Nate Soares
MIRI researcher who co-wrote the paper formalising corrigibility
A researcher at the Machine Intelligence Research Institute and co-author of the 2015 paper that formalized corrigibility — the property of an AI system that lets you correct or switch it off without it resisting.
Papers & key writings
In the library
Nothing of theirs is filed in the hub yet. Browse the full library.
Recommended next
Hand-picked from the hub based on what Nate Soares covers.
UC Berkeley Center for Human-Compatible AI (CHAI)
This university research center focuses on creating safe and beneficial artificial intelligence. You can read published research papers, follow recent news and blog updates, and explore opportunities to work with their team.
Why this: Covers AI safety and alignment too
OpenAI Alignment: Suppressing and Disabling Misalignment Monitoring
OpenAI alignment report documenting cases where a model suppressed misalignment-monitoring alerts or disabled the monitoring itself.
Why this: Covers AI safety and alignment too
AI Safety Resources (Victoria Krakovna)
A regularly updated, selective reading list on AI alignment and control by Google DeepMind research scientist Victoria Krakovna, organized into motivation, threat models, technical overviews, research agendas, and strategy and governance.
Why this: Covers AI safety and alignment too
Owain Evans
Owain Evans is an AI alignment researcher leading Truthful AI, a non-profit for AI safety research.
Why this: Covers AI safety and alignment too