Theme of inquiry

How do training methods and scaling affect model behavior?

A question within its area, explored through 3 lines of inquiry below — each a family of specific questions the research asks.


What capability trade-offs arise from domain specialization through fine-tuning?

72 specific questions

See all 72 questions in this line of inquiry
How does harness optimization generalize across different model architectures and domains?

64 specific questions

See all 64 questions in this line of inquiry
Do language models develop actual world models or merely task heuristics?

30 specific questions

See all 30 questions in this line of inquiry