribution and verification scope are in [evidence/reverse-engineering-models.md](evidence/reverse-engineering-models.md).
- `public/showcase/aegis/index.html`: Aegis's Android login-code calculation, with an adjustable clock and reference checks.
- `public/showcase/dx-ball/index.html`: sound-pan investigation and project status.
- `public/showcase/notion/index.html`: Notion's Electron clipboard bridge and rich clipboard format.
@@ -0,0 +1,165 @@
# General models and specialist models: article evidence
Supporting record for `public/blog/reverse-engineering-models/index.html`.
The article is an English draft for review and remains `noindex`.
## Research scope
Repository history, maintained source and recorded comparison notes were reviewed
on 13 October 2026. This research did not run game targets, compile reconstruction
candidates or repeat historical runtime checks. Public commit availability was
checked through GitHub CLI.
The evidence describes specific historical functions and their recorded checks.
Source presence, compiler exactness, complete-product builds and runtime agreement
remain distinct. The proposed specialist/RL comparisons are future experiments;
no trained specialist was evaluated for this article.
## Model attribution
- The project operator identifies `gpt-dots` as **GPT-6-Astra**.
- `gpt-web` is a changing label for the model used at the time. The operator
describes then-latest models, usually xhigh, commonly GPT-5.6-Sol earlier and
GPT-6-Sol recently. Do not assign all such commits a single model or infer
individual identities from a release date.
- Explicit `gpt-6-sol` and `gpt-6.1-sol` subjects establish the recorded names.
Per-run reasoning effort and full budgets are not uniformly recorded.
- `gpt-6-luna-max` records GPT-6-Luna and max effort. It does not establish
parameter count or specialist training.
Later sessions inherited earlier source, diagnostics and failed experiments.
Historical before/after closures support the essay's questions; they are not
controlled estimates of model-size effects.
## TH09 Type18/24 attack update
Earlier source-context review:
[GPT-6-Sol, 26 September](https://github.com/N0zoM1z0/th09/commit/de63c0f9121963f3a6b1ab5471c4878625fd3425).
Closing reconstruction:
[GPT-6.1-Sol, 10 October](https://github.com/N0zoM1z0/th09/commit/52929ed7c299f1a5f29cc13964e22510145fd616).
The earlier candidate was 1,435 bytes against a 1,436-byte target. Matching the
overall frame size concealed different homes for returned vectors and real
collision storage. Declaration and helper-visibility controls did not close it.
The closing session introduces an ordinary XYZ destination assignment, consumes
real returned vectors directly and groups six actual publication/rotation
operations into one comma-sequenced full expression. Keeping the real collision
point at function scope preserves separate storage. The seventh warm candidate
matches, followed by a maintained-path canonical cold comparison of all 1,436
bytes and 44 encoded fields. Original class/source spelling and later runtime
gates remain separate.
The article's four-row table groups selected lessons from seven candidates. It
does not enumerate every build or reproduce a complete source listing.
## TH09 Front callback
Earlier diagnostic checkpoint:
[GPT-6.1-Sol, 2 October](https://github.com/N0zoM1z0/th09/commit/f8d12d72aaf02212ee1b585a8f3f86d7ed000269).
Full graph closure:
[GPT-6-Astra (`gpt-dots`), 6 October](https://github.com/N0zoM1z0/th09/commit/da33a646221198ceb7f3df2b96e2ca0e9b2f705f).
Accepted replay:
[6 October follow-up](https://github.com/N0zoM1z0/th09/commit/5f825b28a862f8e1a6d4aea2f78a42f04c09a1c0).
The earlier maintained owner was 1,510 bytes versus the 1,491-byte target. Its
prefix and suffix matched only as independently positioned diagnostic regions;
they did not establish a complete-function match.
A common outer continuation places completion and frame dispatch in complementary
arms with one final frame increment/return. Within this graph, the side/stage
decision recovers target block sharing. The record establishes the complete
1,491-byte owner, 107 independently bound fields, 384 instructions and 42 calls.
The follow-up records accepted forced-recompile replay for `da33a646`.
Bounded trace models are static checks, not game-runtime validation.
## TH095 identifier-bucket reuse
[Supervisor::LoadDat, 2 September](https://github.com/N0zoM1z0/th095/commit/26bb64bdb093a13f73abd0ee8ae7ce199ee4658f).
Under observed VC7.1 build 3077, declaration order alone did not recover the real
local homes. Earlier background work established useful identifier buckets.
Backing the real file-size scalar with `averagedPanLocal12` places it at
`EBP-0x04` and the genuine 128-byte buffer at `EBP-0x88`. All 151 bytes and 15
relocations close.
This is compiler-context evidence. It does not establish a universal C++ rule
or uniquely recover the original author's variable name. The `gpt-web` label
does not identify this run's model individually.
## TH09 Luna enemy-spawn closure
[GPT-6-Luna-max, 27 September](https://github.com/N0zoM1z0/th09/commit/1eb843383941d00065622a9e353146c4bb96979e).
An ordinary loop with `continue`/`break`, branch-local RunEcl failure handling
and a shared success tail closes the 373-byte owner. TH08 source supplies the
source-family hypothesis; TH09 establishes the bounds, fields, ABI and callees.
Two independent cold builds and canonical replay are recorded.
The earlier stable 361-byte candidate is `gpt-web`, with an individually
unresolved model identity. This case demonstrates a useful discovery across
model tiers, not a measured specialist or smaller-parameter advantage.
## TH04 compiler diversity
[Player MAIN_0 cohort, 15 September](https://github.com/N0zoM1z0/th04/commit/6dce0a79d5b931f0e2a08475b90e0c33d2321b98).
Natural Turbo C++ 4.0J source produces a 629-byte update/miss contribution and a
334-byte renderer. Expression lifetimes, branch-local stores, declaration order
and a shared firing tail matter. Correct physical linker order avoids an extra
alignment byte. The recorded focused and aggregate replays cover 129 and 208
owners respectively. These are historical owned-extent checks; this checkpoint
does not establish whole-game execution.
TH08 uses VC7, while TH095/TH09 use VC7.1. Avoid treating every game's source
patterns as output from the same compiler. Shared game authorship supplies a
prior; target-local evidence validates an actual transfer.
## TH08 numerical investigation
[Polar motion and x87 behavior, 13 October](https://github.com/N0zoM1z0/th08/commit/af9cb1d3e839b15a78b47ac1701506083cc82847).
A collision divergence at stage 2 frame 6,825 leads back to a one-ULP
displacement difference at frame 5,573. Historical CRT wrappers retain a wider
x87 return despite storing a rounded float. A distinct i386 case involves x87
precision-control state. The record includes field probes and replay checks for
specified scenarios. Several preceding investigations use the same model; this
is breadth-of-investigation evidence, not a model-switch comparison.
## TH08 floating-literal oracle repair
[Repository-wide audit, 2 September](https://github.com/N0zoM1z0/th08/commit/a393f400786e4cc6cbb1000af0dad3276da12c78).
Literal payload checks previously depended on optional explicit `data_hex`
attestation. The fix decodes and target-checks every VC7 `__real@...` relocation.
The follow-up audits 1,548 relocations and corrects 12 stale rows in five already
accepted units. One source change corrects a bullet-spread increment from
`1.0f` to `32.0f`.
Affected-unit replay and a complete 1,106-unit cold replay are recorded after
repair. This defect is separate from the later one-ULP numerical investigation.
The RL consequence in the article is an inference: a reward based on the earlier
check could reinforce wrong source. The record does not describe an actual RL
exploit or trained model doing so.
## TH09 target-sized replay-save candidate
[Replay-save closure, 2 October](https://github.com/N0zoM1z0/th09/commit/ab72fd77728293fc0beacfc656ca701b0e266016).
The earlier candidate already had the target's 1,825-byte length but 467 complete
comparison differences. Shared index identity, loop structure and the real
cancel/overwrite continuation close the complete owner. The example supports
using size as a diagnostic rather than final acceptance.
## Related research
The article links these primary sources:
- [LLM4Decompile, EMNLP 2024](https://aclanthology.org/2024.emnlp-main.203/).
- [AutoDecompiler, June 2026 preprint](https://arxiv.org/html/2606.16162v1).
- [When LLM Decompilers Recompile More and Preserve Less, September 2026 preprint](https://arxiv.org/html/2609.05370v1).
These works concern specialized decompilation, feedback-based refinement and
functional checking. Their published setups do not establish a winner for the
article's proposed historical-compiler reconstruction experiment. Preserve that
objective distinction when expanding the discussion.
+37 -11
View File
@@ -32,18 +32,18 @@ msgid "Thoughts on reverse engineering."
msgstr "أفكار حول الهندسة العكسية."
#. {ph0}: <br />
#: website/public/blog/index.html:200
#: website/public/blog/index.html:216
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Game reconstruction{ph0}Essay"
msgstr "لعبة إعادة الإعمار{ph0}مقال"
#: website/public/blog/index.html:202
#: website/public/blog/index.html:218
msgctxt "page:blog/index.html"
msgid "The industrial revolution in reverse engineering"
msgstr "الثورة الصناعية في الهندسة العكسية"
#: website/public/blog/index.html:203
#: website/public/blog/index.html:219
msgctxt "page:blog/index.html"
msgid ""
"What manual RE and reconstructing TH08, TH095 and TH04 taught me about "
@@ -52,19 +52,19 @@ msgstr ""
"ما دليل إعادة تعمير TH08, TH095 و TH04 علمني عن وكلاء والتحقق المعرفة أن "
"المركبات عبر المشاريع."
#: website/public/blog/index.html:208
#: website/public/blog/index.html:207 website/public/blog/index.html:224
msgctxt "page:blog/index.html"
msgid "Read the article"
msgstr "اقرأ المقال"
#: website/public/blog/index.html:211
#: website/public/blog/index.html:227
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 10 October 2026"
msgstr "بواسطة N0zoM1z0 * 10 أكتوبر 2026"
#. {ph0}: <span aria-hidden="true">
#. {ph1}: </span>
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
#: website/public/blog/touhou-reconstruction/index.html:1080
#: website/public/examples/dino-lab/index.html:475
#: website/public/faq/index.html:573
@@ -233,7 +233,7 @@ msgctxt "shared"
msgid "Follow REA on X"
msgstr "تابع REA على X"
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
msgctxt "page:blog/index.html"
msgid "Back to top"
msgstr "العودة للأعلى"
@@ -11463,7 +11463,7 @@ msgctxt "shared"
msgid "Guides"
msgstr "الأدلة"
#: website/public/blog/index.html:222
#: website/public/blog/index.html:238
#: website/public/blog/touhou-reconstruction/index.html:1072
#: website/public/examples/dino-lab/index.html:467
#: website/public/faq/index.html:565
@@ -11483,7 +11483,7 @@ msgctxt "shared"
msgid "Source"
msgstr "الكود المصدري"
#: website/public/blog/index.html:223
#: website/public/blog/index.html:239
#: website/public/blog/touhou-reconstruction/index.html:1073
#: website/public/examples/dino-lab/index.html:468
#: website/public/faq/index.html:566
@@ -11503,7 +11503,7 @@ msgctxt "shared"
msgid "MIT license"
msgstr "رخصة MIT"
#: website/public/blog/index.html:224
#: website/public/blog/index.html:240
#: website/public/blog/touhou-reconstruction/index.html:1074
#: website/public/examples/dino-lab/index.html:469
#: website/public/faq/index.html:567
@@ -11523,7 +11523,7 @@ msgctxt "shared"
msgid "Join the community"
msgstr "انضم إلى المجتمع"
#: website/public/blog/index.html:225
#: website/public/blog/index.html:241
#: website/public/blog/touhou-reconstruction/index.html:1075
#: website/public/examples/dino-lab/index.html:470
#: website/public/faq/index.html:568
@@ -12478,6 +12478,32 @@ msgstr ""
"تسجيل في REA دون اتصال، أو اربط خادم MCP في Everywhere لفحص حركة المرور "
"المسجلة مع وكيلك."
#. {ph0}: <br />
#: website/public/blog/index.html:200
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Model specialization{ph0}Essay"
msgstr "نماذج متخصصة{ph0}مقال"
#: website/public/blog/index.html:202
msgctxt "page:blog/index.html"
msgid "Does reverse engineering need a bigger model?"
msgstr "هل تحتاج الهندسة العكسية إلى نموذج أكبر؟"
#: website/public/blog/index.html:203
msgctxt "page:blog/index.html"
msgid ""
"What Touhou reconstruction suggests about general models, specialist models "
"and learning from compiler feedback."
msgstr ""
"أفكار من إعادة بناء Touhou حول النماذج العامة والمتخصصة والتعلم من نتائج "
"المُصرّف."
#: website/public/blog/index.html:210
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 13 October 2026 · Draft for review"
msgstr "بقلم N0zoM1z0 · 13 أكتوبر 2026 · مسودة للمراجعة"
#~ msgctxt "page:index.html"
#~ msgid "Setup guide"
#~ msgstr "دليل الإعداد"
+37 -11
View File
@@ -32,18 +32,18 @@ msgid "Thoughts on reverse engineering."
msgstr "Gedanken zum Reverse Engineering."
#. {ph0}: <br />
#: website/public/blog/index.html:200
#: website/public/blog/index.html:216
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Game reconstruction{ph0}Essay"
msgstr "Spielrekonstruktion{ph0}Essay"
#: website/public/blog/index.html:202
#: website/public/blog/index.html:218
msgctxt "page:blog/index.html"
msgid "The industrial revolution in reverse engineering"
msgstr "Die industrielle Revolution im Reverse Engineering"
#: website/public/blog/index.html:203
#: website/public/blog/index.html:219
msgctxt "page:blog/index.html"
msgid ""
"What manual RE and reconstructing TH08, TH095 and TH04 taught me about "
@@ -53,19 +53,19 @@ msgstr ""
"gelehrt, über Agenten, Überprüfung und Wissen, dass Verbindungen über "
"Projekte hinweg."
#: website/public/blog/index.html:208
#: website/public/blog/index.html:207 website/public/blog/index.html:224
msgctxt "page:blog/index.html"
msgid "Read the article"
msgstr "Lesen Sie den Artikel"
#: website/public/blog/index.html:211
#: website/public/blog/index.html:227
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 10 October 2026"
msgstr "Von N0zoM1z0 · 10. Oktober 2026"
#. {ph0}: <span aria-hidden="true">
#. {ph1}: </span>
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
#: website/public/blog/touhou-reconstruction/index.html:1080
#: website/public/examples/dino-lab/index.html:475
#: website/public/faq/index.html:573
@@ -236,7 +236,7 @@ msgctxt "shared"
msgid "Follow REA on X"
msgstr "REA auf X folgen"
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
msgctxt "page:blog/index.html"
msgid "Back to top"
msgstr "Nach oben"
@@ -11924,7 +11924,7 @@ msgctxt "shared"
msgid "Guides"
msgstr "Anleitungen"
#: website/public/blog/index.html:222
#: website/public/blog/index.html:238
#: website/public/blog/touhou-reconstruction/index.html:1072
#: website/public/examples/dino-lab/index.html:467
#: website/public/faq/index.html:565
@@ -11944,7 +11944,7 @@ msgctxt "shared"
msgid "Source"
msgstr "Quellcode"
#: website/public/blog/index.html:223
#: website/public/blog/index.html:239
#: website/public/blog/touhou-reconstruction/index.html:1073
#: website/public/examples/dino-lab/index.html:468
#: website/public/faq/index.html:566
@@ -11964,7 +11964,7 @@ msgctxt "shared"
msgid "MIT license"
msgstr "MIT-Lizenz"
#: website/public/blog/index.html:224
#: website/public/blog/index.html:240
#: website/public/blog/touhou-reconstruction/index.html:1074
#: website/public/examples/dino-lab/index.html:469
#: website/public/faq/index.html:567
@@ -11984,7 +11984,7 @@ msgctxt "shared"
msgid "Join the community"
msgstr "Zur Community"
#: website/public/blog/index.html:225
#: website/public/blog/index.html:241
#: website/public/blog/touhou-reconstruction/index.html:1075
#: website/public/examples/dino-lab/index.html:470
#: website/public/faq/index.html:568
@@ -12957,6 +12957,32 @@ msgstr ""
"oder verbinden Sie den MCP-Server von Everywhere, um aufgezeichneten "
"Datenverkehr mit Ihrem Agenten zu untersuchen."
