High Signal Podcasts Evidence ledger
Method
Browse
← Back to evidence

Evidence receipt / belief

Published · transcript-backed

Dries Smit: belief

1 Jul 2026 Machine Learning Street Talk The Benchmark With No Instructions — ARC-AGI-3 (winning team!)

“For example, you have this reasoning tokens which has like abstract representation of objects, which we then manifest or write down in like an English language textual tokens. So I would say that's more abstract, you identify objects, you try and find out what the mechanics is, dynamics of the game, what the goal is.”

— Dries Smit

Source trail

Everything needed to verify it.

Speaker
Dries Smit
Attribution
Verified speaker
Claim type
belief
Recorded
1 Jul 2026
Publisher
Machine Learning Street Talk

Transcript context

…Yeah, you mentioned exploration as well. Guess there's a bit of an elephant in the room which is that Cholet is talking about the acquisition and synthesis of abstractions. And when reinforcement learning folks talk about exploration, it seems to be in quite a surface superficial way. So in terms of like entropy or things changing. And do you think is that in any way against this idea that we can acquire deep abstractions about the domain? Yes. Definitely for sarcastic goose. It was not at all what I guess what Funcher at the end wants as a good solution for Arcadia 3, but I can't speak to what he actually thinks is a good solution. But that was purely to see if I can benchmark, maximize this competition within 2 weeks. I think the duck and things we're doing on that side is perhaps more in line with what that initial vision is. For example, you have this reasoning tokens which has like abstract representation of objects, which we then manifest or write down in like an English language textual tokens. So I would say that's more abstract, you identify objects, you try and find out what the mechanics is, dynamics of the game, what the goal is. That might be more abstract And it's also kind of like a neural guided search and also the programs, the Python programs it creates is like executable Python programs to abstract and also build a some sort a simplified world model and search over that world model using actual like algorithms like breakfast search. There is understanding debt, right? That you're building this really really complex thing and after a while have you noticed in Claude code, they don't even show you the code anymore? Yeah. Right? You you can expand it, but by default, a lot of people don't even look at the code. So do do do you think that you need to be familiar with the deep abstractions in your code base in order to kind of build mental models and evolve it and extend it? You know, do you get lost in no man's land? Yes, this is a, yeah, if you will. This is an active discussion within our team.…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.

Search evidence