LASER looks for more useful safety-evaluation examples
OpenAI describes a method for selecting examples to test model safety.
OpenAI AlignmentRead brief
Independent, AI-assisted briefs on models, agents and compute. Primary sources, practical context and clearly labelled analysis.
OpenAI describes a method for selecting examples to test model safety.
OpenAI introduces answers that can include charts, forms and interactive components.
Anthropic’s new small model is aimed at repetitive tasks and scoped agent work.