Login
Careers
Research
Blog
Contact
Research
Measuring Progress on Scalable Oversight for Large Language Models
Discovering Language Model Behaviors with Model-Written Evaluations
Training Verifiers to Solve Math Word Problems
Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets
Improving Accuracy of Language Models through Web Browsing
Constitutional AI: Harmlessness from AI Feedback
GAIA: a benchmark for General AI Assistants
Scaling Instruction Finetuned Language Models
DOC: Improving Long Story Coherence With Detailed Outline Control
Learning to Reason With Relational Abstractions
Enabling Large Language Models to Generate Text with Citations
Inverse Scaling: When Bigger Isn't Better