Jul 2016 - Present. Primary author of Undebt, a static code analysis tool for performing massive automated code refactoring with over 1,400 stars on GitHub, and ...
Safety Researcher, Anthropic - Cited by 1020 - AGI Safety
Sep 17, 2024 · Alignment Stress-Testing Team Lead @AnthropicAI. Opinions my own. Previously: MIRI, OpenAI, Google, Yelp, Ripple. (he/him/his) California
Jul 10, 2018 · Evan Hubinger (he/him/his) (evanjhub@gmail.com). I am a research scientist at Anthropic where I lead the Alignment Stress-Testing team.
Evan Hubinger
>
Research interests: AGI Safety
Evan Hubinger's papers/posters: An overview of 11 proposals for building safe advanced AI · Risks from Learned Optimization in Advanced Machine Learning Systems ...
AGI safety Research Scientist at Anthropic. Previously Research Fellow at Machine Intelligence Research Institute. https://www.alignmentforum.org/users ...
Evan Hubinger (he/him/his) (evanjhub@gmail.com). I am a research scientist at Anthropic where I lead the Alignment Stress-Testing team.
Feb 12, 2024 · Evan Hubinger leads the Alignment stress-testing at Anthropic and recently published "Sleeper Agents: Training Deceptive LLMs That Persist ...
Evan Hubinger · Member of technical staff at Anthropic · Former Research fellow at Machine Intelligence Research Institute · Former Member of Technical Staff ...
Author of the Coconut programming language. An overview of 11 proposals for building safe advanced AI. May 2020. Papers. Evan Hubinger.