Evan Hubinger
Alignment Stress-Testing lead · Anthropic
At a glance. Evan Hubinger is listed as Alignment Stress-Testing lead at Anthropic. The profile sits among the builders and open-source contributors. Fields listed: Safety and alignment and Language models. The source lists 1 official page and open-role pages for Anthropic and OpenAI.
Summary
Alignment Stress-Testing lead at Anthropic; first author of the Sleeper Agents paper.
Known for: Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training; Alignment faking in large language models; Risks from Learned Optimization in Advanced Machine Learning Systems.
Works at
- Anthropic 34 people in the wiki
Other documented roles
Not confirmed as current in the source profile.
- Listed as a previous organization on Hubinger's GitHub profile, Machine Intelligence Research Institute
- Listed as a previous organization on Hubinger's GitHub profile, OpenAI
Open roles
Related people
- Ethan PerezAlso at Anthropic
- Collin BurnsAlso at Anthropic
- Arthur ConmyAlso at Anthropic
- Jared KaplanAlso at Anthropic
- Nicholas CarliniAlso at Anthropic
- Eric Michael SmithSafety and alignment · Language models
- Yulia TsvetkovLanguage models · Safety and alignment
- Mathias LechnerLanguage models · Safety and alignment
- Su Lin BlodgettSafety and alignment · Language models
- Zvi MowshowitzLanguage models · Safety and alignment
Source and corrections
Read the full profile on USASI ↗
Facts on this page come from that USASI profile (reviewed Oct 21, 2026); data last checked Oct 23, 2026. See something wrong? Suggest a correction.