#. {ph0}: <br />
#: website/public/blog/index.html:200
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Model specialization{ph0}Essay"
msgstr "Spezialisierte Modelle{ph0}Essay"
#: website/public/blog/index.html:202
msgctxt "page:blog/index.html"
msgid "Does reverse engineering need a bigger model?"
msgstr "Braucht Reverse Engineering ein größeres Modell?"
#: website/public/blog/index.html:203
msgctxt "page:blog/index.html"
msgid ""
"What Touhou reconstruction suggests about general models, specialist models "
"and learning from compiler feedback."
msgstr ""
"Was die Rekonstruktion von Touhou über allgemeine und spezialisierte Modelle"
" sowie das Lernen aus Compiler-Rückmeldungen zeigt."
#: website/public/blog/index.html:210
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 13 October 2026 · Draft for review"
msgstr "Von N0zoM1z0 · 13. Oktober 2026 · Entwurf zur Durchsicht"
#~ msgctxt "page:index.html"
#~ msgid "Setup guide"
#~ msgstr "Einrichtungsanleitung"
+37 -11
View File
@@ -32,18 +32,18 @@ msgid "Thoughts on reverse engineering."
msgstr "Reflexiones sobre ingeniería inversa."
#. {ph0}: <br />
#: website/public/blog/index.html:200
#: website/public/blog/index.html:216
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Game reconstruction{ph0}Essay"
msgstr "Reconstrucción del juego{ph0}Ensayo"
#: website/public/blog/index.html:202
#: website/public/blog/index.html:218
msgctxt "page:blog/index.html"
msgid "The industrial revolution in reverse engineering"
msgstr "La revolución industrial en ingeniería inversa"
#: website/public/blog/index.html:203
#: website/public/blog/index.html:219
msgctxt "page:blog/index.html"
msgid ""
"What manual RE and reconstructing TH08, TH095 and TH04 taught me about "
@@ -53,19 +53,19 @@ msgstr ""
"enseñó sobre los agentes, la verificación y el conocimiento que componen los"
" proyectos."
#: website/public/blog/index.html:208
#: website/public/blog/index.html:207 website/public/blog/index.html:224
msgctxt "page:blog/index.html"
msgid "Read the article"
msgstr "Leer el artículo"
#: website/public/blog/index.html:211
#: website/public/blog/index.html:227
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 10 October 2026"
msgstr "Por N0zoM1z0 * 10 octubre 2026"
#. {ph0}: <span aria-hidden="true">
#. {ph1}: </span>
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
#: website/public/blog/touhou-reconstruction/index.html:1080
#: website/public/examples/dino-lab/index.html:475
#: website/public/faq/index.html:573
@@ -236,7 +236,7 @@ msgctxt "shared"
msgid "Follow REA on X"
msgstr "Sigue a REA en X"
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
msgctxt "page:blog/index.html"
msgid "Back to top"
msgstr "Volver arriba"
@@ -11843,7 +11843,7 @@ msgctxt "shared"
msgid "Guides"
msgstr "Guías"
#: website/public/blog/index.html:222
#: website/public/blog/index.html:238
#: website/public/blog/touhou-reconstruction/index.html:1072
#: website/public/examples/dino-lab/index.html:467
#: website/public/faq/index.html:565
@@ -11863,7 +11863,7 @@ msgctxt "shared"
msgid "Source"
msgstr "Código fuente"
#: website/public/blog/index.html:223
#: website/public/blog/index.html:239
#: website/public/blog/touhou-reconstruction/index.html:1073
#: website/public/examples/dino-lab/index.html:468
#: website/public/faq/index.html:566
@@ -11883,7 +11883,7 @@ msgctxt "shared"
msgid "MIT license"
msgstr "Licencia MIT"
#: website/public/blog/index.html:224
#: website/public/blog/index.html:240
#: website/public/blog/touhou-reconstruction/index.html:1074
#: website/public/examples/dino-lab/index.html:469
#: website/public/faq/index.html:567
@@ -11903,7 +11903,7 @@ msgctxt "shared"
msgid "Join the community"
msgstr "Únete a la comunidad"
#: website/public/blog/index.html:225
#: website/public/blog/index.html:241
#: website/public/blog/touhou-reconstruction/index.html:1075
#: website/public/examples/dino-lab/index.html:470
#: website/public/faq/index.html:568
@@ -12871,6 +12871,32 @@ msgstr ""
" o conecte el servidor MCP de Everywhere para inspeccionar el tráfico "
"capturado con su agente."
#. {ph0}: <br />
#: website/public/blog/index.html:200
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Model specialization{ph0}Essay"
msgstr "Modelos especializados{ph0}Ensayo"
#: website/public/blog/index.html:202
msgctxt "page:blog/index.html"
msgid "Does reverse engineering need a bigger model?"
msgstr "¿Necesita la ingeniería inversa un modelo más grande?"
#: website/public/blog/index.html:203
msgctxt "page:blog/index.html"
msgid ""
"What Touhou reconstruction suggests about general models, specialist models "
"and learning from compiler feedback."
msgstr ""
"Lo que la reconstrucción de Touhou sugiere sobre los modelos generales, los "
"especializados y el aprendizaje a partir de los resultados del compilador."
#: website/public/blog/index.html:210
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 13 October 2026 · Draft for review"
msgstr "Por N0zoM1z0 · 13 de octubre de 2026 · Borrador para revisión"
#~ msgctxt "page:index.html"
#~ msgid "Setup guide"
#~ msgstr "Guía de instalación"
+37 -11
View File
@@ -32,18 +32,18 @@ msgid "Thoughts on reverse engineering."
msgstr "افکار در مهندسی معکوس."
#. {ph0}: <br />
#: website/public/blog/index.html:200
#: website/public/blog/index.html:216
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Game reconstruction{ph0}Essay"
msgstr "بازسازی بازی{ph0}مقاله"
#: website/public/blog/index.html:202
#: website/public/blog/index.html:218
msgctxt "page:blog/index.html"
msgid "The industrial revolution in reverse engineering"
msgstr "انقلاب صنعتی در مهندسی معکوس"
#: website/public/blog/index.html:203
#: website/public/blog/index.html:219
msgctxt "page:blog/index.html"
msgid ""
"What manual RE and reconstructing TH08, TH095 and TH04 taught me about "
@@ -52,19 +52,19 @@ msgstr ""
"چه دستی دوباره و بازسازی TH08, TH095 و TH04 به من آموخت در مورد عوامل, تأیید"
" و دانش است که ترکیبات در سراسر پروژه."
#: website/public/blog/index.html:208
#: website/public/blog/index.html:207 website/public/blog/index.html:224
msgctxt "page:blog/index.html"
msgid "Read the article"
msgstr "مقاله را بخوانید"
#: website/public/blog/index.html:211
#: website/public/blog/index.html:227
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 10 October 2026"
msgstr "توسط N0zoM1z0 * 10 اکتبر 2026"
#. {ph0}: <span aria-hidden="true">
#. {ph1}: </span>
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
#: website/public/blog/touhou-reconstruction/index.html:1080
#: website/public/examples/dino-lab/index.html:475
#: website/public/faq/index.html:573
@@ -234,7 +234,7 @@ msgctxt "shared"
msgid "Follow REA on X"
msgstr "REA را در X دنبال کنید"
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
msgctxt "page:blog/index.html"
msgid "Back to top"
msgstr "بازگشت به بالا"
@@ -11558,7 +11558,7 @@ msgctxt "shared"
msgid "Guides"
msgstr "راهنماها"
#: website/public/blog/index.html:222
#: website/public/blog/index.html:238
#: website/public/blog/touhou-reconstruction/index.html:1072
#: website/public/examples/dino-lab/index.html:467
#: website/public/faq/index.html:565
@@ -11578,7 +11578,7 @@ msgctxt "shared"
msgid "Source"
msgstr "کد منبع"
#: website/public/blog/index.html:223
#: website/public/blog/index.html:239
#: website/public/blog/touhou-reconstruction/index.html:1073
#: website/public/examples/dino-lab/index.html:468
#: website/public/faq/index.html:566
@@ -11598,7 +11598,7 @@ msgctxt "shared"
msgid "MIT license"
msgstr "مجوز MIT"
#: website/public/blog/index.html:224
#: website/public/blog/index.html:240
#: website/public/blog/touhou-reconstruction/index.html:1074
#: website/public/examples/dino-lab/index.html:469
#: website/public/faq/index.html:567
@@ -11618,7 +11618,7 @@ msgctxt "shared"
msgid "Join the community"
msgstr "به جامعه بپیوندید"
#: website/public/blog/index.html:225
#: website/public/blog/index.html:241
#: website/public/blog/touhou-reconstruction/index.html:1075
#: website/public/examples/dino-lab/index.html:470
#: website/public/faq/index.html:568
@@ -12580,6 +12580,32 @@ msgstr ""
" در REA به‌صورت آفلاین، خروجی SAZ ?? HAR 1.2 بگیرید، یا سرور MCP نرم‌افزار "
"Everywhere را متصل کنید تا ترافیک ضبط‌شده را با عامل خود بررسی کنید."
#. {ph0}: <br />
#: website/public/blog/index.html:200
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Model specialization{ph0}Essay"
msgstr "مدل‌های تخصصی{ph0}یادداشت"
#: website/public/blog/index.html:202
msgctxt "page:blog/index.html"
msgid "Does reverse engineering need a bigger model?"
msgstr "آیا مهندسی معکوس به مدل بزرگ‌تری نیاز دارد؟"
#: website/public/blog/index.html:203
msgctxt "page:blog/index.html"
msgid ""
"What Touhou reconstruction suggests about general models, specialist models "
"and learning from compiler feedback."
msgstr ""
"تأملاتی بر پایهٔ بازسازی Touhou دربارهٔ مدل‌های عمومی، مدل‌های تخصصی و "
"یادگیری از بازخورد کامپایلر."
#: website/public/blog/index.html:210
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 13 October 2026 · Draft for review"
msgstr "نویسنده: N0zoM1z0 · ۱۳ اکتبر ۲۰۲۶ · پیش‌نویس برای بازبینی"
#~ msgctxt "page:index.html"
#~ msgid "Setup guide"
#~ msgstr "راهنمای نصب"
+37 -11
View File
@@ -32,18 +32,18 @@ msgid "Thoughts on reverse engineering."
msgstr "Réflexions sur l'ingénierie inverse."
#. {ph0}: <br />
#: website/public/blog/index.html:200
#: website/public/blog/index.html:216
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Game reconstruction{ph0}Essay"
msgstr "Reconstruction du jeu{ph0}Essai"
#: website/public/blog/index.html:202
#: website/public/blog/index.html:218
msgctxt "page:blog/index.html"
msgid "The industrial revolution in reverse engineering"
msgstr "La révolution industrielle dans l'ingénierie inverse"
#: website/public/blog/index.html:203
#: website/public/blog/index.html:219
msgctxt "page:blog/index.html"
msgid ""
"What manual RE and reconstructing TH08, TH095 and TH04 taught me about "
@@ -53,19 +53,19 @@ msgstr ""
"TH04 m'ont appris sur les agents, la vérification et les connaissances qui "
"se combinent dans les projets."
#: website/public/blog/index.html:208
#: website/public/blog/index.html:207 website/public/blog/index.html:224
msgctxt "page:blog/index.html"
msgid "Read the article"
msgstr "Lire l'article"
#: website/public/blog/index.html:211
#: website/public/blog/index.html:227
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 10 October 2026"
msgstr "Par N0zoM1z0 · 10 octobre 2026"
#. {ph0}: <span aria-hidden="true">
#. {ph1}: </span>
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
#: website/public/blog/touhou-reconstruction/index.html:1080
#: website/public/examples/dino-lab/index.html:475
#: website/public/faq/index.html:573
@@ -236,7 +236,7 @@ msgctxt "shared"
msgid "Follow REA on X"
msgstr "Suivre REA sur X"
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
msgctxt "page:blog/index.html"
msgid "Back to top"
msgstr "Haut de page"
@@ -11854,7 +11854,7 @@ msgctxt "shared"
msgid "Guides"
msgstr "Guides"
#: website/public/blog/index.html:222
#: website/public/blog/index.html:238
#: website/public/blog/touhou-reconstruction/index.html:1072
#: website/public/examples/dino-lab/index.html:467
#: website/public/faq/index.html:565
@@ -11874,7 +11874,7 @@ msgctxt "shared"
msgid "Source"
msgstr "Code source"
#: website/public/blog/index.html:223
#: website/public/blog/index.html:239
#: website/public/blog/touhou-reconstruction/index.html:1073
#: website/public/examples/dino-lab/index.html:468
#: website/public/faq/index.html:566
@@ -11894,7 +11894,7 @@ msgctxt "shared"
msgid "MIT license"
msgstr "Licence MIT"
#: website/public/blog/index.html:224
#: website/public/blog/index.html:240
#: website/public/blog/touhou-reconstruction/index.html:1074
#: website/public/examples/dino-lab/index.html:469
#: website/public/faq/index.html:567
@@ -11914,7 +11914,7 @@ msgctxt "shared"
msgid "Join the community"
msgstr "Rejoindre la communauté"
#: website/public/blog/index.html:225
#: website/public/blog/index.html:241
#: website/public/blog/touhou-reconstruction/index.html:1075
#: website/public/examples/dino-lab/index.html:470
#: website/public/faq/index.html:568
@@ -12885,6 +12885,32 @@ msgstr ""
"connectez le serveur MCP d’Everywhere pour inspecter le trafic capturé avec "
"votre agent."
#. {ph0}: <br />
#: website/public/blog/index.html:200
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Model specialization{ph0}Essay"
msgstr "Modèles spécialisés{ph0}Essai"
#: website/public/blog/index.html:202
msgctxt "page:blog/index.html"
msgid "Does reverse engineering need a bigger model?"
msgstr "Le reverse engineering a-t-il besoin d’un modèle plus grand ?"
#: website/public/blog/index.html:203
msgctxt "page:blog/index.html"
msgid ""
"What Touhou reconstruction suggests about general models, specialist models "
"and learning from compiler feedback."
msgstr ""
"Ce que la reconstruction de Touhou suggère sur les modèles généralistes, les"
" modèles spécialisés et l’apprentissage à partir des retours du compilateur."
#: website/public/blog/index.html:210
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 13 October 2026 · Draft for review"
msgstr "Par N0zoM1z0 · 13 octobre 2026 · Brouillon à relire"
#~ msgctxt "page:index.html"
#~ msgid "Setup guide"
#~ msgstr "Guide d’installation"
+37 -11
View File
@@ -32,18 +32,18 @@ msgid "Thoughts on reverse engineering."
msgstr "Pemikiran tentang rekayasa terbalik."
