AIWatch.

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>