AI achieves silver-medal standard solving International Mathematical Olympiad problems - Google DeepMind
Breakthrough models AlphaProof and AlphaGeometry 2 solve advanced reasoning problems in mathematics| Google DeepMind
YouTube link| AXRP - the AI X-risk Research Podcast
Breakthrough models AlphaProof and AlphaGeometry 2 solve advanced reasoning problems in mathematics| Google DeepMind
ARC's current research focus can be thought of as trying to combine mechanistic interpretability and formal verification. If we had a deep understanding of what was going on inside a neural network, we would hope to be able to use that understanding to verify that the network was not going| Alignment Research Center
We prototype using mechanistic interpretability to derive and formally verify guarantees on model performance in a toy setting.| www.alignmentforum.org
YouTube link| AXRP - the AI X-risk Research Podcast
Our AI system surpasses the state-of-the-art approach for geometry problems, advancing AI reasoning in mathematics| Google DeepMind
Contributions| openaipublic.blob.core.windows.net
YouTube link| AXRP - the AI X-risk Research Podcast
