Jesse Mu
Source-listed: Member of Technical Staff · Anthropic
- Language models
Selected work
5- Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red TeamingAuthor · 2025
- Forecasting Rare Language Model BehaviorsContributor · 2025
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety TrainingAuthor · 2024
- Many-shot JailbreakingContributor · 2024
- Learning to Compress Prompts with Gist TokensContributor · 2023