Long-Task Coding Agents Continue to Improve
generativist · x · 2026-07-11
The quote mentions that the author previously let Opus 4.5 handle a task for a month, and its task trajectory gradually "drifted apart" after continuous self-driving.
In comparison, he feels that Fable and Terra show more tangible progress on existing codebases, indicating that these models/agents are becoming more reliable for long-chain development tasks.
More from coding & agent
- Hugging Face wraps 6-month Training Agents series with open recordings and code — SergioPaniego · 2026-10-26
- Agent verified 'success' after double-voting: a lesson in harness vs model bugs — TejasKumar_ · 2026-10-26
- diginomica: agentic automation hype is overdone, and 'The Hackening' of enterprise security has begun — jonerp · 2026-10-26
- 'Vibe verification': ~60% of AI-written formal specs prove the wrong property — basedjensen · 2026-10-26
- Devin launches Security suite powered by Claude Mythos with $100M+ credits — DevinAI · 2026-10-26
- HackBench injects reward hacks into agent trajectories to stress-test monitors — DanielKhashabi · 2026-10-26