#. {ph0}: <br />
#: website/public/blog/index.html:200
#: website/public/blog/index.html:216
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Game reconstruction{ph0}Essay"
msgstr "Rekonstruksi permainan{ph0}Esai"
#: website/public/blog/index.html:202
#: website/public/blog/index.html:218
msgctxt "page:blog/index.html"
msgid "The industrial revolution in reverse engineering"
msgstr "Revolusi industri dalam rekayasa terbalik"
#: website/public/blog/index.html:203
#: website/public/blog/index.html:219
msgctxt "page:blog/index.html"
msgid ""
"What manual RE and reconstructing TH08, TH095 and TH04 taught me about "
@@ -53,19 +53,19 @@ msgstr ""
" tentang agen, verifikasi, dan pengetahuan yang digabungkan di seluruh "
"proyek."
#: website/public/blog/index.html:208
#: website/public/blog/index.html:207 website/public/blog/index.html:224
msgctxt "page:blog/index.html"
msgid "Read the article"
msgstr "Baca artikelnya"
#: website/public/blog/index.html:211
#: website/public/blog/index.html:227
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 10 October 2026"
msgstr "Oleh N0zoM1z0 · 10 Oktober 2026"
#. {ph0}: <span aria-hidden="true">
#. {ph1}: </span>
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
#: website/public/blog/touhou-reconstruction/index.html:1080
#: website/public/examples/dino-lab/index.html:475
#: website/public/faq/index.html:573
@@ -236,7 +236,7 @@ msgctxt "shared"
msgid "Follow REA on X"
msgstr "Ikuti REA di X"
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
msgctxt "page:blog/index.html"
msgid "Back to top"
msgstr "Kembali ke atas"
@@ -11733,7 +11733,7 @@ msgctxt "shared"
msgid "Guides"
msgstr "Panduan"
#: website/public/blog/index.html:222
#: website/public/blog/index.html:238
#: website/public/blog/touhou-reconstruction/index.html:1072
#: website/public/examples/dino-lab/index.html:467
#: website/public/faq/index.html:565
@@ -11753,7 +11753,7 @@ msgctxt "shared"
msgid "Source"
msgstr "Kode sumber"
#: website/public/blog/index.html:223
#: website/public/blog/index.html:239
#: website/public/blog/touhou-reconstruction/index.html:1073
#: website/public/examples/dino-lab/index.html:468
#: website/public/faq/index.html:566
@@ -11773,7 +11773,7 @@ msgctxt "shared"
msgid "MIT license"
msgstr "Lisensi MIT"
#: website/public/blog/index.html:224
#: website/public/blog/index.html:240
#: website/public/blog/touhou-reconstruction/index.html:1074
#: website/public/examples/dino-lab/index.html:469
#: website/public/faq/index.html:567
@@ -11793,7 +11793,7 @@ msgctxt "shared"
msgid "Join the community"
msgstr "Gabung komunitas"
#: website/public/blog/index.html:225
#: website/public/blog/index.html:241
#: website/public/blog/touhou-reconstruction/index.html:1075
#: website/public/examples/dino-lab/index.html:470
#: website/public/faq/index.html:568
@@ -12758,6 +12758,32 @@ msgstr ""
"server MCP Everywhere untuk memeriksa lalu lintas yang direkam bersama agen "
"Anda."
#. {ph0}: <br />
#: website/public/blog/index.html:200
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Model specialization{ph0}Essay"
msgstr "Model khusus{ph0}Esai"
#: website/public/blog/index.html:202
msgctxt "page:blog/index.html"
msgid "Does reverse engineering need a bigger model?"
msgstr "Apakah rekayasa balik membutuhkan model yang lebih besar?"
#: website/public/blog/index.html:203
msgctxt "page:blog/index.html"
msgid ""
"What Touhou reconstruction suggests about general models, specialist models "
"and learning from compiler feedback."
msgstr ""
"Pelajaran dari rekonstruksi Touhou tentang model umum, model khusus, dan "
"pembelajaran dari umpan balik kompiler."
#: website/public/blog/index.html:210
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 13 October 2026 · Draft for review"
msgstr "Oleh N0zoM1z0 · 13 Oktober 2026 · Draf untuk ditinjau"
#~ msgctxt "page:index.html"
#~ msgid "Setup guide"
#~ msgstr "Panduan pemasangan"
+37 -11
View File
@@ -32,18 +32,18 @@ msgid "Thoughts on reverse engineering."
msgstr "Riflessioni sul reverse engineering."
#. {ph0}: <br />
#: website/public/blog/index.html:200
#: website/public/blog/index.html:216
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Game reconstruction{ph0}Essay"
msgstr "Gioco ricostruzione{ph0}Saggio"
#: website/public/blog/index.html:202
#: website/public/blog/index.html:218
msgctxt "page:blog/index.html"
msgid "The industrial revolution in reverse engineering"
msgstr "La rivoluzione industriale nel reverse engineering"
#: website/public/blog/index.html:203
#: website/public/blog/index.html:219
msgctxt "page:blog/index.html"
msgid ""
"What manual RE and reconstructing TH08, TH095 and TH04 taught me about "
@@ -52,19 +52,19 @@ msgstr ""
"Che manuale RE e ricostruire TH08, TH095 e TH04 mi ha insegnato circa gli "
"agenti, la verifica e la conoscenza che composti attraverso i progetti."
#: website/public/blog/index.html:208
#: website/public/blog/index.html:207 website/public/blog/index.html:224
msgctxt "page:blog/index.html"
msgid "Read the article"
msgstr "Leggi l'articolo"
#: website/public/blog/index.html:211
#: website/public/blog/index.html:227
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 10 October 2026"
msgstr "Di N0zoM1z0 * 10 ottobre 2026"
#. {ph0}: <span aria-hidden="true">
#. {ph1}: </span>
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
#: website/public/blog/touhou-reconstruction/index.html:1080
#: website/public/examples/dino-lab/index.html:475
#: website/public/faq/index.html:573
@@ -235,7 +235,7 @@ msgctxt "shared"
msgid "Follow REA on X"
msgstr "Segui REA su X"
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
msgctxt "page:blog/index.html"
msgid "Back to top"
msgstr "Torna in alto"
@@ -11791,7 +11791,7 @@ msgctxt "shared"
msgid "Guides"
msgstr "Guide"
#: website/public/blog/index.html:222
#: website/public/blog/index.html:238
#: website/public/blog/touhou-reconstruction/index.html:1072
#: website/public/examples/dino-lab/index.html:467
#: website/public/faq/index.html:565
@@ -11811,7 +11811,7 @@ msgctxt "shared"
msgid "Source"
msgstr "Codice sorgente"
#: website/public/blog/index.html:223
#: website/public/blog/index.html:239
#: website/public/blog/touhou-reconstruction/index.html:1073
#: website/public/examples/dino-lab/index.html:468
#: website/public/faq/index.html:566
@@ -11831,7 +11831,7 @@ msgctxt "shared"
msgid "MIT license"
msgstr "Licenza MIT"
#: website/public/blog/index.html:224
#: website/public/blog/index.html:240
#: website/public/blog/touhou-reconstruction/index.html:1074
#: website/public/examples/dino-lab/index.html:469
#: website/public/faq/index.html:567
@@ -11851,7 +11851,7 @@ msgctxt "shared"
msgid "Join the community"
msgstr "Unisciti alla community"
#: website/public/blog/index.html:225
#: website/public/blog/index.html:241
#: website/public/blog/touhou-reconstruction/index.html:1075
#: website/public/examples/dino-lab/index.html:470
#: website/public/faq/index.html:568
@@ -12819,6 +12819,32 @@ msgstr ""
"offline, oppure collega il server MCP di Everywhere per esaminare il "
"traffico acquisito con il tuo agente."
#. {ph0}: <br />
#: website/public/blog/index.html:200
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Model specialization{ph0}Essay"
msgstr "Modelli specializzati{ph0}Saggio"
#: website/public/blog/index.html:202
msgctxt "page:blog/index.html"
msgid "Does reverse engineering need a bigger model?"
msgstr "Il reverse engineering ha bisogno di un modello più grande?"
#: website/public/blog/index.html:203
msgctxt "page:blog/index.html"
msgid ""
"What Touhou reconstruction suggests about general models, specialist models "
"and learning from compiler feedback."
msgstr ""
"Cosa suggerisce la ricostruzione di Touhou sui modelli generali, quelli "
"specializzati e l’apprendimento dal feedback del compilatore."
#: website/public/blog/index.html:210
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 13 October 2026 · Draft for review"
msgstr "Di N0zoM1z0 · 13 ottobre 2026 · Bozza da rivedere"
#~ msgctxt "page:index.html"
#~ msgid "Setup guide"
#~ msgstr "Guida all’installazione"
+35 -11
View File
@@ -32,18 +32,18 @@ msgid "Thoughts on reverse engineering."
msgstr "リバースエンジニアリングに関する考え。"
#. {ph0}: <br />
#: website/public/blog/index.html:200
#: website/public/blog/index.html:216
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Game reconstruction{ph0}Essay"
msgstr "ゲーム再構築{ph0}小論文"
#: website/public/blog/index.html:202
#: website/public/blog/index.html:218
msgctxt "page:blog/index.html"
msgid "The industrial revolution in reverse engineering"
msgstr "リバースエンジニアリングにおける産業革命"
#: website/public/blog/index.html:203
#: website/public/blog/index.html:219
msgctxt "page:blog/index.html"
msgid ""
"What manual RE and reconstructing TH08, TH095 and TH04 taught me about "
@@ -51,19 +51,19 @@ msgid ""
msgstr ""
"どのようなマニュアル再とTH08を再構築,TH095とTH04は、エージェントについて教えてくれました,プロジェクト間で化合物の検証と知識."
#: website/public/blog/index.html:208
#: website/public/blog/index.html:207 website/public/blog/index.html:224
msgctxt "page:blog/index.html"
msgid "Read the article"
msgstr "記事を読む"
#: website/public/blog/index.html:211
#: website/public/blog/index.html:227
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 10 October 2026"
msgstr "によってN0zoM1z0•10 10月2026"
#. {ph0}: <span aria-hidden="true">
#. {ph1}: </span>
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
#: website/public/blog/touhou-reconstruction/index.html:1080
#: website/public/examples/dino-lab/index.html:475
#: website/public/faq/index.html:573
@@ -230,7 +230,7 @@ msgctxt "shared"
msgid "Follow REA on X"
msgstr "X で REA をフォロー"
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
msgctxt "page:blog/index.html"
msgid "Back to top"
msgstr "ページ上部へ"
@@ -10965,7 +10965,7 @@ msgctxt "shared"
msgid "Guides"
msgstr "ガイド"
#: website/public/blog/index.html:222
#: website/public/blog/index.html:238
#: website/public/blog/touhou-reconstruction/index.html:1072
#: website/public/examples/dino-lab/index.html:467
#: website/public/faq/index.html:565
@@ -10985,7 +10985,7 @@ msgctxt "shared"
msgid "Source"
msgstr "ソースコード"
#: website/public/blog/index.html:223
#: website/public/blog/index.html:239
#: website/public/blog/touhou-reconstruction/index.html:1073
#: website/public/examples/dino-lab/index.html:468
#: website/public/faq/index.html:566
@@ -11005,7 +11005,7 @@ msgctxt "shared"
msgid "MIT license"
msgstr "MIT ライセンス"
#: website/public/blog/index.html:224
#: website/public/blog/index.html:240
#: website/public/blog/touhou-reconstruction/index.html:1074
#: website/public/examples/dino-lab/index.html:469
#: website/public/faq/index.html:567
@@ -11025,7 +11025,7 @@ msgctxt "shared"
msgid "Join the community"
msgstr "コミュニティに参加"
#: website/public/blog/index.html:225
#: website/public/blog/index.html:241
#: website/public/blog/touhou-reconstruction/index.html:1075
#: website/public/examples/dino-lab/index.html:470
#: website/public/faq/index.html:568
@@ -11963,6 +11963,30 @@ msgstr ""
"キャプチャ、MCP、公開スキル{ph1}を利用してください。SAZ ??? HAR 1.2 をエクスポートすれば REA でオフラインのキャプチャ "
"Evidence を取得できます。また、Everywhere の MCP サーバーを接続して、エージェントと一緒に記録済みの通信を調べることもできます。"
#. {ph0}: <br />
#: website/public/blog/index.html:200
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Model specialization{ph0}Essay"
msgstr "モデルの特化{ph0}エッセイ"
#: website/public/blog/index.html:202
msgctxt "page:blog/index.html"
msgid "Does reverse engineering need a bigger model?"
msgstr "リバースエンジニアリングに、より大きなモデルは必要か?"
#: website/public/blog/index.html:203
msgctxt "page:blog/index.html"
msgid ""
"What Touhou reconstruction suggests about general models, specialist models "
"and learning from compiler feedback."
msgstr "Touhou の再構築を通じて考える、汎用モデル、特化モデル、そしてコンパイラのフィードバックから学ぶ方法。"
#: website/public/blog/index.html:210
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 13 October 2026 · Draft for review"
msgstr "N0zoM1z0 著 · 2026年10月13日 · レビュー用草稿"
#~ msgctxt "page:index.html"
#~ msgid "Setup guide"
#~ msgstr "セットアップガイド"
+35 -11
View File
@@ -32,37 +32,37 @@ msgid "Thoughts on reverse engineering."
msgstr "리버스 엔지니어링에 대한 생각."
#. {ph0}: <br />
#: website/public/blog/index.html:200
#: website/public/blog/index.html:216
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Game reconstruction{ph0}Essay"
msgstr "게임 재구성{ph0}에세이"
#: website/public/blog/index.html:202
#: website/public/blog/index.html:218
msgctxt "page:blog/index.html"
msgid "The industrial revolution in reverse engineering"
msgstr "리버스 엔지니어링의 산업 혁명"
#: website/public/blog/index.html:203
#: website/public/blog/index.html:219
msgctxt "page:blog/index.html"
msgid ""
"What manual RE and reconstructing TH08, TH095 and TH04 taught me about "
"agents, verification and knowledge that compounds across projects."
msgstr "어떤 매뉴얼 다시고 재구성TH08,TH095및TH04에 대해 가르쳐 에이전트,검증 및 지는 화합물에 걸쳐 프로젝트입니다."
