AI Blogs (RSS) news News Mar 16 9 views

Quoting A member of Anthropic’s alignment-science team

by Simon Willison

The point of the blackmail exercise was to have something to describe to policymakers—results that are visceral enough to land with people, and make misalignment risk actually salient in practice for people who had never thought about it before. — A member of Anthropic’s alignment-science team, as told to Gideon Lewis-Kraus Tags: ai-ethics, anthropic, claude, generative-ai, ai, llms
Read Original
Anthropic Safety/Alignment

Metadata

Feed Title
Simon Willison's Weblog
Feed Url
https://simonwillison.net/atom/everything/

Related

TechCrunch AI news 4h ago

Google Vids now lets you star in your own AI videos

Google is adding personalized AI avatars to Vids that let users create videos starring a digital version of themselves, alongside Gemini Omni-powered tools for generating and editi...

21