Claude Code user files complaint over repeated false-positive safety refusals killing sessions
garon1576 · ghdev · 2026-11-05
A developer filed issue #107248 on anthropics/claude-code alleging repeated false-positive safety refusals in the Claude desktop app (Opus, Windows) during routine work like checking PRs and refreshing a usage-status file for a GPU training job.
The blocked session coordinated 15+ work sessions, halting merges and task assignment, and the expired usage file auto-killed a training job. The user asks Anthropic to explain what triggered the refusal, add an appeal/recovery path short of starting a new session, not bill usage lost to false positives, and reduce refusal false positives in long dev sessions.
More from coding & agent
- Voice agent stack consolidation: OpenAI's vertical integration could squeeze out LiveKit and pipecat layers — juberti · 2026-11-05
- Scrapling on GitHub: 96.8k stars, one framework from single request to full crawl — abhishek__AI · 2026-11-05
- Automating a Spotify-to-YouTube Music migration with a single Codex prompt — burkov · 2026-11-05
- Peking University and NVIDIA use a coding agent to replace teleoperation for robot data — DAGroup-PKU · 2026-11-05
- Siri AI opens to all developers: Larder sample app shows full integration — rudrank · 2026-11-05
- Two recordings, 32 videos: dev scripts FFmpeg overlays via Copilot — DanWahlin · 2026-11-05