AlphaFold 2

part of AlphaFold

3 statements across 1 episodes · 0 bullish · 0 bearish · 1 people on the record · first statement Jul 15, 2025 by John Jumper · said 5 times in 2 episodes since 2025 · across every show →

Mentions by year

brought up most by John Jumper (4), Demis Hassabis (1)

tap a year for its mentions
00214120252026episodesmentions
01120252026episodes it came up in
0020.54120252026episodesmentions per episode

every mention, scene by scene, with the transcript →

Everything said about AlphaFold 2, oldest first

Jul 15, 2025
Assertion Supported
Jumper: AlphaFold 2 architecture on 1% of data matched AlphaFold 1
“The Al Qureshi lab, did a very, ah, careful experiment, where they took AlphaFold II, the architecture, and they trained it on one percent of the available data. And they could show that alpha fold two trained on one percent of the data was as accurate or more…”
John Jumper Jul 15, 2025 ▶ 13:37 Nobel Laureate John Jumper: AI is Revolutionizing Scientific Discovery · Y Combinator
Jul 15, 2025
Assertion Supported
Jumper: Equivariance explains only 2-3 GDT of AlphaFold 2's 30-point gain
“The sixth row there, no IPA, invariant point attention, that removes all the equivariance in alpha fold, and it hurts a bit, but only a bit. Alpha fold itself on this GDT scale that you can see on the left graph, alpha fold two was about 30 GDT better than alp…”
John Jumper Jul 15, 2025 ▶ 15:34 Nobel Laureate John Jumper: AI is Revolutionizing Scientific Discovery · Y Combinator
Jul 15, 2025
Assertion Partly supported
Jumper: AlphaFold 2's final model trained on 128 TPUv3s for two weeks
“The final model itself was a 128 TPU V three cores, roughly equivalent to a GPU per core for two weeks.”
John Jumper Jul 15, 2025 ▶ 11:46 Nobel Laureate John Jumper: AI is Revolutionizing Scientific Discovery · Y Combinator
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 300 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.