One of the Rubicon moments will be when a new Transformer-scale architecture is discovered by AI and we're all using it.

68:01certain problems and certain challenges that we have to adapt to. I think the best way to do so is just interact with this technology as much as you can, and um maybe find new research ideas for out of that experience. >> And how is AI scientist V2 different to V1? >> In V1, we we used sort of a template-based approach. So, we had like a base experiment, and then for that

68:24base experiment, we asked sort of an LLM to generate ideas sort of with Semantic Scholar calls and sort of literature search, and then it implemented sort of these ideas based on the template, right? It did basically code diffs. And then it linearly executed like an experiment plan and wrote a paper in the end. And so, what could happen was that there was an idea, and that idea didn't

68:46work out, right? But then in the end, the paper like the experiments were still executed linearly, and you wrote a paper. And this was already impressive in the sense that it looked very much like like science, but if you think about human sort of science and like the scientific method. Um, it's much more like research, like I said before, right? You sort of adapt what you're going to execute next, and

69:09you sort of refine based on evidence that you accumulated, right? So, this is sort of the the notion of falsificationism from from Karl Popper, right? In the sense that uh, we collect evidence for hypotheses and reject and we reject others, and we do so in in a loop, basically, until we we want to publish or we find something. And we try to take this notion and directly build it into the agentic

69:31scaffolding for the AI scientist V2. So, now it's basically like an parallelizable agentic tree search, where there's no longer a template experiment needed, but this is drafted up by the LLM itself. And thereby, the AI scientist V2 can be applied to many more sort of settings, if you will. So, at the core is sort of this new agentic tree search paradigm, and then we use sort of a couple of minor technical

69:57changes like using a VLM reader for sort of figuring out if captions of a paper are aligned with the figures, and we we scale this up to many more sort of computational nodes, and then write a paper in the end again. >> So, I'm I'm trying to say this in the most polite way possible, but a critic might say I don't want to use the word slop, but a critic might say