The Wisdom Wall

“What we see in enterprise is rarely things that are solved with agents because that's not necessarily where you would expect, uh, an FDE to be most useful. Where there is more values, value is in, uh, more complex workflows where you will have several, uh, agents interact through a workflow to automate something…”

“and that I think that was the big change in, um, and realization through vibe coding is that agents are good enough at, uh, manipulating file systems that they can use this as a replacement for, uh, their Context window, basically. They can select parts of what they want to read, they can select parts of the tool…”

“there's no real difference between Creating a new thinking trace or calling the right tool. It's, it's all the same to me, because what you're optimizing at the end is what is the best, uh, output for the model to create before it gets results to, uh, to me.”

“getting the data perfect, because we knew, um, this was potentially not the most exciting part of the work, but it was absolutely critical, and any improvement on the data quality would, Tenex, the, uh, improvements that we would get by really, um, improving on the model architecture or things like this”

“Requirements I see for control and governance in enterprise make me think that even if I had, uh, some AGIS model on my, uh, servers right now, if I were to go into a large bank and say, Here is a thing. Please let it control everything for you. They wouldn't be happy to let it do it.”

“when you run inference on a few GPUs, or when you run small scale trainings on hundreds of GPUs, margin for error is a lot larger than when you run trainings on thousands of GPUs at the same time.”

“What we have seen in terms of success is that given the current stack, it still requires, um, a lot of expertise, uh, to manage to come to, um, actual value and, um, and things that go to production, basically.”

“The reason we do this is that it lets clients build where their data is, and without having to shuffle things around, which, as I've learned as a CTO, is something that you don't want to do ever. Because it asks, it raises a lot of questions, and it's quite a stressful thing to do.”

“to me to get the full, um, ROI of coding, you need customization, uh, because a lot of ROI is unlocked, uh, on like sprawling code bases that are completely impossible to know for, uh, for something that's been trained on the web.”

“The more focused your use case is, the smaller you can make the model through fine-tuning or through just distillation in an even smaller architecture.”

“MOEs are really nice systems to train because of the lower amount of flops, which makes us able to push performances a lot more during training.”

“They are not necessarily the best format for on-prem deployment, because As of today, if you want to get the best efficiency out of a mixture of experts model, you require a lot of volume, because you're looking at deployments across dozens of GPUs usually, and to justify that amount of GPUs, you need to have the right…”

“Typically, if the file system is just representing textual context, and you're not expecting the agent to do much action on it, then you don't really need a full sandbox. You just need some representation of that context as a file system, and it can be Any sort of abstraction. But if you are, I don't know, typically…”

“So before it was about, uh, accruing world knowledge and the, uh, web helps a lot with this. Now it's more and more about acquiring know-how.”

“customers aren't happy if you require them to deploy five different, uh, models to get their job done.”

“having a system that is good at handling a file system is more generally very interesting. Even if you're not using it to code, you can use it to reason about enterprise knowledge, you can use it to connect to enterprise systems, and it's, to me, it's the basis of really the enterprise intelligence that we're starting…”

“sometimes it's a lot cheaper Uh, to use a small OCR model to just get the text that you care about and then potentially post-process it or deal with it with another system than to run it through a large, uh, multimodal model that will, uh, basically do the same thing but at a higher cost.”