MIRI Updates

Updates Ramana Kumar and Scott Garrabrant argue that the AGI safety community should begin prioritizing “approaches that work well in the absence of human models”: [T]o the extent that human modelling is a good idea, it is important to do...

Our December fundraiser was a success, with 348 donors contributing just over $950,000. Supporters leveraged a variety of matching opportunities, including employer matching programs, WeTrust Spring’s Ethereum-matching campaign, Facebook’s Giving Tuesday event, and professional poker players Dan Smith, Aaron Merchak,...

Edward Kmett has joined the MIRI team! Edward is a prominent Haskell developer who popularized the use of lenses for functional programming, and currently maintains many of the libraries around the Haskell core libraries. I’m also happy to announce another...

In 2018 Update: Our New Research Directions, Nate Soares discusses MIRI’s new research; our focus on “deconfusion”; some of the thinking behind our decision to default to nondisclosure on new results; and why more people than you might think should...

The AI Alignment Forum has left beta! Dovetailing with the launch, MIRI researchers Scott Garrabrant and Abram Demski will be releasing a new sequence introducing our research over the coming week, beginning here: Embedded Agents. (Shorter illustrated version here.) Other...

Summer MIRI Updates: Buck Shlegeris and Ben Weinstein-Raun have joined the MIRI team! Additionally, we ran a successful internship program over the summer, and we’re co-running a new engineer-oriented workshop series with CFAR. On the fundraising side, we received a...