#: website/public/blog/index.html:208
#: website/public/blog/index.html:207 website/public/blog/index.html:224
msgctxt "page:blog/index.html"
msgid "Read the article"
msgstr "기사 읽기"
#: website/public/blog/index.html:211
#: website/public/blog/index.html:227
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 10 October 2026"
msgstr "여N0zoM1z0·10 월 2026"
#. {ph0}: <span aria-hidden="true">
#. {ph1}: </span>
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
#: website/public/blog/touhou-reconstruction/index.html:1080
#: website/public/examples/dino-lab/index.html:475
#: website/public/faq/index.html:573
@@ -229,7 +229,7 @@ msgctxt "shared"
msgid "Follow REA on X"
msgstr "X에서 REA 팔로우"
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
msgctxt "page:blog/index.html"
msgid "Back to top"
msgstr "맨 위로"
@@ -10931,7 +10931,7 @@ msgctxt "shared"
msgid "Guides"
msgstr "가이드"
#: website/public/blog/index.html:222
#: website/public/blog/index.html:238
#: website/public/blog/touhou-reconstruction/index.html:1072
#: website/public/examples/dino-lab/index.html:467
#: website/public/faq/index.html:565
@@ -10951,7 +10951,7 @@ msgctxt "shared"
msgid "Source"
msgstr "소스 코드"
#: website/public/blog/index.html:223
#: website/public/blog/index.html:239
#: website/public/blog/touhou-reconstruction/index.html:1073
#: website/public/examples/dino-lab/index.html:468
#: website/public/faq/index.html:566
@@ -10971,7 +10971,7 @@ msgctxt "shared"
msgid "MIT license"
msgstr "MIT 라이선스"
#: website/public/blog/index.html:224
#: website/public/blog/index.html:240
#: website/public/blog/touhou-reconstruction/index.html:1074
#: website/public/examples/dino-lab/index.html:469
#: website/public/faq/index.html:567
@@ -10991,7 +10991,7 @@ msgctxt "shared"
msgid "Join the community"
msgstr "커뮤니티 참여"
#: website/public/blog/index.html:225
#: website/public/blog/index.html:241
#: website/public/blog/touhou-reconstruction/index.html:1075
#: website/public/examples/dino-lab/index.html:470
#: website/public/faq/index.html:568
@@ -11927,6 +11927,30 @@ msgstr ""
"사용하세요. SAZ ?? HAR 1.2로 내보내면 REA에서 오프라인 캡처 Evidence를 얻을 수 있으며, Everywhere의 "
"MCP 서버를 연결하여 에이전트와 함께 캡처된 트래픽을 살펴볼 수도 있습니다."
#. {ph0}: <br />
#: website/public/blog/index.html:200
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Model specialization{ph0}Essay"
msgstr "전문 모델{ph0}에세이"
#: website/public/blog/index.html:202
msgctxt "page:blog/index.html"
msgid "Does reverse engineering need a bigger model?"
msgstr "리버스 엔지니어링에는 더 큰 모델이 필요할까?"
#: website/public/blog/index.html:203
msgctxt "page:blog/index.html"
msgid ""
"What Touhou reconstruction suggests about general models, specialist models "
"and learning from compiler feedback."
msgstr "Touhou 재구축 경험을 바탕으로 범용 모델, 전문 모델, 컴파일러 피드백을 통한 학습을 생각해 봅니다."
#: website/public/blog/index.html:210
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 13 October 2026 · Draft for review"
msgstr "작성: N0zoM1z0 · 2026년 10월 13일 · 검토용 초안"
#~ msgctxt "page:index.html"
#~ msgid "Setup guide"
#~ msgstr "설정 가이드"
+38 -14
View File
@@ -101,32 +101,56 @@ msgstr ""
#: website/public/blog/index.html:200
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Game reconstruction{ph0}Essay"
msgid "Model specialization{ph0}Essay"
msgstr ""
#: website/public/blog/index.html:202
msgctxt "page:blog/index.html"
msgid "The industrial revolution in reverse engineering"
msgid "Does reverse engineering need a bigger model?"
msgstr ""
#: website/public/blog/index.html:203
msgctxt "page:blog/index.html"
msgid ""
"What Touhou reconstruction suggests about general models, specialist models and "
"learning from compiler feedback."
msgstr ""
#: website/public/blog/index.html:207 website/public/blog/index.html:224
msgctxt "page:blog/index.html"
msgid "Read the article"
msgstr ""
#: website/public/blog/index.html:210
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 13 October 2026 · Draft for review"
msgstr ""
#. {ph0}: <br />
#: website/public/blog/index.html:216
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Game reconstruction{ph0}Essay"
msgstr ""
#: website/public/blog/index.html:218
msgctxt "page:blog/index.html"
msgid "The industrial revolution in reverse engineering"
msgstr ""
#: website/public/blog/index.html:219
msgctxt "page:blog/index.html"
msgid ""
"What manual RE and reconstructing TH08, TH095 and TH04 taught me about agents, "
"verification and knowledge that compounds across projects."
msgstr ""
#: website/public/blog/index.html:208
msgctxt "page:blog/index.html"
msgid "Read the article"
msgstr ""
#: website/public/blog/index.html:211
#: website/public/blog/index.html:227
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 10 October 2026"
msgstr ""
#: website/public/blog/index.html:222
#: website/public/blog/index.html:238
#: website/public/blog/touhou-reconstruction/index.html:1072
#: website/public/examples/dino-lab/index.html:467 website/public/faq/index.html:565
#: website/public/first-investigation/index.html:515
@@ -143,7 +167,7 @@ msgctxt "shared"
msgid "Source"
msgstr ""
#: website/public/blog/index.html:223
#: website/public/blog/index.html:239
#: website/public/blog/touhou-reconstruction/index.html:1073
#: website/public/examples/dino-lab/index.html:468 website/public/faq/index.html:566
#: website/public/first-investigation/index.html:516
@@ -160,7 +184,7 @@ msgctxt "shared"
msgid "MIT license"
msgstr ""
#: website/public/blog/index.html:224
#: website/public/blog/index.html:240
#: website/public/blog/touhou-reconstruction/index.html:1074
#: website/public/examples/dino-lab/index.html:469 website/public/faq/index.html:567
#: website/public/first-investigation/index.html:517
@@ -177,7 +201,7 @@ msgctxt "shared"
msgid "Join the community"
msgstr ""
#: website/public/blog/index.html:225
#: website/public/blog/index.html:241
#: website/public/blog/touhou-reconstruction/index.html:1075
#: website/public/examples/dino-lab/index.html:470 website/public/faq/index.html:568
#: website/public/first-investigation/index.html:518
@@ -196,7 +220,7 @@ msgstr ""
#. {ph0}: <span aria-hidden="true">
#. {ph1}: </span>
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
#: website/public/blog/touhou-reconstruction/index.html:1080
#: website/public/examples/dino-lab/index.html:475 website/public/faq/index.html:573
#: website/public/first-investigation/index.html:523
@@ -337,7 +361,7 @@ msgctxt "shared"
msgid "Follow REA on X"
msgstr ""
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
msgctxt "page:blog/index.html"
msgid "Back to top"
msgstr ""
+37 -11
View File
@@ -32,18 +32,18 @@ msgid "Thoughts on reverse engineering."
msgstr "Myśli o inżynierii odwrotnej."
#. {ph0}: <br />
#: website/public/blog/index.html:200
#: website/public/blog/index.html:216
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Game reconstruction{ph0}Essay"
msgstr "Rekonstrukcja gry{ph0}Esej"
#: website/public/blog/index.html:202
#: website/public/blog/index.html:218
msgctxt "page:blog/index.html"
msgid "The industrial revolution in reverse engineering"
msgstr "Rewolucja przemysłowa w inżynierii odwrotnej"
#: website/public/blog/index.html:203
#: website/public/blog/index.html:219
msgctxt "page:blog/index.html"
msgid ""
"What manual RE and reconstructing TH08, TH095 and TH04 taught me about "
@@ -52,19 +52,19 @@ msgstr ""
"Co Instrukcja RE i rekonstrukcji TH08, TH095 i TH04 nauczył mnie O agentów, "
"weryfikacja i wiedza, że związki całej projektów."
#: website/public/blog/index.html:208
#: website/public/blog/index.html:207 website/public/blog/index.html:224
msgctxt "page:blog/index.html"
msgid "Read the article"
msgstr "Przeczytaj artykuł"
#: website/public/blog/index.html:211
#: website/public/blog/index.html:227
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 10 October 2026"
msgstr "Przez N0zoM1z0 * 10 października 2026"
#. {ph0}: <span aria-hidden="true">
#. {ph1}: </span>
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
#: website/public/blog/touhou-reconstruction/index.html:1080
#: website/public/examples/dino-lab/index.html:475
#: website/public/faq/index.html:573
@@ -235,7 +235,7 @@ msgctxt "shared"
msgid "Follow REA on X"
msgstr "Obserwuj REA na X"
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
msgctxt "page:blog/index.html"
msgid "Back to top"
msgstr "Do góry"
@@ -11697,7 +11697,7 @@ msgctxt "shared"
msgid "Guides"
msgstr "Poradniki"
#: website/public/blog/index.html:222
#: website/public/blog/index.html:238
#: website/public/blog/touhou-reconstruction/index.html:1072
#: website/public/examples/dino-lab/index.html:467
#: website/public/faq/index.html:565
@@ -11717,7 +11717,7 @@ msgctxt "shared"
msgid "Source"
msgstr "Kod źródłowy"
#: website/public/blog/index.html:223
#: website/public/blog/index.html:239
#: website/public/blog/touhou-reconstruction/index.html:1073
#: website/public/examples/dino-lab/index.html:468
#: website/public/faq/index.html:566
@@ -11737,7 +11737,7 @@ msgctxt "shared"
msgid "MIT license"
msgstr "Licencja MIT"
#: website/public/blog/index.html:224
#: website/public/blog/index.html:240
#: website/public/blog/touhou-reconstruction/index.html:1074
#: website/public/examples/dino-lab/index.html:469
#: website/public/faq/index.html:567
@@ -11757,7 +11757,7 @@ msgctxt "shared"
msgid "Join the community"
msgstr "Dołącz do społeczności"
#: website/public/blog/index.html:225
#: website/public/blog/index.html:241
#: website/public/blog/touhou-reconstruction/index.html:1075
#: website/public/examples/dino-lab/index.html:470
#: website/public/faq/index.html:568
@@ -12723,6 +12723,32 @@ msgstr ""
"1.2, aby uzyskać Evidence z zapisu w REA offline, lub połącz serwer MCP "
"Everywhere, aby analizować zapisany ruch z agentem."
#. {ph0}: <br />
#: website/public/blog/index.html:200
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Model specialization{ph0}Essay"
msgstr "Modele specjalistyczne{ph0}Esej"
#: website/public/blog/index.html:202
msgctxt "page:blog/index.html"
msgid "Does reverse engineering need a bigger model?"
msgstr "Czy inżynieria odwrotna potrzebuje większego modelu?"
#: website/public/blog/index.html:203
msgctxt "page:blog/index.html"
msgid ""
"What Touhou reconstruction suggests about general models, specialist models "
"and learning from compiler feedback."
msgstr ""
"Co rekonstrukcja Touhou mówi o modelach ogólnych, modelach specjalistycznych"
" i uczeniu się na podstawie informacji zwrotnych z kompilatora."
#: website/public/blog/index.html:210
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 13 October 2026 · Draft for review"
msgstr "Autor: N0zoM1z0 · 13 października 2026 · Szkic do przejrzenia"
#~ msgctxt "page:index.html"
#~ msgid "Setup guide"
#~ msgstr "Instrukcja instalacji"
+37 -11
View File
@@ -32,18 +32,18 @@ msgid "Thoughts on reverse engineering."
msgstr "Reflexões sobre engenharia reversa."
#. {ph0}: <br />
#: website/public/blog/index.html:200
#: website/public/blog/index.html:216
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Game reconstruction{ph0}Essay"
msgstr "Reconstrução do jogo{ph0}Ensaio"
#: website/public/blog/index.html:202
#: website/public/blog/index.html:218
msgctxt "page:blog/index.html"
msgid "The industrial revolution in reverse engineering"
msgstr "A Revolução industrial na engenharia reversa"
#: website/public/blog/index.html:203
#: website/public/blog/index.html:219
msgctxt "page:blog/index.html"
msgid ""
"What manual RE and reconstructing TH08, TH095 and TH04 taught me about "
@@ -52,19 +52,19 @@ msgstr ""
"O manual RE e reconstrução TH08, TH095 e TH04 me ensinou sobre agentes, "
"verificação e conhecimento que compostos entre projetos."
#: website/public/blog/index.html:208
#: website/public/blog/index.html:207 website/public/blog/index.html:224
msgctxt "page:blog/index.html"
msgid "Read the article"
msgstr "Leia o artigo"
#: website/public/blog/index.html:211
#: website/public/blog/index.html:227
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 10 October 2026"
msgstr "Por N0zoM1z0 * 10 de outubro de 2026"
#. {ph0}: <span aria-hidden="true">
#. {ph1}: </span>
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
#: website/public/blog/touhou-reconstruction/index.html:1080
#: website/public/examples/dino-lab/index.html:475
#: website/public/faq/index.html:573
@@ -235,7 +235,7 @@ msgctxt "shared"
msgid "Follow REA on X"
msgstr "Siga o REA no X"
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
msgctxt "page:blog/index.html"
msgid "Back to top"
msgstr "Voltar ao topo"
@@ -11774,7 +11774,7 @@ msgctxt "shared"
msgid "Guides"
msgstr "Guias"
#: website/public/blog/index.html:222
#: website/public/blog/index.html:238
#: website/public/blog/touhou-reconstruction/index.html:1072
#: website/public/examples/dino-lab/index.html:467
#: website/public/faq/index.html:565
@@ -11794,7 +11794,7 @@ msgctxt "shared"
msgid "Source"
msgstr "Código-fonte"
#: website/public/blog/index.html:223
#: website/public/blog/index.html:239
#: website/public/blog/touhou-reconstruction/index.html:1073
#: website/public/examples/dino-lab/index.html:468
#: website/public/faq/index.html:566
@@ -11814,7 +11814,7 @@ msgctxt "shared"
msgid "MIT license"
msgstr "Licença MIT"
#: website/public/blog/index.html:224
#: website/public/blog/index.html:240
#: website/public/blog/touhou-reconstruction/index.html:1074
#: website/public/examples/dino-lab/index.html:469
#: website/public/faq/index.html:567
@@ -11834,7 +11834,7 @@ msgctxt "shared"
msgid "Join the community"
msgstr "Participe da comunidade"
#: website/public/blog/index.html:225
#: website/public/blog/index.html:241
#: website/public/blog/touhou-reconstruction/index.html:1075
#: website/public/examples/dino-lab/index.html:470
#: website/public/faq/index.html:568
@@ -12798,6 +12798,32 @@ msgstr ""
"servidor MCP do Everywhere para inspecionar o tráfego capturado com seu "
"agente."
#. {ph0}: <br />
#: website/public/blog/index.html:200
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Model specialization{ph0}Essay"
msgstr "Modelos especializados{ph0}Ensaio"
#: website/public/blog/index.html:202
msgctxt "page:blog/index.html"
msgid "Does reverse engineering need a bigger model?"
msgstr "A engenharia reversa precisa de um modelo maior?"
#: website/public/blog/index.html:203
msgctxt "page:blog/index.html"
msgid ""
"What Touhou reconstruction suggests about general models, specialist models "
"and learning from compiler feedback."
msgstr ""
"O que a reconstrução de Touhou sugere sobre modelos gerais, modelos "
"especializados e o aprendizado com o retorno do compilador."
#: website/public/blog/index.html:210
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 13 October 2026 · Draft for review"
msgstr "Por N0zoM1z0 · 13 de outubro de 2026 · Rascunho para revisão"
#~ msgctxt "page:index.html"
#~ msgid "Setup guide"
#~ msgstr "Guia de instalação"
+37 -11
View File
@@ -32,18 +32,18 @@ msgid "Thoughts on reverse engineering."
msgstr "Мысли о реверс-инжиниринге."
#. {ph0}: <br />
#: website/public/blog/index.html:200
#: website/public/blog/index.html:216
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Game reconstruction{ph0}Essay"
msgstr "Реконструкция игры{ph0}Сочинение"
#: website/public/blog/index.html:202
#: website/public/blog/index.html:218
msgctxt "page:blog/index.html"
msgid "The industrial revolution in reverse engineering"
msgstr "Промышленная революция в области реверс-инжиниринга"
#: website/public/blog/index.html:203
#: website/public/blog/index.html:219
msgctxt "page:blog/index.html"
msgid ""
"What manual RE and reconstructing TH08, TH095 and TH04 taught me about "
@@ -52,19 +52,19 @@ msgstr ""
"Чему меня научило руководство по обновлению и реконструкции TH08, TH095 и "
"TH04 об агентах, проверке и знаниях, которые используются в разных проектах."
