前DeepMind研究员：AlphaGo式打法可治AI幻觉

Former Deepmind researcher Thore Graepel founded Metis Reasoning to make AI systems more reliable and verifiable, using AlphaGo's approach as a blueprint. The method separates knowledge from model weights and stores it in an external ledger, where an independent module checks every assumption against evidence. The approach aims to cut hallucinations and provide source-backed explanations, but so far it exists only as a theoretical framework with no working system. Former Deepmind researcher Thore Graepel wants to build AI systems that track what they know and check every conclusion against evidence. Larger language models won't fix this problem, his team says. Thore Graepel believes the same idea that let AlphaGo beat Go professional Lee Sedol in 2016 can make AI systems more reliable, including in robots. The former Deepmind researcher founded Metis Reasoning and laid out the approach at Nvidia's GTC conference in Berlin, where the chipmaker has been expanding its platform for robotics and physical AI with the goal of turning robotics' data problem into a compute problem . Today's language models amount to just AlphaGo's prediction network, which suggested possible moves, according to Metis. AlphaGo paired that network with a systematic search through game sequences and found the famous Move 37 , a move the network would have given a human player roughly a one-in-ten-thousand chance of making. Metis wants to bring that kind of search to general reasoning. Ad Doing so requires what the company's paper calls an explicit knowledge ledger, comparable to the game board. Similar ideas already exist: Microsoft's GraphRAG organizes knowledge outside model weights in a knowledge graph, and Google's AlphaGeometry2 pairs a language model with a symbolic engine that verifies mathematical proofs. Metis wants to extend those principles to open questions in the real world. Ad Its knowledge ledger records what is known, how confident the system is, and which questions remain open. A separate module checks new entries against calculations, formal proofs, or empirical evidence, and when an assumption falls away, every conclusion that depended on it gets re-evaluated. A "move" can be a question, an experiment, or a challenge to an existing assumption; the system picks whichever one reduces uncertainty about the original question the most, ultimately delivering either an answer or a justified abstention. As in AlphaGo, two neural networks suggest and evaluate moves, trained on logged prior investigations but unable to override the verification rules. Metis says the setup should produce fewer hallucinations, explanations with source citations, and knowledge that can be changed or deleted without retraining. Because reasoning breaks into small steps, the approach could also favor smaller models running on edge devices and in robots. Ad More data and compute improve language models but don't solve the technology's fundamental problems, according to Metis: the models fabricate answers, their reasoning chains can't be verified, and their knowledge is locked inside the weights. Hallucinations come from the training process itself , the paper argues, because models learn to produce plausible text rather than true text, and even the chains of thought in today's reasoning models often fail to show how an answer was actually reached. That, the paper says, is why AI has had so little economic impact so far . When an agent acts on behalf of a company, errors are hard to trace back to their source and wrong knowledge can't be removed from the model. AI took off in software engineering because code is easy to test and roll back, but in medicine, finance, chip design, and robotics, the paper argues, AI needs to be verifiable from the ground up. Ad The white paper describes only a research program, with no working system, no benchmarks, and no comparisons with current reasoning models. The team acknowledges that the real world, unlike Go, provides on