John Schulman: evaluation

Transcript context

…Is this all happening at the same time? Is it just a new training regime where all these things can happen at once, whether it’s long-horizon or this kind of training? Are they separate or not? Is the model smart enough to both introspect and act on longer horizons so that you get adequate reward on the long-horizon tasks? If you're doing some kind of long-horizon task, you're learning while you do the task, right? The only way to do something that involves a lot of steps is to have learning and memory that gets updated during the task. There’s a continuum between short-term and long-term memory. I expect the need for this capability would start to become clear when we start to look more at long-horizon tasks. To some extent, putting a lot of stuff into context will take you pretty far because we have really long context now. You probably also want things like fine-tuning. As for introspection and the ability to do active learning, that might automatically fall out of the models’ abilities to know what they know. Models do have some calibration regarding what they know. That's why models don't hallucinate that badly. They have some understanding of their own limitations. That same kind of ability could be used for something like active learning. Interesting. I want to step back and ask about your own history, at least at OpenAI. You led the creation of ChatGPT. At what point did you realize that these LLMs are the path to go? When did you realize a chatbot or some way to instruct them would be useful? Just walk me through the whole lineage from when this became your main focus and what the process was like.…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.