CISAC & on Bluesky @stanfordcisac.bsky.social
@stanfordcisac
Stanford's Center for International Security and Cooperation produces knowledge to build a safer world and trains the next generation of security specialists.
ID: 150481419
http://cisac.stanford.edu/ 01-06-2010 01:43:04
11,11K Tweet
14,14K Followers
1,1K Following
The Helpful, Honest, and Harmless (HHH) principle is key for AI alignment but current interpretations miss contextual nuances. CISAC postdoc Max Lamparth & colleagues propose an adaptive framework to prioritize values, balance trade-offs, & enhance AI ethics arxiv.org/abs/2502.06059