The Wisdom Wall

“If you're optimizing for cost, absolutely be remote. If you're optimizing for creativity, which I think that software and product building is a creative endeavor, if you're optimizing for creativity, it's kind of like composing an album. You can't do it on the cheap. You want the very best album that you can make, and…”

“the more you can put your agent on rails, one, the more reliable it's going to be, obviously, but two, it's also going to be easier to use for the user, because you can really, as a user, you get, instead of just getting this, like, big, giant, intimidating text field, and you type words in there, and you have no idea…”

“I think people fail to truly, and me included, they fail to truly internalize the bitter lesson. So for the listeners out there who don't know about it, it's basically like you just scale the model, like GPUs go brrr, it's all that matters. I think it also holds for the, the, the cognitive architecture. I used to be…”

“It is actually, I think, whenever you can have a GUI, it is better than to have just a pure text interface.”

“The problem with EA is, like, the CEO has no willingness to actually tinker and, and play with the platform.”

“I wouldn't recommend it to build your own eval tool. There's better solutions out there, and our eval tool breaks all the time, and it's a nightmare to maintain, and that's not something we want to be spending our time on.”

“My philosophy about it is anything that can be done with an API must be done by an API or should be done by an API for a very long time.”

“Anytime you make a system more understandable from the top down, it performs less well from the bottom up. And it's fine if that's what you want, but you should at least make this trade off with your eyes wide open. You should know I am sacrificing performance for understandability, for legibility.”

“once there is a network effects that are just so incredibly powerful, they can't be broken, really. And we tried with San Francisco, I tried with San Francisco, like during COVID, there was a movement of people moving to Miami. Co-Host (Founder of Smol AI): You and I both moved there. Florent Crivello: How did that pan…”

“I think many people, when they started working on agents, they were very LLM-peeled and, and ChatGPT-peeled, right? They got ahead of themselves in a way, and as included, and they thought that agents were actually, uh, and LLMs were actually more advanced than they actually were.”

“Agents still get confused if they have too many memories, to my point earlier about that.”

“I think of it in terms of like jobs to be done, and I think of it in terms of who is the Lindy serving.”

“And I think that the reason for that is because search in each vertical has more in common with search than it does with each vertical. And search is so expensive to get right. Like Google is a big company. That it makes a lot of sense to aggregate all of these different use cases and to spread your R&D budget across…”

“I also think it is natural for the vertical solutions to emerge first, because they're just easier to build. It's just much, much, much harder to build something horizontal.”

“as long as you have some inductive bias about like some loose idea about where you want to go, I think it makes sense to follow a sort of greedy search along that path.”

“By creativity, I mean, is it about direction or magnitude? If it is about direction, like decide what to do, then it's a creative endeavor. If it is about magnitude and just do it as fast as possible, as cheap as possible, then it's, it's magnitude.”