Math for AI Safety

Add to your list(s) Download to your calendar using vCal

• Lionel Levine (Cornell University)
• Thursday 31 October 2024, 10:30-11:15
• Seminar Room 1, Newton Institute.

If you have a question about this talk, please contact nobody.

SSDW03 - Geometry, occupation fields, and scaling limits

AI holds great promise and, many believe, great peril. What can mathematicians contribute to ensuring that promise is fulfilled, and peril avoided? Using Activated Random Walk as a running example, I’ll illustrate the capabilities and the shortcomings of large language models on reasoning and coding tasks. I’ll highlight some research directions that might help to align future AI systems with human well being.

This talk is part of the Isaac Newton Institute Seminar Series series.

This talk is included in these lists:

• All CMS events
• Featured lists
• INI info aggregator
• Isaac Newton Institute Seminar Series
• School of Physical Sciences
• Seminar Room 1, Newton Institute
• bld31

Note that ex-directory lists are not shown.