Andrew Gordon: recommendation

Transcript context

…People are increasingly using these models for very sensitive topics and questions for mental health, for, how should they should navigate problems in their lives. And there is no oversight on that. And in any other area where these topics are discussed, there is a lot of regulation and and a lot of kind of ethical conduct built into it. Whereas here is kind of the Wild West at the moment, and some companies are taking it more seriously than others and trying to study the ways in which humans are, using the models for for more personal topics and and problems. And we've seen some pretty starky examples recently with with Groktri and Mecha Hitler. And it does raise questions about how how thin of a veneer is the safety training on top of some of these models. Well, there is no leaderboard for safety. Right? Like, there's no metric. Like, we we don't grade LLMs by how safe they are. In fact, it's not really even in the question apart from some researchers. So I mean, I I would argue that that should be just as important as how fast or smart the model is. You know, how safe is it for the people to use? There's been a lot of interesting research coming from Anthropic in that direction with regards to safety, with regards to alignments of the models and using constitutional AI and various approaches that they've that they've explored and also around mechanistic interpretability, just peering kind of behind the curtains of the models and understanding how an input produces a certain output, which can feature these concepts, which circuits get activated along the way and kind of tracing the thoughts essentially of these models and trying to isolate where potential problems may emerge. So work of this kind is very important and raising the confidence that these models will be able to handle novel situations in safe ways.…

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