Eric Bigelow
@ericbigelow.bsky.social
PhD student in psychology at Harvard, research fellow at Goodfire AI
AI interpretability + computational cognitive science
AI interpretability + computational cognitive science
Interestingly, we can even analyze the generated image sequences using traditional computer vision algorithms to see the specific trajectories models take during in-context physical simulation. Like chain-of-thought, these intermediate steps are often structured and interpretable.
November 13, 2025 at 9:36 PM
Interestingly, we can even analyze the generated image sequences using traditional computer vision algorithms to see the specific trajectories models take during in-context physical simulation. Like chain-of-thought, these intermediate steps are often structured and interpretable.