🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Discover the best prompting techniques for the OpenAI o1-preview model, which achieved unprecedented accuracy on medical benchmarks. msft.it/6019WNc35

Microsoft test-time compute scaling tests on o1: few % point bumps on medical reasoning for 15-30% more reasoning tokens. But overall enhanced pareto frontier. Shown across prompting & models for perf vs $ o1 has nearly saturated this bench set & needs so much less scaffolding

Reasoning models like o1/o3 will dramatically improve medical use-cases of LLMs. Here's some evidence for that. Microsoft tested o1-preview on a bunch of medical QA tasks. Not only did it achieve new SOTA, but spending more time thinking with more reasoning tokens improved the

Absolutely fantastic work by Karan Singhal and co-authors OpenAI . Comprehensive and thoughtful evaluations for language models applications in healthcare. Open source evaluation work like this really moves the entire field forward.

OpenAI Developers OMFG Regex in structured outputs? stop I’m not ready for this kind of intimacy

Was a fantastic collaboration on bringing guidance to the full family of OpenAI models. The most comprehensive structured outputs meet the world's best models 🫶 github.com/guidance-ai Shoutout Michal Moskal Andrew Braunstein cc Michelle Pokrass Nikunj Handa Eric Horvitz Kevin Scott

MAI-DxO appears to be a remarkable advance in medical AI! “> MAI-DxO boosted performance of every model tested on those 304 cases > 85.5% solve rate vs. 20% by a group of physicians > Its higher accuracy came with LOWER overall testing costs than lone LLMs or physicians”

Agentic A.I. vs experienced physicians for diagnosis of > 300 complex diagnostic cases: 4-fold higher accuracy and 20% lower cost arxiv.org/abs/2506.22405 Harsha Nori Chris Kelly Dominic King Mustafa Suleyman Eric Horvitz

AI vs. doctors for diagnosis of >300 complex cases. AI had 4x higher accuracy with 20% lower cost.

Excited to share two advances that bring us closer to real-world impact in healthcare AI: SDBench introduces a new benchmark that transforms 304 NEJM cases into interactive diagnostic simulations. AI must ask questions, order tests, and weigh costs, mirroring the complexity of

Excited for the new release of #HuggingFace durant.ly/huggingface - proud investor! durant.ly/hfrelease