large language model

“One thing that I'm really excited about is actually augmenting large language models with the ability to take actions. And so we've seen a few examples of this at the startup called adapt AI that are doing this and a few others where you essentially let the la…”

“Then the use cases that people are building now tend to be a lot more subjective than you might have done with machine learning before. And so evaluation is a lot harder. You can't just calculate accuracy on a test set.”

“What they actually have figured out is that for a lot of large language models, if you do any sort of fine tuning or training with private data, you can actually just speak to the model and get it to spit out your private data again, and they have a solution t…”

“While in the next five or 10 years I think we will get far more used to using it that way I think the low-hanging fruit right now is just using the large language model To actually do the sort of knowledge work that a human being could do, and then package it …”

“I think for summer of 23, it was close to 50% of the batch.”

“I mean, this is why I think the chat interface is wrong. Like I actually think there is value accrued to really great UX, like good copy, good you know, interaction design, information hierarchy you know, being able to approach a product and say like, this is …”

“There's one way of doing these things where we go to each of these domains and like try to build an index of it and put it into specific formats like tables and then have the LLM, like read that. In a structured language of SQL, or you could do the other way w…”

“Like it's wild how your coding style changes when actually writing the code becomes a thousand X cheaper. Like as a human, you would never just like blow away something that you'd worked on for a long time and rewrite it from scratch because you had a bug. You…”

“Where is the last parking spot in a rainstorm here in San Francisco? How many apples does the local grocery store have in aisle six? These are questions that actually nobody has, no LLM has the answer to no one has the answer to, and I think that the physical …”

“It's so powerful that pretty soon I actually expect all the major coding tools to be able to ingest these errors Without humans having to copy paste. If you think about it, our value being the copy paste machine is, is kind of weird, right? We're like, we're l…”

“So I'll often just download all of the documentation for a given set of APIs and put them in a subdirectory of my working folder so the LLM can access them locally. And then in my instructions, I'll say, go and read the docs before you implement this thing. An…”

“I think we might see a shift towards more modular or service-based architecture where the LLM has clear API boundaries that it can work within while maintaining a consistent external interface Rather than these huge monorepos with massive interdependencies.”

“In the response format. To give it the ability to have part of the response be essentially a complaint to you, the developer that like you have given it confusing or underspecified information and it doesn't know what to do. And then the nice thing about that …”

“And I think what's changed, and I think is a quite fundamental change, is that neural networks became programmable. With large language models. And so I see this as quite new, unique. It's a new kind of a computer. And so in my mind, it's worth giving it a new…”

“LLMs are kind of like a new operating system, right? So, the LLM is a new kind of a computer. It's setting, it's kind of like the CPU equivalent. The context windows are kind of like the memory, and then the LLM is orchestrating memory and compute for problem …”

“That's gonna happen.”

“And so if you really take something like a simple thing like discharge the amount that you take the back end of an EMR system with just an LLM and a prompt that itself is going to save so much time and money and energy that it would sort of pay for itself.”

“Constructing world model might be a little more nuanced. The world is more structured. There might be signals that we need to use to guide it. You can call it in the shape of prior. You can call it supervision in your data, whatever it is.”

“And to do a project like training a large language model requires a lot of people to collaborate on like a really complicated piece of infrastructure that isn't going to be a paper, right? Like you're not going to publish like, oh, I got a slightly, I got five…”

“But you do want to control, like you don't want to show too many things at once where, Like it just becomes like a wall of text. You want to control like, ah, the things that are running, you show them in the more like focusable spot. And as it progresses, it …”

“I almost wonder, like if you just one shot landing pages do you actually go and really like use it with the same Attention detail as you feel if you had like built it from scratch. And then because you don't you just ship things that are, that you wouldn't hav…”