EXCITED to share the release of two foundation models for electrocardiogram interpretation in @ehj_ed We built DeepECG-SL and DeepECG-SSL, two open-source ECG foundation models trained on >1M ECGs and validated across 11 external datasets (881K ECGs). 🔗 academic.oup.com/eurheartj/a…

Today we are thrilled to announce Clinical System One (CS1), a fast and efficient general-purpose decision model for medicine. Read our preprint 📄: arxiv.org/abs/2610.27099 Watch the video 🎬👇 Blog: linkedin.com/pulse/reading-f… Healthcare has a scale problem. Every health system holds decades of notes, reports, and timelines. They contain answers to questions we rarely get to ask of more than a few patients at a time. Which patients could join this trial? Who missed a follow-up? What happened to everyone who took this drug? Reading all of it, for every question, has always been too slow and too expensive. That was true even with LLMs. Thats why our team built Clinical System One (CS1). Its a small, fast decision model tailored for clinical records. Trained on 12.4 million questions and 3.6 million patients, CS1-4B beats open decision models on reading real-world patient records across diverse healthcare systems, and it runs on a single desktop GPU. We show the power of composing CS1 with traditional System 2 LLMs into agentic systems that read dense patient timelines and assess trial eligibility from a pool of a thousand candidates. Imagine trials that find every eligible patient automatically, registries that fill themselves, and care gaps surfaced across a whole population. Thats the future were building toward.

Dario has written that we need to “pace the frontier,” and Sam has agreed. People may be surprised by my response: go ahead. You guys are the frontier. By any reasonable metric — market share, revenue growth, model capability — the two of you have a duopoly on frontier intelligence. You’ve also claimed the lead is widening because of recursive self-improvement. I don’t see what you see in the lab. If the unreleased models are scary enough that you think you should slow down, I support your decision to be responsible. But stop pretending you need anyone else’s permission. Stop pretending antitrust law has to be suspended so you can form a cartel. Stop pretending you need a regulatory approval process that supersedes product liability. Stop pretending METR is independent when it is intertwined with Anthropic’s investors and staff. Stop pretending you need those same evaluators to police competitors who aren’t even at the frontier. Most of all, stop pretending the motivation to slow down is purely altruistic. You face massive product-liability exposure if your products enable a truly damaging cyberattack. The market already punishes models that behave in unpredictable or unauthorized ways. After the Hugging Face episode, it is simply good business for OpenAI and Anthropic to trade some raw power for reliability and predictability. Call it alignment if you want. It is also just giving customers what they want. Pacing the frontier would also create breathing room for a more intelligent conversation about regulation than Bernie Sanders’ “shut it all down.” China is very unlikely to join a global agreement, as you know, and that has to be taken into account as well. So go ahead and pace the frontier. You are the ones setting it. The easiest way not to build superintelligence is for you to agree not to build it. Demanding your preferred regulatory framework as the price of that will look like blackmail of the public and the political system. So just do it. If you do, you’ll buy goodwill for the next conversation. If you don’t, we’ll know this was just another bid for regulatory capture — or an election-season psyop.

How does an AI-ECG model trained at a hospital perform in a community setting detecting structural heart disease? We answered this question using the PREVUE-VALVE data, out now in @JACCJournals with @timpotsMD @djc795 @PierreEliasMD!

introducing ocr in anydoc now your agents can read scanned docs for free → sub-5ms for non ocr → 190ms median per ocr page → layout detection, tables, formulas → ocr hosted option via @firecrawl → free, no api key needed github.com/firecrawl/anydoc

OpenMHC brings together 10+ years of My Heart Counts data, to our knowledge the largest openly accessible HealthKit dataset to date: 60M+ hours of sensor data 11,894 consenting participants 19 minute-level channels 169 linked health, lifestyle, mood & behavior variables

No more LogiOptions crap... openlogi.org 🙌

@grok what’s that black thing under

[6/7] @ICMtl cardiologists and residents reviewed reports without knowing who wrote them. Rated individually: model 32% better, 35% same, clinician 33% better. Side by side: model chosen 31%, 42% same, clinician chosen 28%. Model and clinician reports were rated similarly.

[3/7] How do you give an LLM an ECG signal? 1. Turn a 12-lead ECG into discrete tokens using residual vector quantization. 2. Q-Former connects the ECG tokens with text. 3. Instruct-tune MedGemma-4B to answer ECG related questions. All training details in suppl. material.

Proud of you Rohan. Two years of tokenizer debugging and QA pipelines, and now it is out in the open. One model, one signal, from free text interpretation to LVEF and AF risk. Go celebrate, the reviewers can wait until tomorro