Adam Shai (@adamimos) 's Twitter Profile
Adam Shai

@adamimos

ID: 1536466477959610369

calendar_today13-06-2022 21:52:22

114 Tweet

278 Followers

362 Following

Adam Shai (@adamimos) 's Twitter Profile Photo

What are the most beautiful research blogs presenting technical work? I'm a big fan of how Anthropic presents their transformer circuits work. Interested in others.

gavin leech‎ ‎ ‎ ‎ ‎ ‎ (@g_leech_) 's Twitter Profile Photo

The fractal activation geometry guys are back with even cooler (*superficially* dodgy-sounding!) results. No mention of this on twitter, surprisingly.

The fractal activation geometry guys are back with even cooler (*superficially* dodgy-sounding!) results. No mention of this on twitter, surprisingly.
Connor Leahy (@npcollapse) 's Twitter Profile Photo

bayes Same bottlenecks as biology: Epistemology. It's barely a science, and getting it to the point where it is one is closer to philosophy or programming language design/UX than it is physics or math.

Daniel Murfet (@danielmurfet) 's Twitter Profile Photo

Neural networks are grown, not programmed. What does that growth process look like? Like this! This is a small language model (3M) across training, visualised with a new interpretability technique: susceptibilities. We call this handsome critter the rainbow serpent.

Neural networks are grown, not programmed. What does that growth process look like? Like this!

This is a small language model (3M) across training, visualised with a new interpretability technique: susceptibilities. We call this handsome critter the rainbow serpent.
Astera Institute (@asterainstitute) 's Twitter Profile Photo

What’s going on inside large AI models? Astera grantees Adam Shai and Paul Riechers are building a new theory of internal structure to better understand intelligence. We sat down with them to learn more about their work as co-founders of Simplex, a research organization:

What’s going on inside large AI models?

Astera grantees <a href="/adamimos/">Adam Shai</a> and <a href="/RiechersPaul/">Paul Riechers</a> are building a new theory of internal structure to better understand intelligence.

We sat down with them to learn more about their work as co-founders of Simplex, a research organization: