Fax-degraded table fools 7 of 16 top open models into misreading a child's dose
MaziyarPanahi · x · 2026-11-06
A safety test: on a clean pediatric dosing table, all 16 top open models correctly read 300 mg. After simulating a fax (slight blur/noise), the 3 breaks apart, 7 models read it as 100 mg — and none of the 7 flagged it. A wrong number in a neat table is worse than a blurry page: clean presentation gives misreadings false credibility. High-stakes domains like healthcare should beware silent multimodal OCR errors.
More from Models
- Bittensor miners train open-source decision model REAX 1.3 — const_reborn · 2026-11-06
- Bittensor subnet 92 releases REAX 1.3, an open-source decision model blending miner models — const_reborn · 2026-11-06
- Kimi K3.1 Pro scores 9.9% on agentic WeirdML v3, ahead of Kimi-K3 but behind Claude Haiku 5.5 — scaling01 · 2026-11-06
- Rumor: GLM-5.5 to come in 32B and 122B sizes, community figure says no — TheZachMueller · 2026-11-06
- User screenshot suggests Anthropic's weekly Claude limits feel effectively unlimited — StewartalsopIII · 2026-11-06
- Leonie Shares Full Slide Deck on Building Decision Models, Still Early Days — helloiamleonie · 2026-11-06