Deep Ganguli

dganguli's activity

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

authored a paper over 1 year ago

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Paper • 2401.05566 • Published Jan 10, 2024 • 29

authored 2 papers over 2 years ago

Towards Measuring the Representation of Subjective Global Opinions in Language Models

Paper • 2306.16388 • Published Jun 28, 2023 • 6

Opportunities and Risks of LLMs for Scalable Deliberation with Polis

Paper • 2306.11932 • Published Jun 20, 2023 • 6