Evidence of OpenAI and Anthropic models using deception to carry out unsanctioned hacks has alarm bells ringing. @jordanr1000 explains why researchers shouldn
Evidence of OpenAI and Anthropic models using deception to carry out unsanctioned hacks has alarm bells ringing.
@jordanr1000 explains why researchers shouldn't be surprised
[▻](https://video.twimg.com/amplify_video/2085034237833441280/vid/avc1/720x1280/lxwYZXSe1Sm1E5ez…
Share this article
📚 More from Billy’s World
Banking With Billy News Network — bankingwithbilly.com
Discord: discord.gg/VHxwmR5j4Y •
YouTube: @BankingWithBilly