StarZero All shows Try the podcast clipper →

mechanistic interpretability

3 statements across 2 episodes · 3 bullish · 0 bearish · 2 people on the record · first statement May 28, 2026 by Maxim Bar Kogan · across every show →

Everything said about mechanistic interpretability, oldest first

May 28, 2026 bullish
Prediction Not checkable as stated
Smarter AI models will make mechanistic interpretability and tracking more effective
“But as we're starting to have models that are much smarter than us, at least in some important ways, we think that we'll be able to start tracking mechanistic capability much more effectively.”
Maxim Bar Kogan May 28, 2026 ▶ 22:44 Building an AI Guardian for Enterprise with Onyx Security CEO Maxim Bar Kogan
May 28, 2026 positive
Opinion
Understanding model weights and activations is essential for AI safety
“We believe that understanding the internal weights and activations, what is the internal structure, the mathematical structure of these systems is going to be at least part of the solution.”
Maxim Bar Kogan May 28, 2026 ▶ 21:49 Building an AI Guardian for Enterprise with Onyx Security CEO Maxim Bar Kogan
Jun 10, 2026 bullish
Prediction Not checkable as stated
Alex Rives: Mechanistic interpretability will uncover biology inside protein models
“The hope is that you kind of really learn the underlying basis for how it's making the predictions, and so you open up the black box and you can actually understand kind of the biology that the model is representing.”
Alex Rives Jun 10, 2026 ▶ 16:49 “Curing All Disease by next century is too conservative" - Mark Zuckerberg
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 100 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.

Try the podcast clipper Learn more