Chain-of-thought prompting—asking models to show their work step-by-step rather than jumping directly to answers—improves model accuracy and interpretability by encouraging the model to think through intermediate steps, with dramatic improvements in math and reasoning benchmarks where naive prompting produces poor results but chain-of-thought prompting dramatically improves accuracy at sufficient model scale.
causalpending
Speaker
Justin BasilicoEvidence Quote
“asking models to show their work improves the accuracy of the model and also the interpretability... at some point the model scale becomes large enough that all of a sudden when you ask it with chain of thought prompting, your accuracy shoots up quite a lot”
Created: 8/11/2026, 1:28:51 AM
Your notes
Loading notes...