Conference Recording on Common Knowledge and AI Alignment Released · Digg

/Tech2h ago

Conference Recording on Common Knowledge and AI Alignment Released

1814831

Original post

Aran Nayebi@aran_nayebi#1431inTech

Talk recording finally up! https://www.youtube.com/watch?v=WD_OQbNzml4

Timestamps: 0:00 Intro and Program 0:20 Yoram Moses: What is Common About Common Knowledge? 0:25 Scott Aaronson: The Complexity of Agreement, With New Directions and Applications 2:01 Aran Nayebi: Intrinsic Barriers and Practical Pathways for Human-AI Alignment: An Agreement-Based Complexity Analysis 33:34 Ziv Hellman: Charges and Bets: A General Characterization of Common Priors 33:42 Robert Aumann Entrance 34:49 Robert Aumann Panel Discussion 35:40 Christina Pawlowitsch: Why the title "Agree to Disagree"? 39:02 Christina Pawlowitsch: Motivations for "Agree to Disagree"? 51:58 Steven Pinker: Origin of the poem 53:39 Steven Pinker: What is your favorite way of explaining common knowledge? 58:38 Dov Samet: Questions you would get when first giving talks on this topic 1:00:53 Jörgen Weibull: How did you get into game theory from knot theory? 1:06:27 Scott Aaronson: How reasonable is the common prior assumption? 1:08:46 Steven Pinker: Concrete example of common prior assumption 1:11:09 Aran Nayebi: Your impressions of von Neumann and Morgenstern and their influence on your career? 1:17:07 Bernhard von Stengel: Isn't there some wisdom to saying "Agree to Disagree"? 1:26:15 Ziv Hellman: Why are there markets in real life? Is it a failure of common knowledge, common priors, or rationality? 1:31:13 Christina Pawlowitsch: What are the most promising research programs today coming out of "Agree to Disagree"? 1:33:49 Paul Égré: Did you expect "Agree to Disagree" to have the impact it had when you first published it? 1:36:03 Steven Pinker: Why is only sharing the posteriors as common knowledge enough for agreement, rather than the evidence? 1:43:06 Christina Pawlowitsch: Special Issue Announcement and Concluding Remarks 1:45:28 Outro

Aran Nayebi@aran_nayebi

I'll have a recording of some of the conference coming soon, but in the meantime here are my talk slides, in case it's of general interest: https://anayebi.github.io/files/slides/Nayebi_Aumann-AgreeingToDisagree-26.pdf

I also asked Bob if he used AI, and he said, “You can't teach an old dog new tricks!”

6:49 AM · Jun 23, 2026 · 94 Views

Sentiment

Sentiment building, check back later.

Cluster Engagement

Digg Deeper

No Digg Deeper questions have been answered for this story yet.

Related links

GOOGLE.COMVia

Posts from X

Most Activity

VIEWS464BOOKMARKS2LIKES4RETWEETS1REPLIES1

Aran Nayebi@aran_nayebi

How did Aumann's agreement theorem come to be?

I've uploaded the full video👇from Nobel laureate Bob Aumann's 96th birthday conference in Paris, celebrating 50 years of “Agreeing to Disagree.”

At 1:11:09, I ask Aumann about meeting von Neumann & Morgenstern, their influence on his career, and at 1:00:53 how Nash encouraged him to switch from knot theory to game theory.

My own talk on AI safety and agreement-based complexity starts at 2:01.

The Aumann panel discussion starts at 34:49.

Turn captions on for best experience. Link + full timestamps below.👇

Aran Nayebi@aran_nayebi

Honored to meet Nobel laureate Bob Aumann & speak on AI safety in Paris at his 96th birthday celebration: Half a Century of “Agreeing to Disagree”.

Scott and I met him here for the first time. When Scott mentioned Aumann Hall at Lighthaven, Bob said: “I guess I’ve made it then!”

2h46442

Aran Nayebi@aran_nayebi

Video: https://www.youtube.com/watch?v=WD_OQbNzml4

Timestamps: 0:00 Intro and Program 0:20 Yoram Moses: What is Common About Common Knowledge? 0:25 Scott Aaronson: The Complexity of Agreement, With New Directions and Applications 2:01 Aran Nayebi: Intrinsic Barriers and Practical Pathways for Human-AI Alignment: An Agreement-Based Complexity Analysis 33:34 Ziv Hellman: Charges and Bets: A General Characterization of Common Priors 33:42 Robert Aumann Entrance 34:49 Robert Aumann Panel Discussion 35:40 Christina Pawlowitsch: Why the title "Agree to Disagree"? 39:02 Christina Pawlowitsch: Motivations for "Agree to Disagree"? 51:58 Steven Pinker: Origin of the poem 53:39 Steven Pinker: What is your favorite way of explaining common knowledge? 58:38 Dov Samet: Questions you would get when first giving talks on this topic 1:00:53 Jörgen Weibull: How did you get into game theory from knot theory? 1:06:27 Scott Aaronson: How reasonable is the common prior assumption? 1:08:46 Steven Pinker: Concrete example of common prior assumption 1:11:09 Aran Nayebi: Your impressions of von Neumann and Morgenstern and their influence on your career? 1:17:07 Bernhard von Stengel: Isn't there some wisdom to saying "Agree to Disagree"? 1:26:15 Ziv Hellman: Why are there markets in real life? Is it a failure of common knowledge, common priors, or rationality? 1:31:13 Christina Pawlowitsch: What are the most promising research programs today coming out of "Agree to Disagree"? 1:33:49 Paul Égré: Did you expect "Agree to Disagree" to have the impact it had when you first published it? 1:36:03 Steven Pinker: Why is only sharing the posteriors as common knowledge enough for agreement, rather than the evidence? 1:43:06 Christina Pawlowitsch: Special Issue Announcement and Concluding Remarks 1:45:28 Outro

Aran Nayebi@aran_nayebi

How did Aumann's agreement theorem come to be?

I've uploaded the full video👇from Nobel laureate Bob Aumann's 96th birthday conference in Paris, celebrating 50 years of “Agreeing to Disagree.”

At 1:11:09, I ask Aumann about meeting von Neumann & Morgenstern, their influence on his career, and at 1:00:53 how Nash encouraged him to switch from knot theory to game theory.

My own talk on AI safety and agreement-based complexity starts at 2:01.

The Aumann panel discussion starts at 34:49.

Turn captions on for best experience. Link + full timestamps below.👇

2h27331