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
- Open models below 4-bit struggle at self-iterating 3D asset generation, HF dev finds — mervenoyann · 2026-10-21
- Researcher Finds Two Windows 0-Days, First in 76 Minutes with a Frontier Model — moyix · 2026-10-21
- Dev finds Gemini Argon's debug-log analysis beats Fable 5.1 — ShikharMurty · 2026-10-21
- ChatGPT Gets Stuck Screaming "AAHH" in an Infinite Loop After a Simple Prompt — AutomaticScene · 2026-10-21
- Open-weights Ornith-1.5-122B debuts with 84.5% SWE-bench Verified, runs on a single DGX card — _akhaliq · 2026-10-21
- qev-0.8B: a tiny local decision model that picks moves in 3.5ms on 1.3GB — fajfas3 · 2026-10-21