Stanford professor: frontier models show 'pretense of understanding' in open bio domains

anshulkundaje · x · 2026-09-26

Stanford professor Anshul Kundaje reports that brainstorming with frontier AI models in open-ended domains like biology—where there are no closed verifiable loops—reveals a clear 'pretense of understanding.' Even with 'Ultra' thinking enabled, deeper critical questions quickly expose holes in the models' original rationale.

Related event: Stanford Professor Finds Frontier Models Fake Understanding in Open-Ended Domains(3 posts)→

Original post →

More from Models

Models channel →