Shawn Wang: belief

Transcript context

…Honestly, all of them, we are behind all of them with between Llama 2 and GPT-4. I mean, it's different challenges every time. Like being good at code or reasoning is something we didn't do at Llama 2. So we had to build everything from scratch. Improving on helpfulness, which is one of the main dimensions that people look at, I think, in the arena, which is, by the way, a very interesting evaluation. Because when we did the preview, and I don't know yet what will be the results for this new Llama 3, but we ended very high in this blind test leaderboard. And to be honest, I didn't expect that. I knew we had good results internally, but how that will transfer to perception from the community, people like using it in practice and comparing it to the other models, I didn't expect that positive feedback. That's high ELO score on this benchmark. It doesn't say like everything, as I said before, which is also interesting, because it's a community that judge the prompts and create the prompts and judge the answers. We are limited. We are not like good to do that. And so it gives you a very good indicator of how good, helpful, how on the main core of the distribution, simple prompts about the tone of the model compared to the others. But for much more complex prompts, much more intelligent reasoning, coding of complex stuff, it doesn't tell the full story. You know, like while we had 7TB preview at the level of GPT-4, even better at the time, I think it was partly true. But clearly we were not at like GPT-4 level in code or reasoning, we are now. There's some conversation about like the math score. I think the next GPT next or whatever has reached 90, which is a big, big jump from the current state of the art. It will be interesting. One of our previous guests, rounding out the topics on potential models, areas of development and evals, Clementine is looking for a confidence estimation or uncertainty benchmark. One of our previous guests, Brian Bischoff, is also asking about like, how do we think about evals for practical things like confidence estimation, structured output, you know, stuff like that. Yeah, I think we lack actually of such evaluations. One of the numbers I was suggesting like two days ago to the team to report at some point is, okay, we have this accuracy on MMLU, on whatever, on math and JSM84. What if we change a bit the prompt and instead of telling the model you have this question, you have to answer A, B, C, or D? What if we tell the model you have to answer A, B, C, or D, or you don't know? And maybe the accuracy will be a bit lower, but I'm curious to see if some models we have different calibrations where maybe model A have 50% correct, model B has 50% correct, but model A answered 100% of the questions, so 50% are not correct. Model B actually said like, answered only 60%, so for 40% of the time he said, I don't know. I prefer model B. And we are not like reflecting that in evaluations.…

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