Science ❯ Computer Science ❯ Machine Learning

Model Training

Reinforcement Learning Performance Evaluation Geospatial Analysis Fine-Tuning Techniques Data Processing Data Transparency Algorithm Alignment Inference Processes Task Generalization Supervised Fine-Tuning Data Generalization Safety in AI Models Prompt Engineering Persona Vectors Inference Optimization Performance Benchmarks Test-Time Compute Energy Optimization Diversity Techniques Performance Metrics Behavioral Analysis

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