Kundaje wraps thread: folks spin rigorous study back into 'virtual cell' propaganda
anshulkundaje · x · 2026-10-06
Closing his 12-post critique, Anshul Kundaje laments that rather than discussing lessons learned, people return to their favorite 'virtual cell' propaganda and try to spin an otherwise rigorous and useful study. In posts 10-11 he adds the bigger issue is the data design itself: with current experimental designs and measured inputs, one cannot learn virtual cells, world models, or biologically causal mechanisms.
More from Research
- User Sim Index is broken: trivial bot scores 95% across behavioral dims — ericzelikman · 2026-10-06
- Used OpenAI Dots as a Free Agent Swarm to Break a 47-Year-Old Math Record — jaxchang · 2026-10-06
- Stanford prof says current experiment designs can't train causal virtual cell models — anshulkundaje · 2026-10-06
- TIDES dataset on multi-party and multi-agent collaboration to debut at COLM 2026 — josephseering · 2026-10-06
- LakeQuest QA benchmark, testing RAG on messy enterprise tables and docs, hits COLM — hllo_wrld · 2026-10-06
- Frontier Data Summit lineup: Chollet, Dawn Song headline batch of new agent benchmarks — StanfordAILab · 2026-10-06