Researcher: Judge Frontier Models on Today's Evidence, Not Hunches About the Future
anshulkundaje · x · 2026-09-09
In the same debate over LLM reasoning, Anshul Kundaje argues it's better to discuss what models can do today based on actual evidence rather than speculate about the future from hunches—especially for frontier models, where everything is opaque.
More from AGI Musings
- Reuters Institute 6-country study: AI-rewritten news boost engagement and clarity — _FelixSimon_ · 2026-09-09
- Linus Ekenstam: The Alignment Problem Is Real, and We Needed to Solve It Yesterday — LinusEkenstam · 2026-09-09
- 'Smarter supply, destroyed demand': the AI layoff-consumption spiral argument — rahul_rajendran01 · 2026-09-09
- A neat AGI test: train on all math up to 1900 and see if it derives relativity — eigenron · 2026-09-09
- Wolf culture: how Huawei traded family for speed, and who pays the bill — thisdudelikesAI · 2026-09-09
- Beff Jezos declares "test time compute is all you need" — beffjezos · 2026-09-09