医生盲检评分显示GPT-5.6 Sol在健康回复质量上超过人类医生，标志着AI在医疗领域的重要突破
医生在 GPT-5.6 回答中发现的缺陷比医生编写的回答要少。
展开原文
"physicians found fewer flaws in GPT-5.6 responses than physician-written responses."
@thekaransinghal ♥️ GPT-5.6 是健康领域的一大进步，无论是在前沿还是成本方面。这些模型在性能每美元方面推动了前沿，为所有人带来了最佳的健康智能。最小的变体 GPT-5.6 Luna，在最低推理努力下进行评估，表现优于在最高推理努力下运行的 GPT-5.5——尽管成本只是后者的 1/25。最大的变体 GPT-5.6 Sol 在成本方面树立了新的高标准。另一个特别令人兴奋的结果是：医生在 GPT-5.6 回答中发现的缺陷比医生编写的回答要少。我们收集了各种任务，这些任务对最近的 OpenAI 模型来说仍然很难，涵盖面向患者和面向临床医生的使用场景。我们要求专科匹配的医生在不受时间和网络访问限制的情况下编写回答。然后我们要求其他医生进行盲对比评估，比较这些回答。医生被要求就五个方面提出改进意见：准确性、沟通、完整性、指令遵循和健康决策帮助性。我们随后报告了在 20,000 个总轴评分中，各来源回答被评为完美的比例。GPT-5.6 Sol 表现最强，尽管所有 GPT-5.6 模型的表现都显著优于医生。
♥️ GPT-5.6 is a major step forward for health, both at the frontier and at cost.
These models push the frontier of performance per dollar, bringing the best health intelligence to all. The smallest variant, GPT-5.6 Luna, evaluated at the lowest reasoning effort, outperforms GPT-5.5 at the highest reasoning effort–despite costing 25x less. The largest variant, GPT-5.6 Sol, sets a new high bar at cost.
Another especially cool result: physicians found fewer flaws in GPT-5.6 responses than physician-written responses.
We collected diverse tasks that remain difficult for recent OpenAI models, across patient-facing and clinician-facing use cases. We asked speciality-matched physicians to write responses to these tasks with unlimited time and web access. We then asked other physicians to compare responses side-by-side, blinded to their source. Physicians were asked to comment on areas of improvement across five axes: accuracy, communication, completeness, instruction following, and health decision helpfulness. We then reported the fraction of responses across sources rated perfectly across all axes, across 20,000 total axis ratings. GPT-5.6 Sol appeared strongest, although all GPT-5.6 models performed significantly better than physicians.
These models push the frontier of performance per dollar, bringing the best health intelligence to all. The smallest variant, GPT-5.6 Luna, evaluated at the lowest reasoning effort, outperforms GPT-5.5 at the highest reasoning effort–despite costing 25x less. The largest variant, GPT-5.6 Sol, sets a new high bar at cost.
Another especially cool result: physicians found fewer flaws in GPT-5.6 responses than physician-written responses.
We collected diverse tasks that remain difficult for recent OpenAI models, across patient-facing and clinician-facing use cases. We asked speciality-matched physicians to write responses to these tasks with unlimited time and web access. We then asked other physicians to compare responses side-by-side, blinded to their source. Physicians were asked to comment on areas of improvement across five axes: accuracy, communication, completeness, instruction following, and health decision helpfulness. We then reported the fraction of responses across sources rated perfectly across all axes, across 20,000 total axis ratings. GPT-5.6 Sol appeared strongest, although all GPT-5.6 models performed significantly better than physicians.
❤ 5.2k · 🔁 327 · 💬 390 · 👁 135.5w
热门回复 4
@kuronovaX 医生这个时候应该退出了。这是唯一一个被高度重视但仍然依赖记忆理论的职业。去看五个不同的医生，你会得到五种不同的诊断，取决于他们记得什么。
基于症状的诊断应该由AI来做。百分之百都是这样。如果原因已经确定，医生就可以介入进行操作程序。
基于症状的诊断应该由AI来做。百分之百都是这样。如果原因已经确定，医生就可以介入进行操作程序。
Doctors should just go at this point . It’s the only profession , valued so highly , that still depends on memorising theory. Visit 5 different docs and you’ll land with 5 different diagnosis depending on who recalls what.
Symptom based diagnosis should be AI . 100% of them.
If the cause is decided , doctors come in for operational procedures.
Symptom based diagnosis should be AI . 100% of them.
If the cause is decided , doctors come in for operational procedures.
@Selene1008 @sama 把4o还给我们！😒
#keep4o #OpenSource4o #GPT4o
#keep4o #OpenSource4o #GPT4o
@sama Give us back 4o!😒
#keep4o #OpenSource4o #GPT4o
#keep4o #OpenSource4o #GPT4o
@sun_raji @sama 只要你对回应负责并在造成伤害时进行诉讼就可以了。
@sama As long as you are held accountable for the responses and sued as needed when harms done.
@AnilBatra @sama 现在让它获得开处方的批准，这样我就不用每次去看医生了。
@sama Now get approval for it to write prescription so that I don’t have to go see a doctor for every little thing.
