large language model

“So, we don't do the transcribing, we don't do the voice, we don't do the LLM. In some ways, like, what are we actually doing? It's just that the UI layer that allows a three-person painting company to have an AI phone receptionist up and running in 10 minutes.…”

“Most of these tools today that help you build, like, a V-one of a product are kind of effective because they're able to hold most of the product in the context window of the LLM... But as soon as your code base gets Sufficiently large, where it doesn't all fit…”

“In our product, the concept of an LLM or a model or a prompt does not exist. There is no choose your model, like absolutely not. It's just the problem and here's the solution for it.”

“The durability of these so-called best practices is so short, like the prompting tools and guidelines and context management, like stuff, stuff that we were writing about six months ago, 12 months ago, 18 months ago is now completely wrong.”

“There is no attorney-client privilege between you and an LLM, and so if later it does become a lawsuit and in Discovery they subpoena your LLM chat, your conversations, they can pull those into Discovery much like they're an email or a private message. And so …”