Evidence receipt / commitment
Published · transcript-backedAdam Marblestone: commitment
30 Dec 2025 Dwarkesh Podcast Adam Marblestone — AI is missing something fundamental about the brain
“You can’t do interp on a hypothetical model-based reinforcement algorithm like the brain that we will eventually converge to when we do AGI.”
Source trail
Everything needed to verify it.
- Speaker
- Adam Marblestone
- Attribution
- Verified speaker
- Claim type
- commitment
- Recorded
- 30 Dec 2025
- Publisher
- Dwarkesh Podcast
Transcript context
…What is the timeline on this? Presumably the idea of this is, first, to inform the development of AI. You want to be able to figure out how we get AIs to want to care about what other people think of its internal thought pattern. But interp researchers are making progress on this question just by inspecting normal neural networks. There must be some feature… You can do interp on LLMs that exist. You can’t do interp on a hypothetical model-based reinforcement algorithm like the brain that we will eventually converge to when we do AGI. Fair. But what timelines on AI do you need for this research to be practical and relevant?…
Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.