Community

Community, Language, Reasoning, Research, Responsible AI, Safety & Alignment, Video generation

Language models can explain neurons in language models

We use GPT-4 to automatically write explanations for the behavior of neurons in large language models and to score those explanations. We release a dataset

Community, Responsible AI, Safety & Alignment, Video generation

Frontier AI regulation: Managing emerging risks to public safety

Community, Reasoning, Research, Responsible AI, Safety & Alignment, Video generation

Improving mathematical reasoning with process supervision

We've trained a model to achieve a new state-of-the-art in mathematical problem solving by rewarding each correct step of reasoning (“process supervision”) instead of simply

Community, Responsible AI, Safety & Alignment, Video generation

Confidence-Building Measures for Artificial Intelligence: Workshop proceedings