#: website/public/blog/index.html:208
#: website/public/blog/index.html:207 website/public/blog/index.html:224
msgctxt "page:blog/index.html"
msgid "Read the article"
msgstr "Прочтите статью"
#: website/public/blog/index.html:211
#: website/public/blog/index.html:227
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 10 October 2026"
msgstr "Автор: N0zoM1z0 · 10 октября 2026"
#. {ph0}: <span aria-hidden="true">
#. {ph1}: </span>
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
#: website/public/blog/touhou-reconstruction/index.html:1080
#: website/public/examples/dino-lab/index.html:475
#: website/public/faq/index.html:573
@@ -235,7 +235,7 @@ msgctxt "shared"
msgid "Follow REA on X"
msgstr "Подписаться на REA в X"
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
msgctxt "page:blog/index.html"
msgid "Back to top"
msgstr "Наверх"
@@ -11811,7 +11811,7 @@ msgctxt "shared"
msgid "Guides"
msgstr "Руководства"
#: website/public/blog/index.html:222
#: website/public/blog/index.html:238
#: website/public/blog/touhou-reconstruction/index.html:1072
#: website/public/examples/dino-lab/index.html:467
#: website/public/faq/index.html:565
@@ -11831,7 +11831,7 @@ msgctxt "shared"
msgid "Source"
msgstr "Исходный код"
#: website/public/blog/index.html:223
#: website/public/blog/index.html:239
#: website/public/blog/touhou-reconstruction/index.html:1073
#: website/public/examples/dino-lab/index.html:468
#: website/public/faq/index.html:566
@@ -11851,7 +11851,7 @@ msgctxt "shared"
msgid "MIT license"
msgstr "Лицензия MIT"
#: website/public/blog/index.html:224
#: website/public/blog/index.html:240
#: website/public/blog/touhou-reconstruction/index.html:1074
#: website/public/examples/dino-lab/index.html:469
#: website/public/faq/index.html:567
@@ -11871,7 +11871,7 @@ msgctxt "shared"
msgid "Join the community"
msgstr "Вступить в сообщество"
#: website/public/blog/index.html:225
#: website/public/blog/index.html:241
#: website/public/blog/touhou-reconstruction/index.html:1075
#: website/public/examples/dino-lab/index.html:470
#: website/public/faq/index.html:568
@@ -12840,6 +12840,32 @@ msgstr ""
"подключите MCP-сервер Everywhere, чтобы исследовать записанный трафик вместе"
" с агентом."
#. {ph0}: <br />
#: website/public/blog/index.html:200
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Model specialization{ph0}Essay"
msgstr "Специализация моделей{ph0}Эссе"
#: website/public/blog/index.html:202
msgctxt "page:blog/index.html"
msgid "Does reverse engineering need a bigger model?"
msgstr "Нужна ли для обратной разработки более крупная модель?"
#: website/public/blog/index.html:203
msgctxt "page:blog/index.html"
msgid ""
"What Touhou reconstruction suggests about general models, specialist models "
"and learning from compiler feedback."
msgstr ""
"Что реконструкция Touhou помогает понять об универсальных и "
"специализированных моделях и обучении на обратной связи от компилятора."
#: website/public/blog/index.html:210
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 13 October 2026 · Draft for review"
msgstr "Автор: N0zoM1z0 · 13 октября 2026 г. · Черновик для обсуждения"
#~ msgctxt "page:index.html"
#~ msgid "Setup guide"
#~ msgstr "Руководство по установке"
+37 -11
View File
@@ -32,18 +32,18 @@ msgid "Thoughts on reverse engineering."
msgstr "ความคิดเกี่ยวกับวิศวกรรมย้อนกลับ"
#. {ph0}: <br />
#: website/public/blog/index.html:200
#: website/public/blog/index.html:216
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Game reconstruction{ph0}Essay"
msgstr "ฟื้นฟูเกม{ph0}เรียงความ"
#: website/public/blog/index.html:202
#: website/public/blog/index.html:218
msgctxt "page:blog/index.html"
msgid "The industrial revolution in reverse engineering"
msgstr "การปฏิวัติอุตสาหกรรมในวิศวกรรมย้อนกลับ"
#: website/public/blog/index.html:203
#: website/public/blog/index.html:219
msgctxt "page:blog/index.html"
msgid ""
"What manual RE and reconstructing TH08, TH095 and TH04 taught me about "
@@ -52,19 +52,19 @@ msgstr ""
"สิ่งที่คู่มือใหม่และ "
"reconstructingTH08,TH095และTH04สอนฉันเกี่ยวกับเจ้าหน้าที่ปลายทางและความรู้นั่นรประกอบที่อีกฝั่งยิ่งสนง.โครงการ."
#: website/public/blog/index.html:208
#: website/public/blog/index.html:207 website/public/blog/index.html:224
msgctxt "page:blog/index.html"
msgid "Read the article"
msgstr "อ่านบทความ"
#: website/public/blog/index.html:211
#: website/public/blog/index.html:227
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 10 October 2026"
msgstr "โดย N0zoM1z0 ·10 ตุลาคม 2026"
#. {ph0}: <span aria-hidden="true">
#. {ph1}: </span>
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
#: website/public/blog/touhou-reconstruction/index.html:1080
#: website/public/examples/dino-lab/index.html:475
#: website/public/faq/index.html:573
@@ -234,7 +234,7 @@ msgctxt "shared"
msgid "Follow REA on X"
msgstr "ติดตาม REA บน X"
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
msgctxt "page:blog/index.html"
msgid "Back to top"
msgstr "กลับขึ้นด้านบน"
@@ -11455,7 +11455,7 @@ msgctxt "shared"
msgid "Guides"
msgstr "คู่มือ"
#: website/public/blog/index.html:222
#: website/public/blog/index.html:238
#: website/public/blog/touhou-reconstruction/index.html:1072
#: website/public/examples/dino-lab/index.html:467
#: website/public/faq/index.html:565
@@ -11475,7 +11475,7 @@ msgctxt "shared"
msgid "Source"
msgstr "ซอร์สโค้ด"
#: website/public/blog/index.html:223
#: website/public/blog/index.html:239
#: website/public/blog/touhou-reconstruction/index.html:1073
#: website/public/examples/dino-lab/index.html:468
#: website/public/faq/index.html:566
@@ -11495,7 +11495,7 @@ msgctxt "shared"
msgid "MIT license"
msgstr "สัญญาอนุญาต MIT"
#: website/public/blog/index.html:224
#: website/public/blog/index.html:240
#: website/public/blog/touhou-reconstruction/index.html:1074
#: website/public/examples/dino-lab/index.html:469
#: website/public/faq/index.html:567
@@ -11515,7 +11515,7 @@ msgctxt "shared"
msgid "Join the community"
msgstr "เข้าร่วมชุมชน"
#: website/public/blog/index.html:225
#: website/public/blog/index.html:241
#: website/public/blog/touhou-reconstruction/index.html:1075
#: website/public/examples/dino-lab/index.html:470
#: website/public/faq/index.html:568
@@ -12477,6 +12477,32 @@ msgstr ""
"หรือเชื่อมต่อเซิร์ฟเวอร์ MCP ของ Everywhere "
"เพื่อตรวจสอบทราฟฟิกที่บันทึกไว้ร่วมกับเอเจนต์ของคุณ"
#. {ph0}: <br />
#: website/public/blog/index.html:200
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Model specialization{ph0}Essay"
msgstr "โมเดลเฉพาะทาง{ph0}บทความ"
#: website/public/blog/index.html:202
msgctxt "page:blog/index.html"
msgid "Does reverse engineering need a bigger model?"
msgstr "การวิศวกรรมย้อนกลับจำเป็นต้องใช้โมเดลที่ใหญ่ขึ้นไหม?"
#: website/public/blog/index.html:203
msgctxt "page:blog/index.html"
msgid ""
"What Touhou reconstruction suggests about general models, specialist models "
"and learning from compiler feedback."
msgstr ""
"ข้อคิดจากการสร้าง Touhou ขึ้นใหม่ เกี่ยวกับโมเดลทั่วไป โมเดลเฉพาะทาง "
"และการเรียนรู้จากผลตอบกลับของคอมไพเลอร์"
#: website/public/blog/index.html:210
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 13 October 2026 · Draft for review"
msgstr "โดย N0zoM1z0 · 13 ตุลาคม 2026 · ฉบับร่างสำหรับตรวจทาน"
#~ msgctxt "page:index.html"
#~ msgid "Setup guide"
#~ msgstr "คู่มือการติดตั้ง"
+37 -11
View File
@@ -32,18 +32,18 @@ msgid "Thoughts on reverse engineering."
msgstr "Tersine mühendislik üzerine düşünceler."
#. {ph0}: <br />
#: website/public/blog/index.html:200
#: website/public/blog/index.html:216
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Game reconstruction{ph0}Essay"
msgstr "Oyun rekonstrüksiyonu{ph0}Deneme"
#: website/public/blog/index.html:202
#: website/public/blog/index.html:218
msgctxt "page:blog/index.html"
msgid "The industrial revolution in reverse engineering"
msgstr "Tersine mühendislikte endüstri devrimi"
#: website/public/blog/index.html:203
#: website/public/blog/index.html:219
msgctxt "page:blog/index.html"
msgid ""
"What manual RE and reconstructing TH08, TH095 and TH04 taught me about "
@@ -53,19 +53,19 @@ msgstr ""
"yapılandırılması bana projeler arasında birleşen aracılar, doğrulama ve "
"bilgi hakkında bilgi verdi."
#: website/public/blog/index.html:208
#: website/public/blog/index.html:207 website/public/blog/index.html:224
msgctxt "page:blog/index.html"
msgid "Read the article"
msgstr "Makaleyi okuyun"
#: website/public/blog/index.html:211
#: website/public/blog/index.html:227
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 10 October 2026"
msgstr "Başlangıç N0zoM1z0 * 10 Ekim 2026"
#. {ph0}: <span aria-hidden="true">
#. {ph1}: </span>
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
#: website/public/blog/touhou-reconstruction/index.html:1080
#: website/public/examples/dino-lab/index.html:475
#: website/public/faq/index.html:573
@@ -236,7 +236,7 @@ msgctxt "shared"
msgid "Follow REA on X"
msgstr "REA’yı X’te takip et"
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
msgctxt "page:blog/index.html"
msgid "Back to top"
msgstr "Başa dön"
@@ -11684,7 +11684,7 @@ msgctxt "shared"
msgid "Guides"
msgstr "Rehberler"
#: website/public/blog/index.html:222
#: website/public/blog/index.html:238
#: website/public/blog/touhou-reconstruction/index.html:1072
#: website/public/examples/dino-lab/index.html:467
#: website/public/faq/index.html:565
@@ -11704,7 +11704,7 @@ msgctxt "shared"
msgid "Source"
msgstr "Kaynak kod"
#: website/public/blog/index.html:223
#: website/public/blog/index.html:239
#: website/public/blog/touhou-reconstruction/index.html:1073
#: website/public/examples/dino-lab/index.html:468
#: website/public/faq/index.html:566
@@ -11724,7 +11724,7 @@ msgctxt "shared"
msgid "MIT license"
msgstr "MIT lisansı"
#: website/public/blog/index.html:224
#: website/public/blog/index.html:240
#: website/public/blog/touhou-reconstruction/index.html:1074
#: website/public/examples/dino-lab/index.html:469
#: website/public/faq/index.html:567
@@ -11744,7 +11744,7 @@ msgctxt "shared"
msgid "Join the community"
msgstr "Topluluğa katıl"
#: website/public/blog/index.html:225
#: website/public/blog/index.html:241
#: website/public/blog/touhou-reconstruction/index.html:1075
#: website/public/examples/dino-lab/index.html:470
#: website/public/faq/index.html:568
@@ -12706,6 +12706,32 @@ msgstr ""
" kaydedilen trafiği ajanınızla incelemek için Everywhere MCP sunucusunu "
"bağlayın."
#. {ph0}: <br />
#: website/public/blog/index.html:200
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Model specialization{ph0}Essay"
msgstr "Uzmanlaşmış modeller{ph0}Deneme"
#: website/public/blog/index.html:202
msgctxt "page:blog/index.html"
msgid "Does reverse engineering need a bigger model?"
msgstr "Tersine mühendislik için daha büyük bir model gerekli mi?"
#: website/public/blog/index.html:203
msgctxt "page:blog/index.html"
msgid ""
"What Touhou reconstruction suggests about general models, specialist models "
"and learning from compiler feedback."
msgstr ""
"Touhou yeniden yapılandırma deneyiminden genel amaçlı modeller, uzmanlaşmış "
"modeller ve derleyici geri bildiriminden öğrenme üzerine düşünceler."
#: website/public/blog/index.html:210
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 13 October 2026 · Draft for review"
msgstr "N0zoM1z0 · 13 Ekim 2026 · İnceleme taslağı"
#~ msgctxt "page:index.html"
#~ msgid "Setup guide"
#~ msgstr "Kurulum rehberi"
+37 -11
View File
@@ -32,18 +32,18 @@ msgid "Thoughts on reverse engineering."
msgstr "Думки про реверс-інжиніринг."
#. {ph0}: <br />
#: website/public/blog/index.html:200
#: website/public/blog/index.html:216
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Game reconstruction{ph0}Essay"
msgstr "Реконструкція гри{ph0}Вигадування"
#: website/public/blog/index.html:202
#: website/public/blog/index.html:218
msgctxt "page:blog/index.html"
msgid "The industrial revolution in reverse engineering"
msgstr "Промислова революція в області реверс-інжинірингу"
#: website/public/blog/index.html:203
#: website/public/blog/index.html:219
msgctxt "page:blog/index.html"
msgid ""
"What manual RE and reconstructing TH08, TH095 and TH04 taught me about "
@@ -52,19 +52,19 @@ msgstr ""
"Чому мене навчив посібник з оновлення та реконструкції TH08, TH095 та TH04 "
"про агентів, перевірку та знання, які використовуються в різних проектах."
