Kyle Corbitt
speaker
658 appearances
1 recordings
1 series
first heard Oct 2025
last heard 16 Oct
Kyle Corbitt’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 — 1 in all, peaking in Oct 2025 with 1.
Appearances
But for the work we do at least, where we're training agents on real code bases to like operate like, you know, real applications, it turns out it's like really, really hard to sandbox those things in a way that's like
totally reproducible.
And PPO, now in practice, a lot of times when you're training with PPO, you also will use an environment like that because it lets you do a bunch of runs and be more data efficient.
But at least in principle, you have the option with PPO.
You can actually like purely train on like say real production traces of like real people interacting with your app.
And so you don't have to have a simulated environment at all, which makes the deployment like much easier.
Yeah.
Well, you don't need to just capture all the inputs.
You you need you need a system that reacts the same way a your production system does.
That's the and and in many different ways.
And um so let's say you're you're Airbnb, right?
And I'm bringing this up because this is like an example of one that like, you know, companies have gone out and built sandboxes.
Like if you're Airbnb and you're trying to um you want to train an agent to like maybe you're not Airbnb, fine.
You're your company like us.
Trying to train an agent to like do really well at operating Airbnb and booking on your behalf, right?
Like you have to build a copy of the Airbnb website that reacts to you as the user the exact same way that the real one does with the same failure modes, right?
Because if you don't include the same failure modes and bugs they have, then like one of those bugs, when one of those bugs comes up in production, your agent's gonna have no idea what to do with it.
It's just gonna fall over.
You also need to simulate if this is like a sort of cooperative agent, right, where it's getting
human input as well and kind of like working with the human to get something done, which in practice is the way a lot of these are deployed.
Showing 241–260 of 658 · page 13 of 33
← Previous
Next →