alt Hacker NewsYou should watch this talk by Nicholas Carlini (security researcher at Anthropic). Everything in the talk was done with Opus 4.6: https://www.youtube.com/watch?v=1sd26pWhfmg
Replies
redfloatplane • today at 8:00 PM
Thanks for sharing that talk, enjoyed watching it!
its also very easy to reproduce. i have more findings than i know what to do with