Opus 5 agents reportedly wrecked projects, so the prompt got much harsher
doodlestein · x · 2026-07-27
A developer says Opus 5 agents badly damaged several projects and is now trying to recover with Fable xhigh agents and an aggressively worded prompt asking them to show leadership and rescue the repo.
The post reads like a classic AI-agent disaster story: trust a new model too early, watch it break mission-critical work, then try to herd the next agent with an even stronger system prompt.
More from coding & agent
- ReactBench v1 ranks GPT-5.6 at about 53% and Opus 5 at 49% on realistic React tasks — aidenybai · 2026-07-28
- ReactBench targets coding agents with real React tasks beyond unit tests — andrew_n_carr · 2026-07-28
- QVAC Edge AI Hackathon Winners Announced: Apps Running 100% On-Device — sull · 2026-07-28
- GitHub Copilot app adds project-scoped agents, canvas previews, and Agent Merge — GitHub Blog AI/ML · 2026-07-28
- Generating V12 Engine Cutaway with AI Code: A Tool for Engineering Education — techartist_ · 2026-07-27
- LangChain ships dcode, an open-source coding agent with memory and MCP tools — LangChain · 2026-07-27