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 similar to like if you and I would discuss something maybe two different days, we might end up with two different outcomes, right?

Or similarly with the virtual lab.

But the nice thing is that we can actually do this.

more inference compute, right?

Basically do more parallel meetings and then actually explore essentially more different path of what are the different things that could play out.

And then the professor in the end will look across the meeting logs of all these parallel meetings and the professor agent will say, okay, so here's the overall consensus and here's what we should do going forward.

So I think in that sense then these meetings for the virtual app, it it is much faster and much more efficient than some of the physical meetings that we can have.

the cost is I would say actually relatively small.

I I would say probably over the

meetings like if you look at essentially like all the words are spoken by different agents, at least in terms of the open AI API cost, I think I would say it's probably like less than a hundred dollars.

It's a good question.

I think it would definitely have taken much longer and if we basically extrapolate based on like the human resource cost, right, of having a team of protein scientists doing this, that would actually be much more expensive.

But perhaps the other thing is that's

It's not really clear that the humans team would have ended up with similar designs, right, similar workflows, because these are actually very hard problems, right?

For example, some of these recent variants like JN one, variant of SARS CoV two, there's not actually a great uh binder to that, right?

Even though there's

certainly a lot of people have been working on these things.

So it's a very important problem.

But the virtual lab I think shows no the design nanobody shows quite promising binding profile.

But I do want to give the caveat that I think we need to do a lot more experimental testing to really like you know validate these, but at least based on the initial ELISA experiments, it looks very promising.

Showing 221–240 of 371 · page 12 of 19