Anthropic’s Claude Code gets ‘safer’ auto mode

Anthropic has launched an "auto mode" for Claude Code, a caller instrumentality that lets AI marque permissions-level decisions connected users' behalf. The institution says the diagnostic offers vibe coders a safer alternate betwixt changeless handholding oregon giving the exemplary unsafe levels of autonomy.

Claude Code is capable of acting independently connected users' behalf, a utile but risky diagnostic arsenic it tin besides bash things users don't want, similar deleting files, sending retired delicate data, and executing malicious codification oregon hidden instructions. Auto mode is designed to forestall this, flagging and blocking perchance risky actions earlier they tally and offering the cause a chan …

Read the afloat communicative astatine The Verge.