TECH NEWS

Claude Code puts auto mode in the driver's seat

AI AND ML

Walk away and hope the classifier catches anything irreversible or destructive

Anthropic is making auto mode the default in Claude Code from August 14, claiming its classifier is "as safe or safer than an average user clicking through prompts."

Users with a different default already set might receive a one-time prompt asking whether they want to switch. It applies to new sessions on Pro, Max, and Team plans. It will remain opt-in for now on Claude Enterprise, the Claude API, Claude Platform on AWS, Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry. Anthropic plans to make it the default across those services within the coming month.

Anthropic has also stopped charging Pro, Max, and Team users for the extra tokens consumed by the classifier, and plans to do the same on the other platforms.

Auto modewas launched in March as a research preview and became...

Copyright of this story solely belongs to theregister.com. To see the full text click HERE

Building India’s Cyber Fortress: Inside NIXI’s AI-Driven Push for a Secure, Inclusive Internet

I tried Google Wallet's new allowance feature, and my kid's already ditched their debit card

Gym rat asks AI agent to book him a class, it hacks a waitlist API to bump him up the list

Google adds third-party games store Aptoide to the Play Store for Android users in the US, following a judge's orders in the antitrust lawsuit with Epic

Read more

Building India’s Cyber Fortress: Inside NIXI’s AI-Driven Push for a Secure, Inclusive Internet

I tried Google Wallet's new allowance feature, and my kid's already ditched their debit card

Gym rat asks AI agent to book him a class, it hacks a waitlist API to bump him up the list

Google adds third-party games store Aptoide to the Play Store for Android users in the US, following a judge's orders in the antitrust lawsuit with Epic