David Lindner

1obextiopo's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper over 1 year ago

On scalable oversight with weak LLMs judging strong LLMs

Paper • 2407.04622 • Published Jul 5, 2024 • 15

authored a paper almost 2 years ago

Evaluating Frontier Models for Dangerous Capabilities

Paper • 2403.13793 • Published Mar 20, 2024 • 7

authored a paper about 2 years ago

Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning

Paper • 2310.12921 • Published Oct 19, 2023 • 19