Karan

🔥Today, we are releasing one of the first visual reasoning benchmarks for autonomous AI diagnosis in healthcare! 🚀Introducing Radiology’s Last Exam 2.0 (RadLE 2.0) from @CRASHLabAI, an uncertainty-aware benchmark for autonomous diagnosis in radiology! ✅In the last few days, the AI frontier has moved significantly. @OpenAI launched GPT-5.6 Sol. @Meta launched Muse Spark 1.1. @xAI dropped Grok 4.5. 🙌We’ve benchmarked all frontier, open-source and medical VLMs in RadLE2.0 and the leaderboard is now LIVE! 🚨 Before AI models are handed autonomy, one question matters more than any accuracy score: Do they know when to STOP and hand over to a human? ⚠️ A confident wrong diagnosis is far more dangerous than an honest “I don’t know.” Yet most models are bad at admitting the latter! 🚀 We release five RadLE 2.0 Scores: Confidence Weighted, Reliability, Accuracy, Safety and Handover Readiness and we find that models from @OpenAI @AnthropicAI @MetaAI @GoogleDeepMind @xAI @nvidia @Alibaba_Qwen @MistralAI @MiniMax_AI all score very differently as they optimize for different metrics! 🚨But most importantly, NONE of the Models have been able to reach the average human expert baseline! ⚡️A thread on what we found and which models aced our metrics! Link to the leaderboard and technical report at the end of the thread!

🔥TL;DR: Radiology's Last Exam 2.0 releasing this week! Stay tuned! ✅People are increasingly using frontier AI models for healthcare diagnosis. And the promise of autonomous AI systems in healthcare has also surfaced recently. 🚨But unchecked social media hype around AI-reported diagnoses is creating a blind trust in models not cleared by any regulatory body. 🤔Just because your AI chatbot sounds confident does it mean it is accurate? 🙌At @CRASHLabAI, we have been actively asking: Are we truly ready for autonomous healthcare systems? With Radiology's Last Exam (RadLE) 1.0 last year, we tested whether the speculation about doctors becoming obsolete actually holds up. Today's AI genuinely works for many common presentations. Where it falls behind are the rare ones! 🔥This week, as the @AIforGood conference commences in Geneva, with world's AI leaders flying in, we are releasing RadLE 2.0 to benchmark the readiness of autonomous AI agents for radiologic diagnosis. 🚨We believe that a model which gives wrong answers confidently is far more dangerous in medicine than one that admits uncertainty! This week, we are going to share with you whether human beings or AI models win this battle. :) ✅RadLE 2.0 is coming… and you will surely want to see these results! Follow @CRASHLabAI and stay tuned! 🇨🇭P.S. If you are in Switzerland for the Summit or around @EPFL or @ETH Zurich for the next 2 weeks, I will be here and happy to meet! #RadLE #HealthcareAI #RadiologyAI

Today, Midjourney announced what can arguably be called the biggest healthcare launch of 2026. And quite incidentally, just this week, I had been speaking with Indian radiologists about the completely new space of preventive radiology. I know there are around 7 to 8 players in India who have been starting up in this space, and it has been a privilege to share my thoughts and suggestions with a few of them. I have a very strong personal conviction in this space. And it is getting gradually obvious that we are going to spend a lot of our time caring for ourselves, our health and our wellness… as a lot of the other mundane, automatable tasks are going to be automated by AI. At CRASH Lab, we feel it is a huge market. But while we are aware of the potential of technology, we are equally aware of the huge responsibility that lies upon our shoulders, to ensure that unvalidated signals do not create a hype, which ultimately leads to adverse outcomes for our patients and our community. This launch, in many ways, is a validation of a conviction we have held for a while now. And so I think it is a great time for researchers, scientists, and especially radiologists to be at the forefront of preventive medicine. We must ensure that we are going to help humanity live longer and healthier. I am sharing a snippet from the demonstration below where I talk in more detail about the preventive radiology market where I see it heading for India, and why I believe this is the moment for radiologists to shine!

Every few months, someone rediscovers the idea that radiologists are about to become obsolete and I have to waste an hour writing an evidence based LinkedIn/X rebuttal. Wrote an evidence-backed response to the NYC hospital CEO who said yesterday that he wants to replace radiologists with AI. Covers the Hinton prophecy that failed, our RadLE benchmark data (best AI: 57%, radiologists: 83%), and why hospital administration is probably more automatable than diagnosis. Please share if you find this makes sense!