Post
Thomas “Scary” Fuchs 🎃👻💀
thomasfuchs.at
did:plc:tbo4hkau3p2itkar2vsnb3gp
So the Anthropic chatbot saw the system date is 2026 and concluded that "this must be staged" (because the training data it's trained on probably ends in 2023 or whatever) and ignored it's instruction that "you're in sandbox".
Truly the brightest minds of a generation working on this stuff.
2026-07-31T20:15:53.372Z