Brandon (Host)
speaker
390 appearances
3 recordings
1 series
first heard Jun 2026
last heard 16 Jul
Brandon (Host)’s voice in public audio — every appearance, attributed to the second.
Trend
recordings per month · last 12 monthsRecordings per month over the last 12 months — 3 in all, peaking in Jul 2026 with 2.
Appearances
And what were some of the failure modes that people, I think, didn't really see coming from a practical standpoint back then?
Or if you can predict this, it requires so much computational resources that you might as well just solve the problem.
Right.
Yeah.
Can you talk about Pearl a bit?
So I think one of the interesting things about Pearl in my mind is it was an attempt to kind of scale what seems unscalable to me.
RNA small molecules, you know, normally if you scale them, models just come out as just like pure pattern matchers.
These things love to tell you what you already know.
And sometimes they're maybe not so great at telling you something you don't know.
So maybe it seems like there's hints that Perl has actually moved beyond this.
Like, what were the key insights that went into this?
Sure.
So like a term for this people sometimes use is like co-folding?
It's called co-folding, right.
AlphaFold3 and then some of the, and then Boltz and OpenFold3 and so on have also implemented some of these ideas in their own way.
Is that kind of the idea?
Yeah.
So it's like your diffusion head is basically learning something like a force field.
and that you're kind of bouncing off between a diffusion-based force field and like a physics-based force field?
Or is that a way of thinking about it?
Showing 161–180 of 390 · page 9 of 20
← Previous
Next →