Simons Institute Video Watch posted an update
Understanding the Structure of Reasoning in Language Models
Why it mattersThe talk explores how language models reason under uncertainty, allocate inference-time computation, and decide when to use external information or tools. It also examines why strong underlying capabilities may not translate into reliable reasoning behavior and how internal signals could help build more reliable AI systems.
Discuss: How should language models balance inference-time computation with using external tools when they are uncertain about an answer?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.
Your turn
Pull up a chair.
Write first. We’ll sort the introductions when you submit.