AI Alignment, Moral Philosophy, Value Systems, Practical Wisdom
Actual Status of AI Agents Safety: In Short — Not Good
pub.towardsai.net·18h
Some mistakes in thinking about AGI evolution and control
lesswrong.com·1d
LAI #86: LLM Gaps, Agent Design, and Smarter Semantic Caching
pub.towardsai.net·1d
“Opponent shaping” as a model for manipulation and cooperation
lesswrong.com·23h
TAI #163: AI Unlocking History’s Secrets; Deepmind’s Aeneas Continues A Recent Trend
pub.towardsai.net·3d
Dimensions of logical time as economic strategies
lesswrong.com·2d
Loading...Loading more...