OPTIMIZE SEARCH LATENCY

“Liquid neural networks are you can think of them as a next step, like, sort of, state space model square. It's non transformer architecture that's more complicated than state state space and really difficult to code if you if I'm being honest, but it's, very efficient. It's, sublin sub quadratic in in length of your context. It's very compact way to represent things.”

“The main savings are coming from the fact that you ran it, you get your job done, and you moved on. Then somebody else in some department you don't know existed runs the same task, but on a newer version. Right now, in most of the organizations, you can't even find out about it so that you can't even measure that you're spending that time twice. Here, if everybody's entangled, that's detected automatically and detected that the output is the same.”

“It's not about just consuming tokens. You can consume tokens, and and, in fact, the anti pattern is running multiple agents too many agents in parallel that don't communicate with each other. That's almost useless, compared to just, fewer agents and burns tokens very efficiently. Setting up the right critique loop, especially with the high quality models where one agent does something, the other one, ideally with a different model, critiques it, suggests ways to improve it.”

“Shopify has decades of history of how people made changes and what there is, the what it resulted in terms of sales. Now what we can do is we have this it's not it's a noisy data. It is a small, usually, websites. But if you aggregate and general, like, everything together and you apply, denoising and collaborating filtering like approach, you can extract a very clear signal. And then you can optimize your agents.”

“If I were doing 400 experiments myself, my betting average would have been much higher, I'm sure. But, also, it first of all, it would take me, like, three years to do 400 experiments. And, I didn't have to do them. Like, the machines were just the price of electricity did that. And I got one improvement, that in my honestly, when I was starting that experiment, my thinking was to go and show that, hey, Andre. Maybe you just don't know how to optimize.”

“The main savings are coming from the fact that you ran it, you get your job done, and you moved on. Then somebody else in some department you don't know existed runs the same task, but on a newer version. Right now, in most of the organizations, you can't even find out about it so that you can't even measure that you're spending that time twice. Here, if everybody's entangled, that's detected automatically and detected that the output is the same.”

“It's not about just consuming tokens. You can consume tokens, and and, in fact, the anti pattern is running multiple agents too many agents in parallel that don't communicate with each other. That's almost useless, compared to just, fewer agents and burns tokens very efficiently. Setting up the right critique loop, especially with the high quality models where one agent does something, the other one, ideally with a different model, critiques it, suggests ways to improve it.”

“The real problem is not in spending time waiting for PR. It's real problem is since there's so much more code, then probability of at least some tests failing going up. And then you, like, keep failing, then you have to find the offending PR, evicted, retest it without that PR. And so deployment cycle becomes much longer.”

“This is number of daily active workers. You know, think of, DAO, basically, daily active users of AI tool as a percentage of all the people in the company. And, you could see that it approaches really a 100% by now. It's hard not to do your job now without interacting deeply at least with one tool.”

“Liquid neural networks are you can think of them as a next step, like, sort of, state space model square. It's non transformer architecture that's more complicated than state state space and really difficult to code if you if I'm being honest, but it's, very efficient. It's, sublin sub quadratic in in length of your context. It's very compact way to represent things.”

“This is number of daily active workers. You know, think of, DAO, basically, daily active users of AI tool as a percentage of all the people in the company. And, you could see that it approaches really a 100% by now. It's hard not to do your job now without interacting deeply at least with one tool.”

“If I were doing 400 experiments myself, my betting average would have been much higher, I'm sure. But, also, it first of all, it would take me, like, three years to do 400 experiments. And, I didn't have to do them. Like, the machines were just the price of electricity did that. And I got one improvement, that in my honestly, when I was starting that experiment, my thinking was to go and show that, hey, Andre. Maybe you just don't know how to optimize.”

“The real problem is not in spending time waiting for PR. It's real problem is since there's so much more code, then probability of at least some tests failing going up. And then you, like, keep failing, then you have to find the offending PR, evicted, retest it without that PR. And so deployment cycle becomes much longer.”

“Shopify has decades of history of how people made changes and what there is, the what it resulted in terms of sales. Now what we can do is we have this it's not it's a noisy data. It is a small, usually, websites. But if you aggregate and general, like, everything together and you apply, denoising and collaborating filtering like approach, you can extract a very clear signal. And then you can optimize your agents.”