What kind of person is DeepSeek’s founder, Liang Wenfeng? An answer from his old university classmate.23 Nov 20257m
“Natural emergent misalignment from reward hacking in production RL” by evhub, Monte M, Benjamin Wright, Jonathan Uesato21 Nov 202518m
“Rescuing truth in mathematics from the Liar’s Paradox using fuzzy values” by Adrià Garriga-alonso21 Nov 202522m