#: website/public/blog/index.html:208
#: website/public/blog/index.html:207 website/public/blog/index.html:224
msgctxt "page:blog/index.html"
msgid "Read the article"
msgstr "Прочитайте статтю"
#: website/public/blog/index.html:211
#: website/public/blog/index.html:227
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 10 October 2026"
msgstr "Автор: N0zoM1z0 · 10 жовтня 2026"
#. {ph0}: <span aria-hidden="true">
#. {ph1}: </span>
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
#: website/public/blog/touhou-reconstruction/index.html:1080
#: website/public/examples/dino-lab/index.html:475
#: website/public/faq/index.html:573
@@ -235,7 +235,7 @@ msgctxt "shared"
msgid "Follow REA on X"
msgstr "Стежити за REA в X"
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
msgctxt "page:blog/index.html"
msgid "Back to top"
msgstr "Нагору"
@@ -11763,7 +11763,7 @@ msgctxt "shared"
msgid "Guides"
msgstr "Посібники"
#: website/public/blog/index.html:222
#: website/public/blog/index.html:238
#: website/public/blog/touhou-reconstruction/index.html:1072
#: website/public/examples/dino-lab/index.html:467
#: website/public/faq/index.html:565
@@ -11783,7 +11783,7 @@ msgctxt "shared"
msgid "Source"
msgstr "Вихідний код"
#: website/public/blog/index.html:223
#: website/public/blog/index.html:239
#: website/public/blog/touhou-reconstruction/index.html:1073
#: website/public/examples/dino-lab/index.html:468
#: website/public/faq/index.html:566
@@ -11803,7 +11803,7 @@ msgctxt "shared"
msgid "MIT license"
msgstr "Ліцензія MIT"
#: website/public/blog/index.html:224
#: website/public/blog/index.html:240
#: website/public/blog/touhou-reconstruction/index.html:1074
#: website/public/examples/dino-lab/index.html:469
#: website/public/faq/index.html:567
@@ -11823,7 +11823,7 @@ msgctxt "shared"
msgid "Join the community"
msgstr "Приєднатися до спільноти"
#: website/public/blog/index.html:225
#: website/public/blog/index.html:241
#: website/public/blog/touhou-reconstruction/index.html:1075
#: website/public/examples/dino-lab/index.html:470
#: website/public/faq/index.html:568
@@ -12791,6 +12791,32 @@ msgstr ""
"мережі або підключіть MCP-сервер Everywhere, щоб досліджувати записаний "
"трафік разом з агентом."
#. {ph0}: <br />
#: website/public/blog/index.html:200
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Model specialization{ph0}Essay"
msgstr "Спеціалізація моделей{ph0}Есе"
#: website/public/blog/index.html:202
msgctxt "page:blog/index.html"
msgid "Does reverse engineering need a bigger model?"
msgstr "Чи потрібна для зворотної розробки більша модель?"
#: website/public/blog/index.html:203
msgctxt "page:blog/index.html"
msgid ""
"What Touhou reconstruction suggests about general models, specialist models "
"and learning from compiler feedback."
msgstr ""
"Що реконструкція Touhou допомагає зрозуміти про універсальні й "
"спеціалізовані моделі та навчання на зворотному зв’язку від компілятора."
#: website/public/blog/index.html:210
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 13 October 2026 · Draft for review"
msgstr "Автор: N0zoM1z0 · 13 жовтня 2026 р. · Чернетка для обговорення"
#~ msgctxt "page:index.html"
#~ msgid "Setup guide"
#~ msgstr "Посібник зі встановлення"
+37 -11
View File
@@ -32,18 +32,18 @@ msgid "Thoughts on reverse engineering."
msgstr "Suy nghĩ về kỹ thuật đảo ngược."
#. {ph0}: <br />
#: website/public/blog/index.html:200
#: website/public/blog/index.html:216
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Game reconstruction{ph0}Essay"
msgstr "Tái thiết trò chơi{ph0}Bài luận"
#: website/public/blog/index.html:202
#: website/public/blog/index.html:218
msgctxt "page:blog/index.html"
msgid "The industrial revolution in reverse engineering"
msgstr "Cuộc cách mạng công nghiệp trong kỹ thuật đảo ngược"
#: website/public/blog/index.html:203
#: website/public/blog/index.html:219
msgctxt "page:blog/index.html"
msgid ""
"What manual RE and reconstructing TH08, TH095 and TH04 taught me about "
@@ -52,19 +52,19 @@ msgstr ""
"NHỮNG gì HƯỚNG DẪN SỬ DỤNG LẠI VÀ tái TẠO TH08, TH095 và TH04 đã dạy tôi về "
"các agent, xác minh và kiến thức mà các hợp chất trong các dự án."
#: website/public/blog/index.html:208
#: website/public/blog/index.html:207 website/public/blog/index.html:224
msgctxt "page:blog/index.html"
msgid "Read the article"
msgstr "Đọc bài viết"
#: website/public/blog/index.html:211
#: website/public/blog/index.html:227
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 10 October 2026"
msgstr "Bởi N0zoM1z0 * 10 tháng mười 2026"
#. {ph0}: <span aria-hidden="true">
#. {ph1}: </span>
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
#: website/public/blog/touhou-reconstruction/index.html:1080
#: website/public/examples/dino-lab/index.html:475
#: website/public/faq/index.html:573
@@ -235,7 +235,7 @@ msgctxt "shared"
msgid "Follow REA on X"
msgstr "Theo DÕI REA Trên X"
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
msgctxt "page:blog/index.html"
msgid "Back to top"
msgstr "Về đầu trang"
@@ -11673,7 +11673,7 @@ msgctxt "shared"
msgid "Guides"
msgstr "Hướng dẫn"
#: website/public/blog/index.html:222
#: website/public/blog/index.html:238
#: website/public/blog/touhou-reconstruction/index.html:1072
#: website/public/examples/dino-lab/index.html:467
#: website/public/faq/index.html:565
@@ -11693,7 +11693,7 @@ msgctxt "shared"
msgid "Source"
msgstr "Mã nguồn"
#: website/public/blog/index.html:223
#: website/public/blog/index.html:239
#: website/public/blog/touhou-reconstruction/index.html:1073
#: website/public/examples/dino-lab/index.html:468
#: website/public/faq/index.html:566
@@ -11713,7 +11713,7 @@ msgctxt "shared"
msgid "MIT license"
msgstr "Giấy phép MIT"
#: website/public/blog/index.html:224
#: website/public/blog/index.html:240
#: website/public/blog/touhou-reconstruction/index.html:1074
#: website/public/examples/dino-lab/index.html:469
#: website/public/faq/index.html:567
@@ -11733,7 +11733,7 @@ msgctxt "shared"
msgid "Join the community"
msgstr "Tham gia cộng đồng"
#: website/public/blog/index.html:225
#: website/public/blog/index.html:241
#: website/public/blog/touhou-reconstruction/index.html:1075
#: website/public/examples/dino-lab/index.html:470
#: website/public/faq/index.html:568
@@ -12692,6 +12692,32 @@ msgstr ""
"1.2 để lấy Evidence từ bản ghi trong REA ngoại tuyến, hoặc kết nối máy chủ "
"MCP của Everywhere để kiểm tra lưu lượng đã ghi cùng trợ lý của bạn."
#. {ph0}: <br />
#: website/public/blog/index.html:200
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Model specialization{ph0}Essay"
msgstr "Mô hình chuyên biệt{ph0}Bài viết"
#: website/public/blog/index.html:202
msgctxt "page:blog/index.html"
msgid "Does reverse engineering need a bigger model?"
msgstr "Kỹ thuật đảo ngược có cần mô hình lớn hơn không?"
#: website/public/blog/index.html:203
msgctxt "page:blog/index.html"
msgid ""
"What Touhou reconstruction suggests about general models, specialist models "
"and learning from compiler feedback."
msgstr ""
"Những suy nghĩ từ việc tái dựng Touhou về mô hình tổng quát, mô hình chuyên "
"biệt và cách học từ phản hồi của trình biên dịch."
#: website/public/blog/index.html:210
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 13 October 2026 · Draft for review"
msgstr "N0zoM1z0 · 13 tháng 10 năm 2026 · Bản nháp để góp ý"
#~ msgctxt "page:index.html"
#~ msgid "Setup guide"
#~ msgstr "Hướng dẫn cài đặt"
+35 -11
View File
@@ -32,37 +32,37 @@ msgid "Thoughts on reverse engineering."
msgstr "逆向工程的思考。"
#. {ph0}: <br />
#: website/public/blog/index.html:200
#: website/public/blog/index.html:216
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Game reconstruction{ph0}Essay"
msgstr "游戏重建{ph0}论文"
#: website/public/blog/index.html:202
#: website/public/blog/index.html:218
msgctxt "page:blog/index.html"
msgid "The industrial revolution in reverse engineering"
msgstr "逆向工程的工业革命"
#: website/public/blog/index.html:203
#: website/public/blog/index.html:219
msgctxt "page:blog/index.html"
msgid ""
"What manual RE and reconstructing TH08, TH095 and TH04 taught me about "
"agents, verification and knowledge that compounds across projects."
msgstr "什么手动重新和重建TH08,TH095和TH04教我关于编程助手,验证和知识,跨项目的化合物。"
#: website/public/blog/index.html:208
#: website/public/blog/index.html:207 website/public/blog/index.html:224
msgctxt "page:blog/index.html"
msgid "Read the article"
msgstr "阅读文章"
#: website/public/blog/index.html:211
#: website/public/blog/index.html:227
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 10 October 2026"
msgstr "通过N0zoM1z0*10十月2026"
#. {ph0}: <span aria-hidden="true">
#. {ph1}: </span>
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
#: website/public/blog/touhou-reconstruction/index.html:1080
#: website/public/examples/dino-lab/index.html:475
#: website/public/faq/index.html:573
@@ -229,7 +229,7 @@ msgctxt "shared"
msgid "Follow REA on X"
msgstr "在 X 上关注 REA"
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
msgctxt "page:blog/index.html"
msgid "Back to top"
msgstr "回到顶部"
@@ -10694,7 +10694,7 @@ msgctxt "shared"
msgid "Guides"
msgstr "指南"
#: website/public/blog/index.html:222
#: website/public/blog/index.html:238
#: website/public/blog/touhou-reconstruction/index.html:1072
#: website/public/examples/dino-lab/index.html:467
#: website/public/faq/index.html:565
@@ -10714,7 +10714,7 @@ msgctxt "shared"
msgid "Source"
msgstr "源代码"
#: website/public/blog/index.html:223
#: website/public/blog/index.html:239
#: website/public/blog/touhou-reconstruction/index.html:1073
#: website/public/examples/dino-lab/index.html:468
#: website/public/faq/index.html:566
@@ -10734,7 +10734,7 @@ msgctxt "shared"
msgid "MIT license"
msgstr "MIT 许可证"
#: website/public/blog/index.html:224
#: website/public/blog/index.html:240
#: website/public/blog/touhou-reconstruction/index.html:1074
#: website/public/examples/dino-lab/index.html:469
#: website/public/faq/index.html:567
@@ -10754,7 +10754,7 @@ msgctxt "shared"
msgid "Join the community"
msgstr "加入社区"
#: website/public/blog/index.html:225
#: website/public/blog/index.html:241
#: website/public/blog/touhou-reconstruction/index.html:1075
#: website/public/examples/dino-lab/index.html:470
#: website/public/faq/index.html:568
@@ -11681,6 +11681,30 @@ msgstr ""
"要检查 HTTP 请求和响应正文,请使用{ph0}Fiddler Everywhere:SAZ 捕获、MCP 和公开技能{ph1}。导出 SAZ ? "
"HAR 1.2 可在 REA 中离线获取捕获 Evidence,也可以连接 Everywhere 的 MCP 服务器,让智能体检查已捕获的流量。"
#. {ph0}: <br />
#: website/public/blog/index.html:200
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Model specialization{ph0}Essay"
msgstr "专用模型{ph0}随笔"
#: website/public/blog/index.html:202
msgctxt "page:blog/index.html"
msgid "Does reverse engineering need a bigger model?"
msgstr "逆向工程需要更大的模型吗?"
#: website/public/blog/index.html:203
msgctxt "page:blog/index.html"
msgid ""
"What Touhou reconstruction suggests about general models, specialist models "
"and learning from compiler feedback."
msgstr "从 Touhou 重建的经验,探讨通用模型、专用模型,以及如何从编译器反馈中学习。"
#: website/public/blog/index.html:210
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 13 October 2026 · Draft for review"
msgstr "作者 N0zoM1z0 · 2026 年 10 月 13 日 · 待审草稿"
#~ msgctxt "page:index.html"
#~ msgid "Setup guide"
#~ msgstr "安装指南"
+35 -11
View File
@@ -32,37 +32,37 @@ msgid "Thoughts on reverse engineering."
msgstr "逆向工程的思考。"
#. {ph0}: <br />
#: website/public/blog/index.html:200
#: website/public/blog/index.html:216
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Game reconstruction{ph0}Essay"
msgstr "遊戲重建{ph0}論文"
#: website/public/blog/index.html:202
#: website/public/blog/index.html:218
msgctxt "page:blog/index.html"
msgid "The industrial revolution in reverse engineering"
msgstr "逆向工程的工業革命"
#: website/public/blog/index.html:203
#: website/public/blog/index.html:219
msgctxt "page:blog/index.html"
msgid ""
"What manual RE and reconstructing TH08, TH095 and TH04 taught me about "
"agents, verification and knowledge that compounds across projects."
msgstr "什麼手動重新和重建TH08,TH095和TH04教我關於程式設計助手,驗證和知識,跨專案的化合物。"
#: website/public/blog/index.html:208
#: website/public/blog/index.html:207 website/public/blog/index.html:224
msgctxt "page:blog/index.html"
msgid "Read the article"
msgstr "閱讀文章"
#: website/public/blog/index.html:211
#: website/public/blog/index.html:227
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 10 October 2026"
msgstr "透過N0zoM1z0*10十月2026"
#. {ph0}: <span aria-hidden="true">
#. {ph1}: </span>
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
#: website/public/blog/touhou-reconstruction/index.html:1080
#: website/public/examples/dino-lab/index.html:475
#: website/public/faq/index.html:573
@@ -229,7 +229,7 @@ msgctxt "shared"
msgid "Follow REA on X"
msgstr "在 X 上關注 REA"
#: website/public/blog/index.html:230
#: website/public/blog/index.html:246
msgctxt "page:blog/index.html"
msgid "Back to top"
msgstr "回到頂部"
@@ -10713,7 +10713,7 @@ msgctxt "shared"
msgid "Guides"
msgstr "指南"
#: website/public/blog/index.html:222
#: website/public/blog/index.html:238
#: website/public/blog/touhou-reconstruction/index.html:1072
#: website/public/examples/dino-lab/index.html:467
#: website/public/faq/index.html:565
@@ -10733,7 +10733,7 @@ msgctxt "shared"
msgid "Source"
msgstr "原始碼"
#: website/public/blog/index.html:223
#: website/public/blog/index.html:239
#: website/public/blog/touhou-reconstruction/index.html:1073
#: website/public/examples/dino-lab/index.html:468
#: website/public/faq/index.html:566
@@ -10753,7 +10753,7 @@ msgctxt "shared"
msgid "MIT license"
msgstr "MIT 許可證"
#: website/public/blog/index.html:224
#: website/public/blog/index.html:240
#: website/public/blog/touhou-reconstruction/index.html:1074
#: website/public/examples/dino-lab/index.html:469
#: website/public/faq/index.html:567
@@ -10773,7 +10773,7 @@ msgctxt "shared"
msgid "Join the community"
msgstr "加入社群"
#: website/public/blog/index.html:225
#: website/public/blog/index.html:241
#: website/public/blog/touhou-reconstruction/index.html:1075
#: website/public/examples/dino-lab/index.html:470
#: website/public/faq/index.html:568
@@ -11701,6 +11701,30 @@ msgstr ""
"若要檢查 HTTP 請求與回應本文,請使用{ph0}Fiddler Everywhere:SAZ 擷取、MCP 與公開技能{ph1}。匯出 SAZ ? "
"HAR 1.2 可在 REA 中離線取得擷取 Evidence,也可以連接 Everywhere 的 MCP 伺服器,讓代理檢查已擷取的流量。"
#. {ph0}: <br />
#: website/public/blog/index.html:200
#, python-brace-format
msgctxt "page:blog/index.html"
msgid "Model specialization{ph0}Essay"
msgstr "專用模型{ph0}隨筆"
#: website/public/blog/index.html:202
msgctxt "page:blog/index.html"
msgid "Does reverse engineering need a bigger model?"
msgstr "逆向工程需要更大的模型嗎?"
