Inside the black box of AI: How AI models actually think | Emmanuel Ameisen (Anthropic)

One of the big questions on people's minds these days is AI doing bad things. That's someone that watches these models think and operate. Why is it so hard to catch it thinking badly trying to deceive us? We train Claude to be helpful, harmless, and honest. Is it the case that it's behaving well? But if you look inside, actually it's like oh I'm only behaving well because Lenny's watching right now. People full time jobs is studying the model how it thinks how it operates. How long has this been a skill set and a job? One of the most important things to realize if you like use language models or think about them as just this like very bizarre fact that to make them is not to understand them. All these models do is just a lot of mathematical operations on many numbers. If you look at it, it makes no sense. You just have a list of a hundred numbers, you know the model's doing math. And then you just try to see if there's patterns. You are figuring it out the same way we figure out how the brain works, looking for patterns. You show this image, this part of the brain lights up, and you're doing the exact same thing with AI. Wow, this is so fascinating. There was this model we were training, it would go crazy. It would do some math, it would get to an answer, I think it was twelve. It would immediately go back and say, like, Oh no, oh my God. The answer actually is for sure.

Thirty six. It would do math again, it would get to twelve. Slow it would like start descending into madness, writing in all caps, literally saying I'm possessed by a demon. Humans, if you really boil it down, like we're basically next token predictors ourselves. We're just trying to figure out the next thing to say. Dario is always out there. This is really dangerous. We gotta be really careful. And everyone's just like no, he's just saying that for marketing reasons, and now it's like wait. Shit. It's really dangerous. Take the idea that this technology is going to keep improving seriously. Do you think about consciousness as a part of this, just like do you think AI is conscious? Oh man. Emmanuel, thank you so much for being here and welcome to the podcast. Thanks for having me, Lenny. So you work on interpretability at Anthropic.

Explain what that is. Explain what it is you do. Yeah. My uh so I work in a team uh of of interpretable researchers and our goal is to understand how L's like Claude work

We already have this episode, so unlocking it is cheap and permanent: the full transcript (72 minutes, 15,108 words), segment and word-level timestamps, and .txt, .srt, .vtt and word-level JSON downloads, as many times as you like, forever.

No account needed, we create one from your checkout email. With credits it is 1 credit; packs start at 10 episodes for $5, and monthly plans are cheaper still.