Illia Polosukhin
speaker
1,903 appearances
90 recordings
18 series
first heard Feb 2020
last heard 6d ago
Illia Polosukhin’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 — 51 in all, peaking in Jul 2026 with 8.
Appearances
The Neuron: AI Explained · Illia Polosukhin: Fixing the Broken System He Helped Create · 12 Sep 2025
podcast
It's like, how did you come up with this?
Where did this come from?
Yeah.
Well, it's all kind of half made up and half is from experience.
They were trying to do something.
It didn't work.
They were changing a bunch of stuff until it worked.
And now they're not going to go and redo everything, figuring out if other options work.
They're just going to keep whatever worked.
Yeah.
And so like figuring out how to like go away from that.
And so RL is even worse.
RL is like literally, you know, we have no idea, but you know, hopefully like this reward function works, you know, we run it, it works great, you know, ship the paper, ship the model.
So it's a very like kind of semi-arbitrary.
There is no like actual science around reward distribution and kind of reward provocation.
Well, it does that.
It's also like, and so it's very prone to like errors because especially like there was like all this fun stories of, you know, your model figuring out that actually it can look in the file where the answers are if you give it like file system tools.
or search or anything, it actually finds out how to get the answers.
And this is way cheaper and better than actually thinking about stuff.
So this is why we kind of need a better kind of training mechanisms.
Showing 1081–1100 of 1,903 · page 55 of 96
← Previous
Next →