Researcher cautions 890K-fold enrichment claims are outliers, not typical
anshulkundaje · x · 2026-09-26
Anshul Kundaje points out that a claimed 890K-fold enrichment for one target is likely a maximum rather than representative of most targets. He argues that distributions across targets and absolute hit rates would be more informative, and that such statements are technically correct but easily misread.
More from Research
- Free Open-Source Site Lets You Deep-Read Einstein's Four 1905 Papers — doodlestein · 2026-09-27
- 119k papers later: top-venue acceptance exploded from 968 to 19,003 per year since 2006 — angelaqdai · 2026-09-27
- Study: AI access drops people's willingness to say "I don't know" from 44% to 3% — The Decoder · 2026-09-27
- Bagel fine-tune packs detection, OCR, depth and masks into one 7B-active model — mostlyired12 · 2026-09-27
- Blanche Minerva's five-step pipeline shows why "just next-token prediction" no longer fits LLMs — BlancheMinerva · 2026-09-27
- Speculation: design breakthroughs in LLMs came from design data, not scaling — menhguin · 2026-09-27