The Ledger, every show

“You know, if agents never write any code, then okay, maybe they're not useful, but I think it's trending where Basically all agents will write code, so that's a very interesting piece, I think.”

“There are also things where it requires iterations. You need to like decide what to do, interact with the environment, get that back. So this whole idea of chaining and agents, I don't like, That's less around context windows and more around interacting with t…”

“It doesn't actually use the tools that are RL into the model. So like anthropic models have some like file editing tools. They have a completely different set of tools in, in the actual harness.”

“Like, I do think we'll get to a place where we have this kind of like synchronous conversational agent kicking off kind of like longer running asynchronous agents in the background.”

“We see people experimenting with it. I think the only real place where they're doing it is when they've reached like really critical scale which I still don't think is that many applications to date.”

“All the big model labs have been RL and code and bash and editing files into those models. And so that is the stuff that works the best.”

“Most harnesses today have sub agents built in. They have skills built in.”

“So I think, like, pretty clearly agents will be long-running and stateful, and so I think we have a deployments product. I think a lot of the I think deployments products that let you build long-running stateful things will be kind of, like, interesting no mat…”

“That's why people are buying Mac minis as a, you know primitive way of sandboxing them and keeping them in a contained environment.”

“In practice, we see people doing about fifty-fifty between each of these.”

“I don't think we have like an off the shelf kind of like implementation of reflection and kind of like the general sense. I think the concepts like absolutely we see used in different kind of like specific cognitive architectures, but I don't think we have one…”

“I saw some paper that used TypeScript notation instead of JSON notation for tool calling and it got a lot better performance.”

“I do think the prompts will probably start to converge in the sense that if you think the models are getting more and more intelligent than like, hopefully these small idiosyncratic sees don't matter as much.”

“We saw Manus, we saw Cloud Code, we saw Deep Research, they all had these four things and we were like, okay, that's pretty common, let's put it into a Python package and make it easy for people to build their own versions of that.”

“I think open AI even recommended, like when you're doing tool calling, it's sometimes helpful to put like a thought field in the tool along with all the actual acquired arguments and then have that one first. So it fills out that first and then, and that's, th…”