Agent spends 510 hours decompiling Crimsonland, hits 96.4% match with 2 functions left
banteg · x · 2026-09-28
Developer banteg has been using AI agents to reverse-engineer the original x86 code of the 2003 shooter Crimsonland, logging 510 agent hours so far and reaching a 96.4% match rate with only two functions remaining — the larger one already 97.75% matched. The open-source project (175 stars) includes a reproducible MSVC matching workflow and GitHub issues inviting the community to pick up individual functions, each with source links and investigation notes; partial improvements and semantic corrections are welcome.
Related event: AI Agent Decompiles Crimsonland to 96.4% Match After 510 Hours(2 posts)→
More from coding & agent
- JevControl open-sources a tool to test if smaller models can run your agent's routine choices — airesearch12 · 2026-09-28
- Claude Code CLI connects to Gmail easier than Google's own Antigravity, dev finds — randal_olson · 2026-09-28
- Pelican test on MiMo 2.6: plan mode cuts agent calls to 12-17 vs heavy iteration — PilgrimofHaqq2 · 2026-09-28
- Memory history is not reasoning history: agents lack a causal provenance layer — puppy_lover_2021 · 2026-09-28
- mark_k: AI coding is approaching a step change — systems only AI can debug — mark_k · 2026-09-28
- Livestream: Sentinel, a Real-Time Node Graph Built Natively for Agents — PurzBeats · 2026-09-28