“When we got AlphaZero right, you know, we gave up on the human data and finally focused on what would it be like to build an algorithm that could discover for itself. So once we got it right, that algorithm, it took just a few hours. Like it took a few hours to outperform the two years of work which we'd done with human in the loop.”
Training Data · AI Research & Frontier Labs · October 2026
Silver explains why his new lab is betting against human data. AlphaGo took two years of human-in-the-loop work, much like the LLM approach. AlphaZero, which learned without human games, beat it within hours. He says today's LLM companies are building learning systems with thousands of people in the loop.
Transcript
…the four humors or there'll be all kinds of strange beliefs that would be embedded in there and be very hard to kind of remove because they're so fundamental to the kind of language and the processes of thinking that humans have used. So I do think that going beyond this is a really important goal.
…with AlphaGo and then Alpha Zero, AlphaGo Zero is maybe the best example that anyone can point to of what happens when you remove human priors. Maybe if you take us back to AlphaGo and then AlphaZero, was it surprising to you that removing human priors would result in even smarter intelligence?
I wasn't sure, honestly. So I remember I always like to do things in research where I think you ask research questions which are like on a knife edge where it's like 50-50. I think it's not very interesting to do research where you already know the answer and you're like 95% certain this thing's going to work. It's kind of like boring, honestly, to do those things. So, you know, I think research, good research is about asking questions where you're really not sure what the answer is in advance. And in this case, I was about 50-50 and I thought that maybe there was a good chance that it might, but I wasn't confident and it was very exciting to see it. I should say, you asked about human priors. So we are making a bet, quite ineffable. And the bet we're making is that we can go further by giving up on the priors that everyone's relying on today, like the human data, like the whole internet of knowledge that everyone else is building their systems upon. That's an important choice. And so we should probably talk about why we're doing that. And I think the reason for me, of course, it's a short-term sacrifice. We give up…
That's very profound. As far as I know, there are humans at ineffable, and some of you are creating environments or crucibles. What does it look like to actually try and make sure that human priors aren't kind of leaking into what you're doing?
Yeah, well, so when we design like environments and like rewards functions and so on, obviously there's a human bias in there. But we don't want to, as Dave was also mentioning earlier, we don't want to bias it towards building a machine based on the von Neumann architecture or something like this.…
So I totally agree with this. I would also say that we're not religious about this. It's not like a religion that you can't have any human prior anywhere. It's more like a pragmatic position that until we give up on relying on the trillion item data sets of human knowledge, that we're not going to…
More from Training Data
