Sholto Douglas & Trenton Bricken — How LLMs actually think

肖尔托·道格拉斯 & 特伦顿·布里克恩 —— LLM 究竟是如何思考的

Dwarkesh Podcast

2024-03-28

3 小时 12 分钟
PDF

单集简介 ...

Had so much fun chatting with my good friends Trenton Bricken and Sholto Douglas on the podcast. No way to summarize it, except:  This is the best context dump out there on how LLMs are trained, what capabilities they're likely to soon have, and what exactly is going on inside them. You would be shocked how much of what I know about this field, I've learned just from talking with them. To the extent that you've enjoyed my other AI interviews, now you know why. So excited to put this out. Enjoy! I certainly did :) Watch on YouTube. Listen on Apple Podcasts, Spotify, or any other podcast platform.  There's a transcript with links to all the papers the boys were throwing down - may help you follow along. Follow Trenton and Sholto on Twitter. Timestamps (00:00:00) - Long contexts (00:16:12) - Intelligence is just associations (00:32:35) - Intelligence explosion & great researchers (01:06:52) - Superposition & secret communication (01:22:34) - Agents & true reasoning (01:34:40) - How Sholto & Trenton got into AI research (02:07:16) - Are feature spaces the wrong way to think about intelligence? (02:21:12) - Will interp actually work on superhuman models (02:45:05) - Sholto’s technical challenge for the audience (03:03:57) - Rapid fire Get full access to Dwarkesh Podcast at www.dwarkesh.com/subscribe
更多

单集文稿 ...

  • Okay, today I have the pleasure to talk with two of my good friends, Shilto and Trenton.

  • Shilto.

  • Just make stuff.

  • I wasn't going to say anything.

  • Let's do this in reverse.

  • How am I going to start it with my good friends?

  • Yeah, Gemini 1.5, the context line, just wow.

  • Shit.

  • Anyways, Shilto, Noah Brown.

  • Noah Brown, the guy who wrote the diplomacy paper, he said this about Shilto.

  • He said, he's only been in the field for 1.5 years,

  • but people in AI know that he was one of the most important people behind Gemini's success.

  • And Trenton, who's an anthropic,

  • Works on mechanistic and turbability and it was widely reported that he has solved alignment So this will be a capabilities only podcast alignment is already solved so no need to discuss further Okay,

  • so let's start by talking about context links.

  • Yep It seemed to be under hype to given how important it seems to me to be that you can just put a million tokens in the context There's apparently some other news that you know got pushed to the front for some reason,

  • but Yeah,

  • tell me about how you see the future of a long context links and what that implies for these models Yeah,

  • so I think it's really on the hype Because until I started working on it,

  • I didn't really appreciate how much of a step up in intelligence it was for the model to have the onboarding problem basically instantly solved.