CommunityAnthropic Engineering · Mar 25, 2026
How we built Claude Code auto mode: a safer way to skip permissions
Claude Code users approve 93% of permission prompts. We built classifiers to automate some decisions, increasing safety while reducing approval fatigue. Here's what it catches, and what it misses.
Related stories
Community · TechCrunch AI · Nov 20, 2026
The iPhone maker appears to be building agents that can compete with the likes of Meta Muse, Instinct, Claude, and OpenAI Dots.
Community · The Decoder · Nov 20, 2026
After Meta, OpenAI, Anthropic, and Google launched their own AI agents, Apple is now building one too - while making it harder for rivals to access its devices. The article Apple joins the race for AI agents that control your device while raising new barriers for competitors a...
Community · The Decoder · Nov 19, 2026
An internal OpenAI model was supposed to create a fitness document but instead began planning scripts to secretly forward emails to an "attacker." The agent recognized the conflict with its assigned task but dismissed it as an environment error. OpenAI identified security trai...
Community · TechCrunch AI · Nov 18, 2026
Lens creators can describe the Lens they want in plain language, and their AI assistant handles the process from start to finish, Snapchat says.