Leads alignment science work at Anthropic, where he joined in January 2023 after about three years as a research fellow at MIRI. His work includes Sleeper Agents, alignment faking in large language models, and emergent misalignment from reward hacking in production RL.
Path
Current
AnthropicAlignment Science lead2023 – present
Previous
- MIMIRIResearch Fellow– 2023
OpenAIPreviously at OpenAI
GooglePreviously at Google- YEYelpPreviously at Yelp
- RIRipplePreviously at Ripple
Sourcesx.comalignmentforum.orglesswrong.comEducation and jobs are read from their own homepage or employer's page; papers checked on arXiv. From LinkedIn only the person's own public posts are read; GitHub is a link only.
Account links back to x.com/EvanHub
Nothing else on the record names them yet.
Something wrong or missing on this page? Tell me and it will be fixed or removed. Contact →