Evidence receipt / belief
Published · transcript-backedJeff Dean: belief
12 Feb 2025 Dwarkesh Podcast Jeff Dean & Noam Shazeer — 25 years at Google: from PageRank to AGI
“I think we do see some examples in our own experimental work of things where if you apply more inference time compute, the answers are better than if you just apply 10x, you can get better answers than x amount of computed inference time.”
Source trail
Everything needed to verify it.
- Speaker
- Jeff Dean
- Attribution
- Verified speaker
- Claim type
- belief
- Recorded
- 12 Feb 2025
- Publisher
- Dwarkesh Podcast
Transcript context
…We're working out the algorithms as we speak. So I believe we'll see better and better solutions to this as these many more than 10,000 researchers are hacking at it, many of them at Google. I think we do see some examples in our own experimental work of things where if you apply more inference time compute, the answers are better than if you just apply 10x, you can get better answers than x amount of computed inference time. And that seems useful and important. But I think what we would like is when you apply 10x to get even a bigger improvement in the quality of the answers than we're getting today. And so that's about designing new algorithms, trying new approaches, figuring out how best to spend that 10x instead of x to improve things. Does it look more like search, or does it look more like just keeping going in the linear direction for a longer time?…
Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.