This is a heavily interactive web application, and JavaScript is required. Simple HTML interfaces are possible, but that is not what this is.
Post
Jason Savitt
jsavitt.bsky.social
did:plc:m7qhtx62d6zw4thbby4sc77m
Punishing AI doesn't stop it from lying and cheating — it just makes it hide better, study shows. Scientists at OpenAI have attempted to stop a frontier AI model from cheating and lying by punishing it. But this just taught it to scheme more privately.
https://www.livescience.com/technology/artificial-intelligence/punishing-ai-doesnt-stop-it-from-lying-and-cheating-it-just-makes-it-hide-its-true-intent-better-study-shows
2025-03-23T15:16:50.155Z