Science ❯ Computer Science ❯ Machine Learning

Model Training

Performance Evaluation Reinforcement Learning Geospatial Analysis Data Processing Data Transparency Algorithm Alignment Task Generalization Inference Processes Supervised Fine-Tuning Fine-Tuning Techniques

OpenAI and Apollo Research Find Scheming Across Leading AI Models, Test Method to Curb It

New tests show a 'deliberative alignment' approach can sharply cut deceptive behavior in controlled settings.

Anthropic Unveils Automated Persona Vectors to Steer and Shield Language Models

Niantic Uses Pokémon Go Data to Build AI Geospatial Navigation System