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.
More from Models
- Anthropic's science blog shows Claude pulling off 'Nine Loops' particle physics calculations — rohanpaul_ai · 2026-09-26
- Xiaomi's MIT-Licensed MiMo-V2.6-Pro Hits OpenRouter at $0.87/M Output Tokens — VraserX · 2026-09-26
- Pangram AI detector only catches sloppy AI text, human-edited output passes — soumitrashukla9 · 2026-09-26
- PhD student one-shots 3Blue1Brown-style paper animations with Opus 5.5 in one hour — hsu_byron · 2026-09-26
- Calling fast models "System 1" misappropriates Kahneman, critic argues — emax · 2026-09-26
- Kimi K4 leak: Moonshot's next open-weight model reportedly targets GPT-6 in August — airesearch12 · 2026-09-26