How Fast Did AlphaZero Overtake Two Years of AlphaGo?

David Silver says the moment the team let go of human data, AlphaZero outperformed two years of human-in-the-loop AlphaGo work in a few hours. Giving up human data is what let the algorithm discover for itself and shoot past the competition.

David Silver says the team spent about two years building AlphaGo. They put in a lot of human data and stayed in the loop, taking the previous generation and choosing how to improve the next one. It took two years to get to AlphaGo. When AlphaZero was right, they gave up on the human data and focused on an algorithm that could discover for itself. Once the algorithm was right, it took a few hours to outperform the two years of work done with a human in the loop. In chess, it took four hours to beat the world champion, the best ever AI that had ever been created. In Go, David Silver says he thinks it took a couple of days.

David Silver says the choice has to be active. He sees a lot of LLM companies building semi-autonomous human-in-the-loop learning algorithms with thousands of people in the loop. He respects how far the work gets, and he does not believe they will reach a true super learner until they step back and discover a process that learns for itself.