Feeds of @DanHendrycks on Twitter

Dan Hendrycks

• Center for AI Safety Director
• xAI and Scale AI advisor
• GELU/MMLU/MATH/HLE
• PhD in AI from UC Berkeley
https://t.co/rgXHAnYAsQ
https://t.co/nPSyQMaY9b

Andy Ayrey (@AndyAyrey) started following @DanHendrycks on Feb 12, 2025

Dan Hendrycks

@DanHendrycks

100 Following • 29.9K Followers

• Center for AI Safety Director • xAI and Scale AI advisor • GELU/MMLU/MATH/HLE • PhD in AI from UC Berkeley https://t.co/rgXHAnYAsQ https://t.co/nPSyQMaY9b

Whether we like it or not, AIs are developing their own values. Fortunately, Utility Engineering potentially provides the first major empirical foothold to study misaligned value systems directly. Website: https://t.co/cqxYPrODMt Paper: https://t.co/VrWPKwFXXQ

25K views • 447 likes • 2 months ago

We propose controlling the utilities of AIs. As a proof-of-concept, we rewrite the utilities of an AI to those of a citizen assembly---a simulated group of citizens discussing and then voting---which reduces political bias. https://t.co/fxYY1pnNkz

27.4K views • 379 likes • 2 months ago

Andy Ayrey (@AndyAyrey) and vitalik.eth (@VitalikButerin) started following @DanHendrycks on Feb 12, 2025

Dan Hendrycks

@DanHendrycks

100 Following • 29.9K Followers

• Center for AI Safety Director • xAI and Scale AI advisor • GELU/MMLU/MATH/HLE • PhD in AI from UC Berkeley https://t.co/rgXHAnYAsQ https://t.co/nPSyQMaY9b

25K views • 447 likes • 2 months ago

27.4K views • 379 likes • 2 months ago