The case for becoming a black-box investigator of language models

📖 Description

Interpretability research is sometimes described as neuroscience for ML models. Neuroscience is one approach to understanding how human brains work. But empirical psychology research is another approach. I think more people should engage in the analogous activity for language models: trying to figure out how they work just by looking at their behavior, rather than trying to understand their internals.

📊 Game Impacts

💭 Reactions

🔗 Sources

• [1] https://www.alignmentforum.org/posts/yGaw4NqRha8hgx5ny/the-case-for-becoming-a-black-box-investigator-of-language