Corey Knowles

I used to use it all the time.

Now I use Ghosty.

Yeah.

I think don't sleep on Atlas.

Yeah.

There's a whole rant there.

But I think that a rant about what the future is there.

But I think it's really interesting to sort of just switch to a mode where it's like, okay, I'm going to...

make sure that AI can see the sites that I'm on when I want it to so that I can ask it questions about it.

So earlier you actually mentioned an article that I was like, oh yeah, I need to refresh my memory on that.

You didn't end up asking me about it.

So I went into Atlas and I literally launched Atlas in order to load the article and then I was like, summarize this.

So that kind of stuff is...

Welcome, humans, to the latest episode of the Neuron Podcast.

I'm Corey Knowles, editor of the Neuron, and we're joined, as always, by Grant Harvey.

How are you, Grant?

Looks like some big news dropped recently here from a company called Logical Intelligence, eh?

So today we're going to break down what energy-based models actually are, why they almost can't hallucinate, where they belong versus language models, and whether this is actually a path to AGI or just a really strong constraint solver.

So today we're going to bring her on.

Eve Bodnia, welcome to The Neuron.