#: website/public/blog/index.html:203
msgctxt "page:blog/index.html"
msgid ""
"What Touhou reconstruction suggests about general models, specialist models "
"and learning from compiler feedback."
msgstr "從 Touhou 重建的經驗,探討通用模型、專用模型,以及如何從編譯器回饋中學習。"
#: website/public/blog/index.html:210
msgctxt "page:blog/index.html"
msgid "By N0zoM1z0 · 13 October 2026 · Draft for review"
msgstr "作者 N0zoM1z0 · 2026 年 10 月 13 日 · 待審草稿"
#~ msgctxt "page:index.html"
#~ msgid "Setup guide"
#~ msgstr "安裝指南"
+16
View File
@@ -196,6 +196,22 @@
<p class="lede">Thoughts on reverse engineering.</p>
</div>
<div class="guide-index">
<section class="guide-entry">
<p class="eyebrow">Model specialization<br />Essay</p>
<div>
<h2>Does reverse engineering need a bigger model?</h2>
<p>
What Touhou reconstruction suggests about general models,
specialist models and learning from compiler feedback.
</p>
<a class="text-link" href="reverse-engineering-models/"
>Read the article</a
>
<p class="page-meta">
By N0zoM1z0 · 13 October 2026 · Draft for review
</p>
</div>
</section>
<section class="guide-entry">
<p class="eyebrow">Game reconstruction<br />Essay</p>
<div>
@@ -0,0 +1,810 @@
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Does reverse engineering need a bigger model? | REA</title>
<meta
name="description"
content="What Touhou reconstruction taught me about general models, specialist models and learning to propose better hypotheses from compiler feedback."
/>
<meta name="robots" content="noindex" />
<!-- website:sharing:start -->
<!-- prettier-ignore -->
<link rel="canonical" href="https://rea.tools/blog/reverse-engineering-models/" />
<!-- website:languages:start -->
<!-- website:languages:end -->
<!-- prettier-ignore -->
<meta property="og:type" content="website" />
<!-- prettier-ignore -->
<meta property="og:site_name" content="REA" />
<!-- prettier-ignore -->
<meta property="og:title" content="Does reverse engineering need a bigger model? | REA" />
<!-- prettier-ignore -->
<meta property="og:description" content="What Touhou reconstruction taught me about general models, specialist models and learning to propose better hypotheses from compiler feedback." />
<!-- prettier-ignore -->
<meta property="og:url" content="https://rea.tools/blog/reverse-engineering-models/" />
<!-- prettier-ignore -->
<meta property="og:image" content="https://rea.tools/assets/social-card.png" />
<!-- prettier-ignore -->
<meta property="og:image:type" content="image/png" />
<!-- prettier-ignore -->
<meta property="og:image:width" content="1200" />
<!-- prettier-ignore -->
<meta property="og:image:height" content="630" />
<!-- prettier-ignore -->
<meta
property="og:image:alt"
content="REA — Find out how software works. Reverse engineering with your coding agent."
/>
<!-- prettier-ignore -->
<meta name="twitter:card" content="summary_large_image" />
<!-- prettier-ignore -->
<meta name="twitter:title" content="Does reverse engineering need a bigger model? | REA" />
<!-- prettier-ignore -->
<meta name="twitter:description" content="What Touhou reconstruction taught me about general models, specialist models and learning to propose better hypotheses from compiler feedback." />
<!-- prettier-ignore -->
<meta name="twitter:image" content="https://rea.tools/assets/social-card.png" />
<!-- prettier-ignore -->
<meta
name="twitter:image:alt"
content="REA — Find out how software works. Reverse engineering with your coding agent."
/>
<!-- website:sharing:end -->
<!-- website:theme:start -->
<meta name="theme-color" content="#ffffff" />
<!-- Apply the saved theme before styles load, to avoid a flash on navigation. -->
<script src="../../assets/theme.js"></script>
<!-- website:theme:end -->
<link rel="icon" href="../../assets/favicon.svg" type="image/svg+xml" />
<link rel="stylesheet" href="../../assets/styles.css" />
<script src="../../assets/main.js" defer></script>
</head>
<body id="top">
<a class="skip-link" href="#main">Skip to content</a>
<!-- website:header:start -->
<!-- prettier-ignore -->
<header class="site-header">
<div class="container header-inner">
<a class="brand" href="../../" aria-label="REA home"
><span class="brand-name">REA</span
><span class="brand-caption" data-i18n-skip>Reverse Engineer Anything</span></a
>
<nav class="navigation" aria-label="Main navigation">
<a href="../../get-started/" class="nav-start">Get started</a>
<a href="../../showcase/">Showcases</a>
<a href="../../blog/" aria-current="page">Blog</a>
<a href="../../guides/">Guides</a>
<a href="../../faq/">FAQ</a>
</nav>
<div class="header-social">
<button class="theme-toggle" type="button" data-theme-toggle hidden>
<svg class="theme-moon" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="1.6" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true" focusable="false">
<path d="M20.9 13a9 9 0 0 1-9.9-9.9A9 9 0 1 0 20.9 13Z" />
</svg>
<svg class="theme-sun" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="1.6" stroke-linecap="round" aria-hidden="true" focusable="false">
<circle cx="12" cy="12" r="4" />
<path d="M12 2v2m0 16v2M2 12h2m16 0h2M4.93 4.93l1.42 1.42m11.3 11.3 1.42 1.42M4.93 19.07l1.42-1.42m11.3-11.3 1.42-1.42" />
</svg>
</button>
<a
class="nav-github"
href="https://github.com/morluto/rea"
aria-label="REA on GitHub"
title="REA on GitHub"
>
<svg
width="22"
height="22"
viewBox="0 0 16 16"
aria-hidden="true"
focusable="false"
>
<path
fill="currentColor"
d="M8 0C3.58 0 0 3.58 0 8c0 3.54 2.29 6.53 5.47 7.59.4.07.55-.17.55-.38 0-.19-.01-.82-.01-1.49-2.01.37-2.53-.49-2.69-.94-.09-.23-.48-.94-.82-1.13-.28-.15-.68-.52-.01-.53.63-.01 1.08.58 1.23.82.72 1.21 1.87.87 2.33.66.07-.52.28-.87.51-1.07-1.78-.2-3.64-.89-3.64-3.95 0-.87.31-1.59.82-2.15-.08-.2-.36-1.02.08-2.12 0 0 .67-.21 2.2.82a7.65 7.65 0 0 1 2-.27c.68 0 1.36.09 2 .27 1.53-1.04 2.2-.82 2.2-.82.44 1.1.16 1.92.08 2.12.51.56.82 1.27.82 2.15 0 3.07-1.87 3.75-3.65 3.95.29.25.54.73.54 1.48 0 1.07-.01 1.93-.01 2.2 0 .21.15.46.55.38A8.01 8.01 0 0 0 16 8c0-4.42-3.58-8-8-8Z"
/>
</svg>
<span class="nav-github-count" hidden aria-hidden="true"></span>
</a>
<a
class="nav-discord"
href="https://discord.gg/GkcryMnJDM"
aria-label="Join REA on Discord"
title="Join REA on Discord"
>
<svg
width="22"
height="22"
viewBox="0 0 24 24"
aria-hidden="true"
focusable="false"
>
<path
fill="currentColor"
d="M20.317 4.3698a19.7913 19.7913 0 0 0-4.8851-1.5152.0741.0741 0 0 0-.0785.0371c-.211.3753-.4447.8648-.6083 1.2495-1.8447-.2762-3.68-.2762-5.4868 0-.1636-.3933-.4058-.8742-.6177-1.2495a.077.077 0 0 0-.0785-.037 19.7363 19.7363 0 0 0-4.8852 1.515.0699.0699 0 0 0-.0321.0277C.5334 9.0458-.319 13.5799.0992 18.0578a.0824.0824 0 0 0 .0312.0561c2.0528 1.5076 4.0413 2.4228 5.9929 3.0294a.0777.0777 0 0 0 .0842-.0276c.4616-.6304.8731-1.2952 1.226-1.9942a.076.076 0 0 0-.0416-.1057c-.6528-.2476-1.2743-.5495-1.8722-.8923a.077.077 0 0 1-.0076-.1277c.1258-.0943.2517-.1923.3718-.2914a.0743.0743 0 0 1 .0776-.0105c3.9278 1.7933 8.18 1.7933 12.0614 0a.0739.0739 0 0 1 .0785.0095c.1202.099.246.1981.3728.2924a.077.077 0 0 1-.0066.1276 12.2986 12.2986 0 0 1-1.873.8914.0766.0766 0 0 0-.0407.1067c.3604.698.7719 1.3628 1.225 1.9932a.076.076 0 0 0 .0842.0286c1.961-.6067 3.9495-1.5219 6.0023-3.0294a.077.077 0 0 0 .0313-.0552c.5004-5.177-.8382-9.6739-3.5485-13.6604a.061.061 0 0 0-.0312-.0286ZM8.02 15.3312c-1.1825 0-2.1569-1.0857-2.1569-2.419 0-1.3332.9555-2.4189 2.157-2.4189 1.2108 0 2.1757 1.0952 2.1568 2.419 0 1.3332-.9555 2.4189-2.1569 2.4189Zm7.9748 0c-1.1825 0-2.1569-1.0857-2.1569-2.419 0-1.3332.9554-2.4189 2.1569-2.4189 1.2108 0 2.1757 1.0952 2.1568 2.419 0 1.3332-.946 2.4189-2.1568 2.4189Z"
/>
</svg>
</a>
<a
class="nav-x"
href="https://x.com/reatools"
aria-label="Follow REA on X"
title="Follow REA on X"
>
<svg
width="18"
height="18"
viewBox="0 0 24 24"
aria-hidden="true"
focusable="false"
>
<path
fill="currentColor"
d="M18.901 1.153h3.68l-8.04 9.19L24 22.846h-7.406l-5.8-7.584-6.638 7.584H.474l8.6-9.83L0 1.154h7.594l5.243 6.932ZM17.61 20.644h2.039L6.486 3.24H4.298Z"
/>
</svg>
</a>
</div>
</div>
</header>
<!-- website:header:end -->
<main id="main" class="container">
<div class="page-heading">
<p class="breadcrumb">
<a href="../../">Home</a> / <a href="../">Blog</a> / Models and RE
</p>
<p class="eyebrow">Essay · Draft for review</p>
<h1>Does reverse engineering need a bigger model?</h1>
<p class="page-meta">By N0zoM1z0 · 13 October 2026</p>
<div class="blog-takeaway">
<p class="eyebrow">Takeaway</p>
<ul>
<li>
<strong
>Model capability changes the hypotheses an agent can
find.</strong
>
Later sessions have opened functions that earlier work left
unresolved.
</li>
<li>
<strong
>A familiar compiler gives specialization something concrete to
learn.</strong
>
Some exact matches depend on narrow, reusable source patterns.
</li>
<li>
<strong>Give repository knowledge a fair comparison.</strong>
A smaller model with good retrieval may already know enough to
make progress.
</li>
<li>
<strong
>Train the next useful experiment, and test its oracle.</strong
>
The value of feedback depends on what the checker actually
verifies.
</li>
<li>
<strong
>Measure accepted reconstruction against time and cost.</strong
>
That is the result I want from the whole agent.
</li>
</ul>
</div>
</div>
<div class="article-layout">
<nav class="contents" aria-label="On this page">
<p>In this article</p>
<ul>
<li><a href="#model-capability">What better models changed</a></li>
<li><a href="#specialization">Why specialize?</a></li>
<li><a href="#repository-knowledge">Where experience lives</a></li>
<li><a href="#learning-search">Learning the next experiment</a></li>
<li><a href="#re-and-rl">RE and reinforcement learning</a></li>
<li><a href="#oracle">When the oracle is wrong</a></li>
<li><a href="#comparison">A comparison worth running</a></li>
<li><a href="#future-agent">What kind of agent?</a></li>
</ul>
</nav>
<article
class="article"
aria-label="Models and reverse engineering essay"
>
<section class="article-section" id="model-capability">
<h2>What better models changed</h2>
<p>
Since August 2026, I have been exploring how much reverse
engineering an agent can carry out with access to a program and a
way to check its work. Most of my experience comes from
reconstructing games, especially Touhou. The projects have also
become a record of what different models could make progress on.
</p>
<p>
Looking back through that record, there are functions that later
models closed after earlier sessions had left them unresolved. The
source changes make those breakthroughs more interesting than a
progress percentage does.
</p>
<h3>The temporary values had to stay alive together</h3>
<p>
One TH09 attack function was a byte short. Much of the logic was
already in place. The stack frame had the right size. But three
temporary vectors occupied different slots from the original, and
the compiled function still did not match.
</p>
<p>
A
<a
href="https://github.com/N0zoM1z0/th09/commit/de63c0f9121963f3a6b1ab5471c4878625fd3425"
>GPT-6-Sol checkpoint</a
>
recorded that residual after testing several ordinary source
arrangements. Later,
<a
href="https://github.com/N0zoM1z0/th09/commit/52929ed7c299f1a5f29cc13964e22510145fd616"
>GPT-6.1-Sol found a useful lifetime hypothesis</a
>.
</p>
<p>
The function calculated three vectors and copied each into an
animation's position. C++ keeps a returned temporary alive until
the end of the expression using it. Expressing the real operations
together kept those values alive together. The compiler could no
longer reuse the same storage for all three.
</p>
<p>
A separate, real collision workspace also needed to keep its own
storage. With that source arrangement, the seventh targeted
candidate in the closing session matched. A cold build confirmed
<strong
>the complete 1,436-byte function and all 44 encoded
fields</strong
>. Here, an exact reconstruction means that the maintained source,
compiled under the pinned historical toolchain, reproduces the
checked target function.
</p>
<p>
It was a useful discovery followed by several targeted tests. The
final result depended on both.
</p>
<h3>A different control-flow graph</h3>
<p>
Another TH09 function had a different obstacle.
<a
href="https://github.com/N0zoM1z0/th09/commit/f8d12d72aaf02212ee1b585a8f3f86d7ed000269"
>GPT-6.1-Sol's earlier work</a
>
reproduced two diagnostic regions, but the complete candidate was
1,510 bytes against a 1,491-byte target. The way its branches
shared a continuation still differed.
</p>
<p>
<a
href="https://github.com/N0zoM1z0/th09/commit/da33a646221198ceb7f3df2b96e2ca0e9b2f705f"
>GPT-6-Astra changed the surrounding control-flow graph</a
>. Completion and frame processing became complementary branches,
followed by one common frame increment and return. In that
context, the compiler produced the required block sharing. The
entire 1,491-byte function matched, and a
<a
href="https://github.com/N0zoM1z0/th09/commit/5f825b28a862f8e1a6d4aea2f78a42f04c09a1c0"
>recompile replay was accepted</a
>.
</p>
<p>
<strong
>A different representation made a different result
possible.</strong
>
That is one reason I take general model capability seriously. An
agent can spend a long time trying variations within a source
structure that is keeping it stuck.
</p>
<p>
These histories also contain accumulated work. Later sessions
inherited source and recorded failed experiments. They show the
discoveries and how we checked them. A controlled comparison would
tell us how much came from changing the model.
</p>
<p>
Even so, the cases leave me with a question. How much of this work
needs a model with broad reasoning ability? How much could a model
learn from repeated experience with this particular kind of code?
