[LIVE] Anthropic Distillation & How Models Cheat (SWE-Bench Dead) | Nathan Lambert & Sebastian Raschka

**Nathan Lambert** (0:00)
Okay, we're live. We have one person.
People will start trickling in. Thanks for coming to SAIL Live number six. This is a very exciting one. I think we have a, I mean, the topics are always fun with these. Whatever is the topic of the day on our little rat racing minds trying to keep up with AI. But we're welcoming the latest writer that is joining the SAIL Coalition. So I think this just means more content for SAIL. I think I've been a fan of Swyx and a friend for a while at this point. So I'm very happy to have his content join this. And I think you've been doing great stuff recently and continuing to evolve this. So welcome to the team. I just think this is my friends and colleagues in the AI media space. And it's just great to be able to support people and keep that network closer.

**Sebastian Raschka** (0:51)
Thanks for joining us. It's really a pleasure to have you on here, Sean or Swyx. So yeah, awesome. I just coincidentally listened to your podcast about the Super Benchmark. So yeah, awesome to Small World. Awesome to have you here.

**Swyx** (1:09)
Yeah, thanks for having me. And yeah, glad to be on in chat. I've never ever done one of these Substack Live things. So I'm curious how it works. I always think about Substack because I can use a later platform, but they want to go multimedia.

**Nathan Lambert** (1:25)
I think the live thing before we get to technical content is actually good because it gives it a different edge. It's just like a little bit sharper when you know you're live. I think we've all done a lot of podcasts, even podcasts that are unedited and put there's later. But I think the live thing is a different element that can be tapped into nicely. So I don't know, why don't we just dive into it? We're going to start with distillation. I put how models cheat in the top so we can talk about benchmarks. I think Anthropic posted this pretty spicy blog post this week. I think it was essentially detailing how they found distributed distillation, quote, unquote, attacks on their services from prominent Chinese labs. I'm very unsurprised with Anthropic calling in an attack. I think that that fits with a lot of their branding. Okay, nice. Screenshare. This is what we mean. Sean Swyx is such a pro. It's like, and the screenshare fever was only dropped a few days ago. But essentially, Anthropic is detailing how they found distributed accounts across multiple Chinese labs, building data that are LLMs, and described what they were doing and why Anthropic is concerned about this in their worldview of AI geopolitics.
I think it's very interesting because I'm of the opinion that the Chinese labs obviously should do this. They're in a massive GPU shortage, and using APIs is way easier than generating synthetic data on their own.

**Sebastian Raschka** (2:54)
Nathan, if I may interrupt you here, maybe we should, just for the general audience, just define distillation before we maybe dive into the details. Yeah, so distillation, that's like a broader concept. It's not like a new concept that came up with L&M's. It's like an older concept in machine learning in general. And distillation essentially is, the idea is that you're taking a larger model and train it on the outputs. Sorry, you have a larger model, let it generate outputs and train a smaller model on these outputs of the larger model. And the idea is that you can train the smaller model more efficiently using that larger model. And originally, I think you just brought up the paper here. Originally, what you would do is you would train on the logits. So old school machine learning people might remember from deep neural networks like the logits, the outputs of the last layer that you usually work with them to compute the loss function across entropy term. And you would train on this signal. And nowadays, in the context of LLMs, it's a bit more loose. So it does not have to be these logits that you train on. It could be just the output data, synthetic data, like Nathan just said. So for example, it's actually a very common practice. For example, in DeepSeq R1 in the paper, or other people do that too, other companies, they would train the flagship model, the largest model, the R1 model, with 671 billion parameters. And then they would create smaller variants, like I forgot the numbers, but one, three billion in a smaller range, like these small models you can run locally. And they are trained on the outputs of their own larger models. I think now the thing is also, I mean, this is very common practice. Everyone does that when they are producing the smaller model variants.