Goodfire(@GoodfireAI):LLMs are like Schrödinger’s cat: many possible trajectories, but you only see one outcome per run. To really understand models, and debug where they go wrong, you can find the "forking tokens" that lead to different trajectories. Our new research does this 100x more efficiently!

Goodfire

@GoodfireAI

Using interpretability to understand, learn from, and design AI.

加入 August 2024

44 正在關注 27.1K 粉絲

Goodfire@GoodfireAI

2026.08.26 17:10

LLMs are like Schrödinger’s cat: many possible trajectories, but you only see one outcome per run. To really understand models, and debug where they go wrong, you can find the "forking tokens" that lead to different trajectories. Our new research does this 100x more efficiently!