MIRI has put out three major new posts: AGI Ruin: A List of Lethalities. Eliezer Yudkowsky lists reasons AGI appears likely to cause an existential catastrophe, and reasons why he thinks the current research community—MIRI included—isn't succeeding at preventing this from happening A central AI alignment problem: capabilities generalization, and the sharp left turn. Nate Soares describes… Read more »
Posts By: Rob Bensinger
Shah and Yudkowsky on alignment failures
This is the final discussion log in the Late 2021 MIRI Conversations sequence, featuring Rohin Shah and Eliezer Yudkowsky, with additional comments from Rob Bensinger, Nate Soares, Richard Ngo, and Jaan Tallinn. The discussion begins with summaries and comments on Richard and Eliezer’s debate. Rohin’s summary has since been revised and published in the… Read more »
Ngo and Yudkowsky on scientific reasoning and pivotal acts
This is a transcript of a conversation between Richard Ngo and Eliezer Yudkowsky, facilitated by Nate Soares (and with some comments from Carl Shulman). This transcript continues the Late 2021 MIRI Conversations sequence, following Ngo’s view on alignment difficulty. Color key: Chat by Richard and Eliezer Other chat 14. October 4 conversation… Read more »
Christiano and Yudkowsky on AI predictions and human intelligence
This is a transcript of a conversation between Paul Christiano and Eliezer Yudkowsky, with comments by Rohin Shah, Beth Barnes, Richard Ngo, and Holden Karnofsky, continuing the Late 2021 MIRI Conversations. Color key: Chat by Paul and Eliezer Other chat 15. October 19 comment [Yudkowsky][11:01] thing that struck me as an iota… Read more »
February 2022 Newsletter
As of yesterday, we've released the final posts in the Late 2021 MIRI Conversations sequence, a collection of (relatively raw and unedited) AI strategy conversations: Ngo's view on alignment difficulty Ngo and Yudkowsky on scientific reasoning and pivotal acts Christiano and Yudkowsky on AI predictions and human intelligence Shah and Yudkowsky on alignment failures Eliezer Yudkowsky, Nate… Read more »
January 2022 Newsletter
MIRI updates MIRI's $1.2 million Visible Thoughts Project bounty now has an FAQ, and an example of a successful partial run that you can use to inform your own runs. Scott Alexander reviews the first part of the Yudkowsky/Ngo debate. See also Richard Ngo's reply, and Rohin Shah's review of several posts from the Late 2021 MIRI Conversations. From Evan… Read more »
December 2021 Newsletter
MIRI is offering $200,000 to build a dataset of AI-dungeon-style writing annotated with the thoughts used in the writing process, and an additional $1,000,000 for scaling that dataset an additional 10x: the Visible Thoughts Project. Additionally, MIRI is in the process of releasing a series of chat logs, the Late 2021 MIRI Conversations, featuring relatively… Read more »
Ngo’s view on alignment difficulty
This post features a write-up by Richard Ngo on his views, with inline comments. Color key: Chat Google Doc content Inline comments 13. Follow-ups to the Ngo/Yudkowsky conversation 13.1. Alignment difficulty debate: Richard Ngo’s case [Ngo][9:31] (Sep. 25) As promised, here’s a write-up… Read more »
