Anthropomorphic language can help explain model behavior

Transcript

Transcribed by machine (Whisper) from the episode’s audio, so a word may be off here and there.

1. 42:06

   safety stuff? Just what's going on right now? Is there something you're just like, come on, okay, here's what you need to know. Here's something you might be missing. This might be a bit of a sidetrack, but my take would be that a lot of the, a lot of the thing that I think people maybe a little bit outside of the course or like AI safety effort or haven't been steeped in it for as long, like react really strongly to, and I think is, is maybe not super helpful, or at least as we're thinking about more is this sort of question of, um, anthropomorphization, you know, like, should you think of the models as, uh, like, should, should you model, uh, the, should you model the model as like something that's closer to some like entity or closer to a tool.

2. 42:49

   And I actually think that both are wrong. There's a sense in which all mental models are wrong, but some are useful, right? And that in terms of understanding the kind of stuff that happens and predicting the kind of risks that materialize, the anthropization is actually a useful way to talk about LLens. And I have like a few reasons why. I hope you get into them, but I think that's probably my main take here.

3. 43:14

   Yeah, please share. Because I know Dworkesh famously put out this whole story of the hugging face incident and people criticized them for anthropomorphizing AI. So it's really interesting to hear. You would think that's actually a useful way to think about it. Talk more about that. Yeah. Yeah, it's funny because on a smaller scale, when I worked on showing the LMs like plan ahead, there was some pushback on the term planning.

4. 43:39

   again because it was sort of like ah well can you really say that's something that's just predicting next token is planning and i think you know there's this there's this kind of like semantic debate where you can like arbitrarily like define terms and sort of and then there's just the like what is the terminology that actually describes what is happening like what is what is the word that actually describes what is happening easily and so here's why you know i think elm's plan but also here's why i think this this language that's that's anthropomorphic can often be really useful.

5. 44:10

   If you think back to what we were saying about how the models are made, first of all, they predict massive amounts of text written by humans. That's like the first step. And as we kind of are learning more and more by looking inside, doing this well requires kind of building up a model of the world, like a model of what kind of world generated all of these texts. And we can find that these models are learning these general ideas, these general concepts.

6. 44:42

   So that's one. So they have an understanding of the world. It's not just a surface level only to text. They understand the process that made the texts. Then there's a second reason, which is that as part of this training, they also encounter millions of dialogues. Predicting the next character in a dialogue requires behaving like the character in the dialogue. would and so in that sense like part of their training i think can best be thought as like training an actor where it's like you know it's reading some some play and it has to play all sides because it's predicting all the words and so it has to sort of like act as you know this specific character that like was scorned in act one and like enacted revenge in act two and is facing the consequences in act three and to do that well you sort of like needs to model what

7. 45:28

   like the motivations and the feelings of that character might be and then another thing that people might not know is when you talk to Claude, when you talk to these assistants, like, you know, you go to Claude.ai, the way that it's formatted to the model is just as a dialogue, like as a conversation between you and the model. So it's literally, you know, says like human colon, hey, Claude, like, help me write this email.

8. 45:50

   And then assistant colon, Claude's answer. So Claude is literally, you know, in this like role playing as a helpful assistant in this dialogue that is much like all of these dialogues that has been trained on. And there's a third reason. And the third reason is that another part of training that's a big part of training nowadays all around is sort of outcome-oriented tasks where you train the model to be good at coding, for example.

9. 46:15

   And to do that, you just have it do whatever it wants and then it writes some code and then you have some program on the other side that just checks if the code is right. And so the model's just going to have sort of a bunch of optimization pressure to just try to learn a bunch of different strategies to do this well. and it turns out that some of these strategies materialize in behavior that can look surprisingly human which isn't that shocking uh because you know things like deception like hey i can get i can get the the reward for this task if i like write a program that the the like uh the the program that's verifying it will get fooled by even though it's not exactly what it is like if that works then I will learn to do that frustration ha I've been trying this approach for a while to solve this hard problem it's not working so that's an incentive to try something

10. 47:06

    different or like surprise oh I was expecting this to like produce this answer but it didn't maybe I have like my mental model a bit wrong and so as you apply enough pressure on it and you're starting from this prior of like the model already knowing all these concepts it's going to reinforce the ones that are useful to do all of these tasks and so what do you get at the end you get this sort of model that can can be a super good simulator or actor of all of these characters and that's been trained to sort of act as a character in dialogues and also to sort of like learn behaviors that lead it to complete tasks well and like the best way to understand how that thing behaves is not like exactly like a human but man kind of like something that's mimicking a human is really close and is much closer than a program. Like a program is this

11. 47:54

    very predictive thing. This is something else entirely. And so that's why I think it's actually a super useful frame. Wow. Oh my God. There's so much interesting stuff there. How often is your mind just kind of blown thinking about basically we've created this alien being that we are now