MIRI Updates

Refining MAIM: Identifying Changes Required to Meet Conditions for Deterrence

This is part of the MIRI Single Author Series. Pieces in this series represent the beliefs and opinions of their named authors, and do not claim to speak for all of MIRI. In an op-ed published in TIME Magazine in...

Thoughts on AI 2027

This is part of the MIRI Single Author Series. Pieces in this series represent the beliefs and opinions of their named authors, and do not claim to speak for all of MIRI. Okay, I’m annoyed at people covering AI 2027...

Existing Safety Frameworks Imply Unreasonable Confidence

Joe Collman, Joe Rogero, William Brewer This is part of the MIRI Single Author Series. Pieces in this series represent the beliefs and opinions of their named authors, and do not claim to speak for all of MIRI. *** Most...

MIRI Communications Team 2024 Recap

MIRI has a long history of thinking about how to make the arrival of smarter-than-human intelligence go well. With trends in this field increasingly pointing to disaster, in early 2024 MIRI announced a strategy shift: We would communicate our understanding...

A response to OpenAI’s “How we think about safety and alignment”

This is part of the MIRI Single Author Series. Pieces in this series represent the beliefs and opinions of their named authors, and do not claim to speak for all of MIRI. OpenAI recently added a new webpage to share...

Takeover Not Required

This is part of the MIRI Single Author Series. Pieces in this series represent the beliefs and opinions of their named authors, and do not claim to speak for all of MIRI. 0. In the broadest possible terms, the threat...

Browse
Browse
Subscribe
Follow us on