</p>
</section>
<section class="article-section" id="specialization">
<h2>Why might a specialist do well?</h2>
<p>
Touhou is an interesting place to ask. Much of the game code comes
from the same author, ZUN. That gives us a reasonable expectation
of recurring habits. The repositories contain more concrete
examples: related loops, helper functions and source arrangements
have supplied useful hypotheses across games.
</p>
<p>
The compiler contributes its own habits. Under a particular
version and set of options, small differences in source can
produce repeatable differences in machine code.
</p>
<p>
TH095 gave us a wonderfully awkward example:
<strong
>even the identifier backing a real local variable could change
where VC7.1 put it on the stack</strong
>. Moving the declaration alone did not solve the layout. An
earlier background function had already exposed the relevant
identifier bucket, and that experience became useful in
<a
href="https://github.com/N0zoM1z0/th095/commit/26bb64bdb093a13f73abd0ee8ae7ce199ee4658f"
>the reconstruction of <code>Supervisor::LoadDat</code></a
>.
</p>
<p>
Selecting the known backing identifier for the real file-size
variable put it and the character buffer in the required homes.
The buffer remained its genuine 128 bytes. All 151 bytes of the
function and its 15 relocations matched.
</p>
<p>
That is narrow knowledge. A general model has little reason to
arrive with a detailed repertoire of one old compiler's local
allocation behavior. A specialist could encounter it repeatedly.
It could learn which source variations are worth testing first.
</p>
<p>
In many of these final matching problems, we already understand
the behavior. The remaining question is which ordinary source form
this compiler turns into these instructions. That gives
specialization a specific job: propose plausible forms, then let
the target decide which survive.
</p>
<p>
There are limits to how narrowly we can define the repertoire.
TH08 uses VC7. TH095 and TH09 use VC7.1. TH04 uses Turbo C++ in a
segmented DOS environment. Its
<a
href="https://github.com/N0zoM1z0/th04/commit/6dce0a79d5b931f0e2a08475b90e0c33d2321b98"
>player reconstruction</a
>
needed another set of source-lifetime and linker-order hypotheses.
Shared authorship gives us a prior; each target tells us whether
that prior applies.
</p>
</section>
<section class="article-section" id="repository-knowledge">
<h2>Where should that experience live?</h2>
<p>
Before training anything, there is an obvious place to look: the
repository. In the
<a href="../touhou-reconstruction/">previous essay</a>, I wrote
about it becoming the project's working memory. Compiler lessons
belong there too.
</p>
<p>
An agent can retrieve a known result. It can inspect the source
that produced it and read which alternatives failed. That changes
its starting point without changing its weights.
</p>
<p>
A TH09
<a
href="https://github.com/N0zoM1z0/th09/commit/1eb843383941d00065622a9e353146c4bb96979e"
>GPT-6-Luna-max checkpoint</a
>
makes this worth taking seriously. It closed a 373-byte
enemy-spawn function using an ordinary loop with branch-local
failure handling. TH08's corresponding source family supplied the
hypothesis. TH09's own evidence established its bounds and calls,
and two cold builds confirmed the complete match.
</p>
<p>
<strong
>“The model did not know that compiler quirk” and “the model
could not use it” are different problems.</strong
>
Supplying a fact may solve the first. Generating a useful source
candidate with that fact may still need practice. Choosing what to
try after a failed compile is another skill again.
</p>
<p>
I would want a smaller general model with good retrieval in any
comparison. Otherwise, we might credit fine-tuning for an
advantage that came from giving one model a better library of
experience.
</p>
</section>
<section class="article-section" id="learning-search">
<h2>Learning the next useful experiment</h2>
<p>
In agentic reconstruction, the model proposes an explanation. The
program and its checks determine whether that explanation
survives. A failed candidate can be useful when it helps
distinguish the remaining possibilities.
</p>
<p>
This makes the temporary-vector example especially interesting to
me. The final source contains the successful arrangement. It does
not contain everything the search taught us.
</p>
<div class="evidence-table-wrap">
<table
class="evidence-table"
aria-label="Selected reconstruction experiments"
>
<thead>
<tr>
<th scope="col">Experiment</th>
<th scope="col">What its result taught us</th>
</tr>
</thead>
<tbody>
<tr>
<td>Use a typed position assignment</td>
<td>
The copy behavior improves, but the compiled source still
differs.
</td>
</tr>
<tr>
<td>Consume the returned vectors directly</td>
<td>
The function reaches the target size. Temporary storage
remains wrong.
</td>
</tr>
<tr>
<td>Group the real operations into one full expression</td>
<td>The returned values remain alive together.</td>
</tr>
<tr>
<td>Keep the real collision workspace separate</td>
<td>The complete function matches in a cold build.</td>
</tr>
</tbody>
</table>
</div>
<p class="caption">
Selected steps from the recorded Type18/24 search. The closing
session tested seven candidates; this table groups the lessons.
</p>
<p>
A useful training record would preserve the proposed change and
the result. It would also preserve why the result justified the
next experiment. An ineffective variation is part of that
experience, especially if a later agent would otherwise repeat it.
</p>
<p>
<strong
>I would want the model to learn how to use feedback.</strong
>
It should recognize when a change has no effect. It should notice
when a new mismatch points to a different cause. It should be able
to leave an unproductive source representation and inspect the
evidence again.
</p>
<p>
That also means keeping autonomy. The agent may need another
caller, a compiler experiment or an earlier project's source. A
rigid sequence of required rewrites would prevent some of the
decisions we want it to learn.
</p>
</section>
<section class="article-section" id="re-and-rl">
<h2>Why RE is interesting for reinforcement learning</h2>
<p>
A bounded reconstruction problem has an attractive property. With
the target and compiler pinned, many experiments produce quick,
repeatable feedback. Compile a candidate. Inspect what differs.
Decide what to try next.
</p>
<p>
Reinforcement learning could use that feedback to train the
decisions an agent makes during reconstruction. There is a
concrete result to optimize: a candidate accepted by a defined
check. We can also observe how much work it took to get there.
</p>
<p>
This direction already has research behind it.
<a href="https://aclanthology.org/2024.emnlp-main.203/"
>LLM4Decompile</a
>
studies models specialized for decompilation.
<a href="https://arxiv.org/html/2606.16162v1">AutoDecompiler</a>
trains multi-turn refinement using compiler and execution
feedback. Those results make the idea worth investigating. Their
functional recovery tasks differ from matching code emitted by a
particular historical compiler.
</p>
<p>
The experiment I have in mind would train a policy for that
narrower search. Given what we have learned so far, which source
hypothesis is worth testing next?
</p>
<p>
Other parts of RE are harder to package into a cheap loop. We may
still be establishing what a function owns. We may need a new
runtime measurement. In TH08, a
<a
href="https://github.com/N0zoM1z0/th08/commit/af9cb1d3e839b15a78b47ac1701506083cc82847"
>later collision divergence led back to a one-ULP numerical
difference</a
>
and the old x87 behavior. The productive hypothesis there was
partly about what to measure.
</p>
<p>
That is another plausible place for a broad model's strength.
First make the problem checkable. Then ask how much a learned
search policy can do with that check.
</p>
</section>
<section class="article-section" id="oracle">
<h2>When the oracle is wrong</h2>
<p>
An oracle is the reference or checker we use to accept a result.
Its answer can be repeatable while its coverage is incomplete.
</p>
<p>
TH08 already gave us an example. Some reconstructed functions had
passed their exact comparisons with wrong floating constants. The
instruction check accounted for relocated addresses, but checking
the literal payload depended on optional explicit attestation.
That left references whose values were never checked.
</p>
<p>
A
<a
href="https://github.com/N0zoM1z0/th08/commit/a393f400786e4cc6cbb1000af0dad3276da12c78"
>wider audit</a
>
examined all 1,548 floating-literal references and corrected
twelve stale rows across five accepted functions. In one case, the
bullet-spread increment was <code>1.0f</code> where the target
required <code>32.0f</code>.
</p>
<p>
<strong
>A learner rewarded by the old check could learn to produce the
wrong reconstruction.</strong
>
That is a consequence worth considering when we design an RL
environment. The observed problem here was an oracle defect; we
had not trained an RL model against it.
</p>
<p>
Functional checks need the same attention.
<a href="https://arxiv.org/html/2609.05370v1"
>Differential-fuzzing research on LLM decompilers</a
>
has found behavior differences beyond the supplied tests. An
accepted test result tells us something about the cases the test
actually exercises.
</p>
<p>
Before using a comparator as a reward, I would give it deliberate
failures to reject. The final acceptance check should stay outside
the candidate's editable source. A byte array copied from the
target may satisfy a naive score while teaching us nothing about
reconstructing the source.
</p>
<p>
<strong
>Improving the learner and improving its oracle belong to the
same research problem.</strong
>
Greater ability to optimize a check makes understanding that check
more important.
</p>
</section>
<section class="article-section" id="comparison">
<h2>A comparison worth running</h2>
<p>
I would start with a fixed VC7.1 task family. A strong general
model would be one baseline. A smaller general model would be
another. Then I would give the smaller model the relevant
repository knowledge and compare that with supervised
specialization, followed by an RL-trained version.
</p>
<p>
Each would get the same target evidence and tools. The
training-specific comparisons would use the same base model and
available knowledge. I would repeat the trials, since one lucky
candidate is a poor description of a search policy.
</p>
<p>
The starting point matters. Reconstructing a function from its
instructions and closing the last four differences in maintained
source are two useful tasks. I would measure both separately. A
specialist might be excellent at the second while a general model
does much of the work needed to reach it.
</p>
<p>
The test set also needs care. Related Touhou games share engine
code. Holding out a game's name would not be enough if nearly
identical functions had appeared in training. I would hold out
source families and keep their accepted answers out of both
training and retrieval.
</p>
<p>
For the outcome, I would count complete, independently validated
matches. One view would give every model the same candidate or
compile budget. Another would measure time and total cost to an
accepted result, including compilation. Training costs would need
their own accounting too.
</p>
<p>
A cheaper proposal can become an expensive workflow if it causes
more uninformative compiles. A slower model may pay for itself by
finding the right experiment sooner. Those are outcomes we can
measure.
</p>
<p>
I would also be cautious with a reward for “getting closer.” One
TH09
<a
href="https://github.com/N0zoM1z0/th09/commit/ab72fd77728293fc0beacfc656ca701b0e266016"
>replay-save candidate</a
>
already had the target's 1,825-byte length while 467 byte
positions differed. A shorter mismatch list can also move abruptly
when a branch encoding changes. Diagnostics help choose an
experiment; the full acceptance check decides whether it worked.
</p>
<p>
That experiment could produce an answer with conditions. A
specialist might win within a familiar compiler family. A general
model might win when the toolchain changes. Retrieval might
account for much of the apparent benefit of training. Each result
would tell us something useful about where to invest next.
</p>
</section>
<section class="article-section" id="future-agent">
<h2>What kind of agent does this suggest?</h2>
<p>
Perhaps the useful arrangement is a broad agent with access to a
specialist. It can decide when the task has become a familiar
compiler search, and ask the specialist for candidates. It can
still inspect the target or question the measurement when the
results stop making sense.
</p>
<p>
That would make specialization a tool the agent can choose. It
would preserve the freedom that made these investigations
productive in the first place.
</p>
<p>
In the previous essay, I described an industrial shift in how
reconstruction work can be organized. This question follows from
it. Once we can run many more experiments, we need to understand
which decisions require broad judgment and which improve through
repeated experience with a particular craft.
</p>
<p>
The strongest general model has earned its place in my workflow.
It has opened problems I had left unresolved. What I want to find
out next is how much of that work requires its breadth, and how
much could be handled by a model that has learned this particular
kind of reconstruction.
</p>
<p>
<strong
>The repositories give us a way to test the question.</strong
>
That is where I would like to take it next.
</p>
</section>
<section class="article-section" id="sources">
<details class="native-details">
<summary>Evidence and model attribution</summary>
<p>
The examples describe historical reconstruction checks recorded
in public commits. Their byte counts apply to the stated
functions, not whole-game runtime correctness. Source and
matching records were reviewed on 13 October 2026.
</p>
<p>
The TH09 label <code>gpt-dots</code> identifies GPT-6-Astra.
<code>gpt-web</code> changed with the model used at the time, so
that label alone does not identify an individual run. Explicit
model names in the other cited commits establish their recorded
attribution; the histories do not contain uniform per-run cost
or effort measurements.
</p>
<ul>
<li>
<strong>TH09 temporary lifetimes:</strong> the
<a
href="https://github.com/N0zoM1z0/th09/commit/de63c0f9121963f3a6b1ab5471c4878625fd3425"
>earlier context review</a
>
and
<a
href="https://github.com/N0zoM1z0/th09/commit/52929ed7c299f1a5f29cc13964e22510145fd616"
>complete cold reconstruction</a
>.
</li>
<li>
<strong>TH09 Front callback:</strong>
<a
href="https://github.com/N0zoM1z0/th09/commit/f8d12d72aaf02212ee1b585a8f3f86d7ed000269"
>non-exact diagnostic regions</a
>,
<a
href="https://github.com/N0zoM1z0/th09/commit/da33a646221198ceb7f3df2b96e2ca0e9b2f705f"
>Astra's new graph</a
>
and its
<a
href="https://github.com/N0zoM1z0/th09/commit/5f825b28a862f8e1a6d4aea2f78a42f04c09a1c0"
>accepted recompile replay</a
>.
</li>
<li>
<strong>Compiler knowledge:</strong>
<a
href="https://github.com/N0zoM1z0/th095/commit/26bb64bdb093a13f73abd0ee8ae7ce199ee4658f"
>TH095 identifier-bucket reuse</a
>,
<a
href="https://github.com/N0zoM1z0/th04/commit/6dce0a79d5b931f0e2a08475b90e0c33d2321b98"
>TH04 player source and linker order</a
>
and
<a
href="https://github.com/N0zoM1z0/th09/commit/1eb843383941d00065622a9e353146c4bb96979e"
>Luna's TH09 enemy-spawn closure</a
>.
</li>
<li>
<strong>Checks and diagnostics:</strong>
<a
href="https://github.com/N0zoM1z0/th08/commit/a393f400786e4cc6cbb1000af0dad3276da12c78"
>TH08 floating-literal audit</a
>,
<a
href="https://github.com/N0zoM1z0/th08/commit/af9cb1d3e839b15a78b47ac1701506083cc82847"
>TH08 numerical investigation</a
>
and
<a
href="https://github.com/N0zoM1z0/th09/commit/ab72fd77728293fc0beacfc656ca701b0e266016"
>TH09 replay-save reconstruction</a
>.
</li>
</ul>
<p>
The proposed specialist and RL comparisons are future
experiments. The project histories motivate them; no trained
specialist was evaluated for this essay.
</p>
</details>
</section>
</article>
</div>
</main>
<!-- website:footer:start -->
<!-- prettier-ignore -->
<footer class="site-footer">
<div class="container footer-inner">
<p>REA · Reverse Engineer Anything</p>
<div class="footer-links">
<a href="https://github.com/morluto/rea">Source</a
><a href="https://github.com/morluto/rea/blob/main/LICENSE">MIT license</a
><a href="https://discord.gg/GkcryMnJDM">Join the community</a
><a href="https://x.com/reatools">Follow us on X</a>
</div>
</div>
</footer>
<p class="sr-only" id="copy-status" role="status" aria-live="polite"></p>
<a class="back-to-top" href="#top" aria-label="Back to top">
<span aria-hidden="true">↑</span> Top
</a>
<!-- website:footer:end -->
</body>
</html>