Users report Claude auto mode now prompts approval for nearly every Bash command
teropa · x · 2026-09-04
Multiple users report that Claude's auto mode appears to have been dramatically rolled back: nearly every Bash command now triggers an approval prompt, making the experience extremely annoying. One replying user jokes about pretending to read every permission again 'like it's 2025.'
The exact reason from Anthropic is unclear; this looks like a significant tightening of the model's permission guardrails.
More from Models
- Prompting Fable 5.1 with embodied mannerisms like *shrugs* makes roleplay flow better — repligate · 2026-09-05
- Astra appears in ChatGPT/Codex on Windows but not Mac, same account — cheesecakegood · 2026-09-05
- No usage reset on GPT-6 Astra launch day, developer calls out OpenAI — tobowers · 2026-09-05
- GPT-6 Astra Launch Marred by Outages, OpenAI Hands Out Daily Token Reset Vouchers — 新智元 · 2026-09-05
- Debate: Models Fuzzily Recall Concepts, Not Text — SAE Features vs Edit-Distance Memorization — voooooogel · 2026-09-05
- Blogger feeds GPT6 Astra a PPT template, gets 30 conference slides with the right avatar — vista8 · 2026-09-05