# Thinking Machines 发布新模型 Inkling，通过分析 2 分钟问诊音频识别出患者未提及的心力衰竭迹象，展示了大型模型在医疗诊断中的潜力

- 来源：Unsloth AI
- 发布时间：2026-07-16 20:57
- AIWatch 分数：63
- AIWatch 标记：未精选
- AIWatch 链接：https://aiwatch.icu/events/evt_01kxznqdwta4905dedtnk0cg62
- 原文链接：https://x.com/UnslothAI/status/2077759337884487929

## 精选理由

常规快讯，保留列表

## AI 摘要

Thinking Machines 发布新模型 Inkling，通过分析 2 分钟问诊音频识别出患者未提及的心力衰竭迹象，展示了大型模型在医疗诊断中的潜力。

## 正文

RT Maziyar PANAHI<br>I played Thinking Machines' new Inkling a 2-minute doctor's visit, on my Mac Studio 🔥<br><br>The patient came in about her knee. Inkling listened to the whole thing and flagged the heart failure instead.<br><br>It heard the real audio, not a transcript. 975B params, the 1-bit GGUF (@UnslothAI), running on llama.cpp (@huggingface). Nothing left the machine.<br><br>The knee was the easy part. Buried in the small talk: out of puff on the hill, sleeping on four pillows, ankles like balloons, and she'd quietly stopped her water tablet in spring. Five signals, one diagnosis, none of it why she booked.<br><br>Her last line: "Should I have said something? It's only the knee I came about."<br><br>A 975B model just did the hardest thing in medicine: it listened to what the patient didn't think was worth mentioning.<br><br>What should it hear next?<br><video width="1920" height="1080" src="https://video.twimg.com/amplify_video/2077739397240229888/vid/avc1/1920x1080/o5Q9gX2R-tfrfnJ6.mp4?tag=29" controls="controls" poster="https://pbs.twimg.com/amplify_video_thumb/2077739397240229888/img/ZL9dkspxdE03dA1f.jpg"></video>