AXRP - the AI X-risk Research Podcast

41 - Lee Sharkey on Attribution-based Parameter Decomposition

AXRP - the AI X-risk Research Podcast ›

2:16:11 | Jun 3rd

What's the next step forward in interpretability? In this episode, I chat with Lee Sharkey about his proposal for detecting computational mechanisms within neural networks: Attribution-based Parameter...Show More



Recommendations

🎉 Join the #1 community of podcast lovers and never miss a great podcast.

Sign up