This version of Talks.cam will be replaced by 1 July 2026, further information is available on the UIS Help Site
 

University of Cambridge > Talks.cam > Foundation AI > Large Language Models, Model Collapse, and the Conservation of Information

  Browse A-Z

Log in

Cambridge users (raven)details Other usersdetails No account?details

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

Large Language Models, Model Collapse, and the Conservation of Information

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

If you have a question about this talk, please contact Pietro Lio.

LT1

Do Large Language Models (LLMs) think and reason? Are they perpetual information machines, producing endless coherent and correct text from finite training data? We explore how LLMs work and whether they produce rational thought and endless information. We show how theoretical considerations and experimental results from philosophy, statistics, information theory, and machine learning argue against the thesis that LLMs are rational, information-generating entities.

This talk is part of the Foundation AI series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Cambridge University Global Health Society Economic and Social History Graduate Workshop AGI East

Other talks

Efficient fMRI design for activations and patterns Advances in Underwater and Coastal Geoarchaeology: The Study of Submerged Neolithic Sites and Landscapes off the Eastern Mediterranean Coast Are Natural Disasters Inevitable? Insights from Science and Religion Argentine Tango in between China and Japan, 1910s-1940s: Transoceanic Fragments of Musical Exchange Sheref Mansy, topic TBA On the dynamics of fast rotating stars
 

© 2006-2026 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity