Dev admits 'dangerously bypassing permissions' with coding agents from day one
brandon_galang · x · 2026-10-29
Developer brandongalang confesses he has used 'dangerously bypass permissions' mode with AI coding agents since day one, never going through a 'manual mode' phase, and asks if others do the same. The post captures a real workflow habit among heavy users who skip safety confirmations entirely.
More from coding & agent
- Weaviate Podcast: MIT PhD's "Machine Studying" lets always-on agents prep without knowing the task — CShorten30 · 2026-10-29
- Dev rebuilds Slack as video with Cursor agents and computer use — mattyp · 2026-10-29
- Deepgram acquires Daily, spins up independent Pipecat Foundation — charles_irl · 2026-10-29
- Don't force multi-agent for enterprise: a one-night RPA script beats slow, costly agents — sujingshen · 2026-10-29
- After 30 approval prompts, 'yes' to everything sent a broken release to his whole list — latent_lurker8587 · 2026-10-29
- Nat Eliason builds a personal AI writing system in one Claude Code session — nateliason · 2026-10-29