Dwarkesh Patel: uncertainty

Transcript context

…Okay. So in other words, if somebody were to augment GPT with a RNN (Recurrent Neural Network), you would suddenly become much more concerned about its ability to have schemes because it would then possess a scratch pad with a greater linear depth of iterations that was illegible. Sounds right? I don’t know enough about how the RNN would be integrated into the thing, but that sounds plausible. Yeah. Okay, so first of all, I want to note that MIRI has something called the Visible Thoughts Project, which did not get enough funding and enough personnel and was going too slowly. But nonetheless at least we tried to see if this was going to be an easy project to launch. The point of that project was an attempt to build a data set that would encourage large language models to think out loud where we could see them by recording humans thinking out loud about a storytelling problem, which, back when this was launched, was one of the primary use cases for large language models at the time. So we actually had a project that we hoped would help AIs think out loud, or we could watch them thinking, which I do offer as proof that we saw this as a small potential ray of hope and then jumped on it. But it’s a small ray of hope. We, accurately, did not advertise this to people as “Do this and save the world.” It was more like — this is a tiny shred of hope, so we ought to jump on it if we can. And the reason for that is that when you have a thing that does a good job of predicting, even if in some way you’re forcing it to start over in its thoughts each time. Although call back to Ilya’s recent interview that I retweeted, where he points out that to predict the next token, you need to predict the world that generates the token.…

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