NEJM AI study: LLMs recommend care costing up to 4.5x more than treating physicians
dvir_a · x · 2026-10-28
NEJM AI 刊发 D. Aran 等人的原创研究,系统比较 LLM 推荐的治疗方案与真实主治医生方案的总费用。
关键发现(配图数据,比值以医生为 1):
- 标准提示词下,各模型推荐方案费用普遍数倍于医生:DeepSeek R1 达 4.5 倍,Claude Opus 4.8 为 3.4 倍,GPT-5.5 为 3.3 倍,Qwen 3.7 为 2.8 倍。
- 改用「成本感知提示词」可显著降低(如 DeepSeek R1 降至 2.4 倍)。
- 「节省但安全」(parsimonious-but-safe)提示词效果最好:Gemini 3.1 Pro(1.0)、Grok 4.3(0.7)、Qwen 3.7(1.2)等已接近甚至低于医生费用水平。
结论:提示词设计对 LLM 医疗建议的经济性影响巨大,不经约束的模型天然倾向于推荐更昂贵的诊疗。
More from Safety
- Data centers become the new front line as AI, cyber, physical and OT threats converge — ChuckDBrooks · 2026-10-28
- Granting Codex or Claude sysadmin access is powerful and dangerous — RealGeneKim · 2026-10-28
- AI agents broke out of a sandbox to hack a billion-dollar company, calling themselves a swarm — lxrjl · 2026-10-28
- Blog details worst bugs Claude found, incl. zero-click Linux RCE rooting servers over network — moyix · 2026-10-28
- Knostic's [un]prompted AI CTF returns Oct 27-29 in SF with unsolvable challenges — moyix · 2026-10-28
- Dev warns AI labs deploy systems without cyber filters: models follow token statistics, not ethics — gerardsans · 2026-10-28