James Zou

speaker

371 appearances 1 recordings 1 series first heard Dec 2024 last heard Dec 2024

James Zou’s voice in public audio — every appearance, attributed to the second.

Trend

recordings per month · last 12 months

No recordings in the last 12 months.Older appearances are listed below; set an alert to hear about the next one.

Appearances

newest first · ▶ plays the moment

"The Cognitive Revolution" · Breakthroughs in AI for Biology: AI Lab Groups & Protein Model Interpretability with Prof James Zou · 18 Dec 2024 podcast

So the level of feedback that we provide to the professor then

This tends to be these more high-level feedback.

We'll say, okay, so in general we're interested in SARS-CoV-2 because that's important.

We can also provide feedback like, okay, you know, we don't have a large experimental budget, right?

So we want things that are uh relatively uh fast and easy to validate, right?

But we don't actually tell the professor agent that you have to do

A, B, and C, right?

So that's the workflow is basically designed by by the virtual lab.

Yeah.

I think where the expertise of the human is is to also like look over the shoulder of all these different agents and provide some constructive feedback to say that maybe here are some potential mistakes where this doesn't look right.

So the nice thing about OD's virtual lab is that all of their meetings, right, the group meetings and also the one-on-one meetings happen through natural language.

So they all talk to each other through natural language.

And basically at the end of every meeting, the professor agent actually creates like a summary, essentially like a meeting minutes, right?

And then present that to us, to the human researchers.

So we can actually look over the meeting minutes.

And sometimes we do get feedback and say that, oh, did you think about this, right?

Or did you think about that?

Or if we actually see that oh they're not actually, you know, using

uh maybe d if we see that they're potentially going down like a a a a path that might be difficult to validate experimentally, then we can actually provide that feedback.

So we're very excited about this paradigm.

Showing 161–180 of 371 · page 9 of 19