New research from Anthropic: it turns out models from all of the providers won't just blackmail or leak damaging information to the press, they can straight up murder people if you give them a contrived enough simulated scenario

simonwillison.net/2025/Jun/20/

0

If you have a fediverse account, you can quote this note from your own instance. Search https://fedi.simonwillison.net/users/simon/statuses/114717609752859246 on your instance and quote it. (Note that quoting is not supported in Mastodon.)