language models

“At OpenAI, we see this sometimes, for example, we had a paper on this unsupervised learning where you train a language model You train a model to predict the next character in Amazon reviews, and just by learning to predict the next character in Amazon reviews…”

“As you scale the language models, both in terms of the number of parameters they have, but also in the size of the data set that they're trained on, it turns out that they continue to get better and better at this prediction task.”

“They are able to do this task extremely well. And the only way to do that is to have gotten better at under, you know, some form of reasoning and some form of knowledge.”

“I had no idea that language models were going to be the thing. You know, we started working on robots and agents playing video games and all these other things.”

“So we bet on the fact that language models can do all the reasoning and parsing and like structuring later, but the more important thing is to start with something more unstructured, and that ended up becoming perplexity.”

“We can use language models to relabel and generate hypothetical human prompts for the scenarios that the robots are in.”

“Theoretically, I shouldn't be able to train a better model than that. Like, I'm just going to get the same thing out. So I think that's-”

“With poetic what we end up giving you is a you know, people are calling these things harnesses now, but you know, or agentic system or whatever you want to call it, that sits on top of one or more language models, and it just performs better than them. And whe…”

“I think the first is Seikan, which to me was the first demonstration of language model and how you can bring all of the common sense knowledge in language model into robotics, and therefore that significantly kind of reduces the need to collect robot-specific …”