Executive summary: The Center on Long-Term Risk reviews its 2023 activities researching AI cooperation incentives and building an s-risk community, and seeks $770,000 to expand efforts in 2024.
Key points:
In 2023, CLR progressed on analyzing commitment races, safe Pareto improvements, conflict-prone AI dispositions, and evaluating language models.
CLR aims to produce an “overseer’s manual” advising on preventing catastrophic bargaining policies and systematically evaluating cooperation in models.
CLR seeks funding to hire more researchers, continue fellowships, establish a Bay Area office, and conduct compute-intensive experiments.
CLR invites expressions of interest for research roles and career guidance around s-risk reduction.
This comment was auto-generated by the EA Forum Team. Feel free to point out issues with this summary by replying to the comment, andcontact us if you have feedback.
Executive summary: The Center on Long-Term Risk reviews its 2023 activities researching AI cooperation incentives and building an s-risk community, and seeks $770,000 to expand efforts in 2024.
Key points:
In 2023, CLR progressed on analyzing commitment races, safe Pareto improvements, conflict-prone AI dispositions, and evaluating language models.
CLR aims to produce an “overseer’s manual” advising on preventing catastrophic bargaining policies and systematically evaluating cooperation in models.
CLR seeks funding to hire more researchers, continue fellowships, establish a Bay Area office, and conduct compute-intensive experiments.
CLR invites expressions of interest for research roles and career guidance around s-risk reduction.
This comment was auto-generated by the EA Forum Team. Feel free to point out issues with this summary by replying to the comment, and contact us if you have feedback.