Dev claims Opus 5.5 one-shotted a stubborn 1,800-line function after 100+ agent-hours by GPT models
almmaasoglu · x · 2026-09-28
Developer banteg reports that Claude Opus 5.5 solved a stubborn 1,800-line playerupdate function in his Crimsonland decompilation project in a single shot. The codebase had accumulated 100+ agent-hours since July: 50 hours by gpt-5.6-sol, 20 by gpt-6-astra, and 36 by Opus 5.5 (unconfirmed GPT version names). When asked if the hype was real, he confirmed it delivered.
Related event: Opus 5.5 Cracks 1,800-Line Decompiled Function in One Pass(3 posts)→
More from coding & agent
- WebArena-Pro launches: 300-task multimodal web-agent benchmark across 20 apps — xhluca · 2026-11-16
- Self-improving agent papers this week: agents learn the benchmark, not the task — TheTuringPost · 2026-11-16
- 1,000 agents, one week, 630k lines: HF builds a weights-free Python chatbot — _lewtun · 2026-11-16
- One-person content agency targets $30K/mo with 11 AI agents — full playbook — VibeMarketer_ · 2026-11-16
- Hugging Face releases definitive fine-tuning guide for 3D generation model TRELLIS.2 — ariG23498 · 2026-11-16
- Continual-ARC: lifelong ARC-AGI stream finds agent harness persistence rarely beats simple caching — unifyai · 2026-11-16