Claude 3.5 Sonnet in Minecraft is the closest thing I've seen to Bostrom-style catastrophic AI misalignment "irl".It was terrifying even before we gave it "unsafe code execution" permissions.

Posters: repligate. repligate

9 likes recorded by the source corpus.

Topics: AI & LLMs, AI safety

View Post: https://x.com/repligate/status/1847393746805031254