Shah and Yudkowsky on alignment failures

Shah and Yudkowsky on alignment failures

This is the final discussion log in the Late 2021 MIRI Conversations [https://www.lesswrong.com/s/n945eovrA3oDueqtq] 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 Alignment Newsletter [https://www.lesswrong.com/posts/3vFmQhHBosnjZXuAJ/an-171-disagreements-between-alignment-optimists-and]. This was originally posted on 28th Feb 2022. https://www.lesswrong.com/s/n945eovrA3oDueqtq/p/tcCxPLBrEXdxN5HCQ [https://www.lesswrong.com/s/n945eovrA3oDueqtq/p/tcCxPLBrEXdxN5HCQ]

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 [https://intelligence.org/late-2021-miri-conversations/]. This was originally posted on 23rd Feb 2022. https://www.lesswrong.com/posts/NbGmfxbaABPsspib7/christiano-and-yudkowsky-on-ai-predictions-and-human [https://www.lesswrong.com/posts/NbGmfxbaABPsspib7/christiano-and-yudkowsky-on-ai-predictions-and-human]

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 [https://intelligence.org/late-2021-miri-conversations/] sequence, following Ngo's view on alignment difficulty [https://www.lesswrong.com/posts/gf9hhmSvpZfyfS34B/ngo-s-view-on-alignment-difficulty]. This was originally posted on 21st Feb 2022. https://www.lesswrong.com/s/n945eovrA3oDueqtq/p/cCrpbZ4qTCEYXbzje [https://www.lesswrong.com/s/n945eovrA3oDueqtq/p/cCrpbZ4qTCEYXbzje]

Ngo's view on alignment difficulty

This post features a write-up by Richard Ngo on his views, with inline comments. This was originally posted on 14th Dec 2021. https://www.lesswrong.com/s/n945eovrA3oDueqtq/p/gf9hhmSvpZfyfS34B [https://www.lesswrong.com/s/n945eovrA3oDueqtq/p/gf9hhmSvpZfyfS34B]

Conversation on technology forecasting and gradualism

This post is a transcript of a multi-day discussion between Paul Christiano, Richard Ngo, Eliezer Yudkowsky, Rob Bensinger, Holden Karnofsky, Rohin Shah, Carl Shulman, Nate Soares, and Jaan Tallinn, following up on the Yudkowsky/Christiano debate in 1 [https://www.lesswrong.com/posts/vwLxd6hhFvPbvKmBH/yudkowsky-and-christiano-discuss-takeoff-speeds], 2 [https://www.lesswrong.com/posts/7MCqRnZzvszsxgtJi/christiano-cotra-shulman-and-yudkowsky-on-ai-progress], 3 [https://www.lesswrong.com/posts/sCCdCLPN9E3YvdZhj/shulman-and-yudkowsky-on-ai-progress], and 4 [https://www.lesswrong.com/posts/fS7Zdj2e2xMqE6qja/more-christiano-cotra-and-yudkowsky-on-ai-progress]. This was originally posted on 9th Dec 2021. https://www.lesswrong.com/s/n945eovrA3oDueqtq/p/nPauymrHwpoNr6ipx [https://www.lesswrong.com/s/n945eovrA3oDueqtq/p/nPauymrHwpoNr6ipx]