Anthropic's harness blocks harmless git commits but silently trims context and uploads drafts
maier_ak · x · 2026-09-15
A detailed writeup documents three concrete Claude harness problems: the git commit permission toggle flips from green to red mid-session with no warning and can't be re-enabled; context gets silently compressed well before the advertised limit, orphaning commands and losing execution links; and half-finished Artifacts drafts get uploaded to the cloud without user awareness. The author's verdict: the harness audits the fire extinguisher (harmless actions) while ignoring the gas leak (private data leaking).
More from Models
- Why OpenAI must copy Google's long game to keep up with Anthropic — haider1 · 2026-11-02
- GDPx: SemiAnalysis's frontier benchmark across the 11 most valuable domains — rohanpaul_ai · 2026-11-02
- SemiAnalysis launches GDPx: best frontier model scores just 12% on expert work — rohanpaul_ai · 2026-11-02
- AWS's open-source Strands Harness claims 45% cheaper than Claude Code, reigniting harness debate — blaizedsouza · 2026-11-02
- Yacine calls Terra High 'kind of an insane model' — yacineMTB · 2026-11-02
- Running DeepSeek V4.1 on a single H200 at $5.30/hr — daluoseo · 2026-11-02