Sami Petersen
@samicpetersen.bsky.social
Reposted by Sami Petersen
GPI Research Affiliate Philip Trammell is giving a summer course on the Economics of Transformative AI at Stanford this year. More info and applications here: digitaleconomy.stanford.edu/etai-course/. Applications close 21 February.
The Economics of Transformative AI Summer 2025
Some claim that advanced AI will greatly accelerate economic growth, displace labor, and/or risk existential catastrophe. This course covers a selection of tools in (mainly) economic theory relevant t...
digitaleconomy.stanford.edu
January 24, 2025 at 10:41 AM
GPI Research Affiliate Philip Trammell is giving a summer course on the Economics of Transformative AI at Stanford this year. More info and applications here: digitaleconomy.stanford.edu/etai-course/. Applications close 21 February.
Reposted by Sami Petersen
New working paper!
We develop an approach for safely delegating to strategically aware and potentially misaligned AI systems. The theoretical tool we use is sequential information design with imperfect recall.
A short thread on the key highlights.
We develop an approach for safely delegating to strategically aware and potentially misaligned AI systems. The theoretical tool we use is sequential information design with imperfect recall.
A short thread on the key highlights.
Imperfect Recall and AI Delegation, the new working paper by Eric Olav Chen, @alexghersen.bsky.social and Sami Petersen is now available to read here: globalprioritiesinstitute.org/imperfect-re...
Imperfect Recall and AI Delegation - Eric Olav Chen, Alexis Ghersengorin and Sami Petersen
A principal wants to deploy an artificial intelligence (AI) system to perform some task. But the AI may be misaligned and aim to pursue a conflicting objective. The principal cannot restrict its optio...
globalprioritiesinstitute.org
December 12, 2024 at 1:57 PM
New working paper!
We develop an approach for safely delegating to strategically aware and potentially misaligned AI systems. The theoretical tool we use is sequential information design with imperfect recall.
A short thread on the key highlights.
We develop an approach for safely delegating to strategically aware and potentially misaligned AI systems. The theoretical tool we use is sequential information design with imperfect recall.
A short thread on the key highlights.
Reposted by Sami Petersen
A new paper on the economics of AI alignment
A new paper on the economics of AI alignment
marginalrevolution.com
December 13, 2024 at 7:30 PM
A new paper on the economics of AI alignment
Reposted by Sami Petersen
Imperfect Recall and AI Delegation, the new working paper by Eric Olav Chen, @alexghersen.bsky.social and Sami Petersen is now available to read here: globalprioritiesinstitute.org/imperfect-re...
Imperfect Recall and AI Delegation - Eric Olav Chen, Alexis Ghersengorin and Sami Petersen
A principal wants to deploy an artificial intelligence (AI) system to perform some task. But the AI may be misaligned and aim to pursue a conflicting objective. The principal cannot restrict its optio...
globalprioritiesinstitute.org
December 4, 2024 at 3:42 PM
Imperfect Recall and AI Delegation, the new working paper by Eric Olav Chen, @alexghersen.bsky.social and Sami Petersen is now available to read here: globalprioritiesinstitute.org/imperfect-re...