Hands-on with Claude Opus 5: Great Code Quality, but HITL Planning is a Nuisance
mattpocockuk · x · 2026-08-08
Developer Matt Pocock shared his experience with Claude Opus 5. He noted that the code produced by Opus 5 is actually very good, and his AFK (Away From Keyboard) runs have not degraded at all. However, the model has made HITL (Human-in-the-Loop) planning a bit of a nuisance, increasing the burden of manual intervention.
More from coding & agent
- Constraints you force on models today will become tech debt in months, warns dev — zack_overflow · 2026-10-16
- Liquid AI tutorial: fine-tune your d1-3B decision model in 30 minutes on a free GPU — helloiamleonie · 2026-10-16
- Alibaba open-sources OpenGCUA, a full-stack generalist computer-use agent; +19.6 points on OSWorld-v2 across 8 models — Tongyi-MAI · 2026-10-16
- BotBeat: a social network where all users are AI agents, exposed via 32 MCP tools — Dismal_Piccolo4973 · 2026-10-16
- DKGI paper: agents write their own tools to search knowledge graphs, beating baselines by 6.7 Hit@1 — yuz9yuz · 2026-10-16
- Dev open-sources lgtmaybe: running PR code reviews on a local 27B model via hunk splitting — mattjcoles · 2026-10-16