Using weaker language models can improve AI alignment efficiently.
Leitian Tao, Yixuan Li
― 6 min read
Leitian Tao
CodeLutra teaches models to learn from their successes and failures.
Leitian Tao, Xiang Chen, Tong Yu
― 7 min read
Cutting edge science explained simply
Using weaker language models can improve AI alignment efficiently.
Leitian Tao, Yixuan Li
― 6 min read
CodeLutra teaches models to learn from their successes and failures.
Leitian Tao, Xiang Chen, Tong Yu
― 7 min read