Article URL: https://girard.perso.math.cnrs.fr/mustard/article.html
Comments URL: https://news.ycombinator.com/item?id=44110931
Points: 3
# Comments: 0
I've built Neuralrad Mammo AI, a free research tool that combines deep learning object detection with vision language models to analyze mammograms. The goal is to provide researchers and medical professionals with a secondary analysis tool for investigation purposes.
Important Disclaimers: - NOT FDA 510(k) cleared - this is purely for research investigation - Not for clinical diagnosis - results should only be used as a secondary opinion - Completely free - no registration, no payment, no

Article URL: https://nathan.rs/posts/gpu-shader-programming/
Comments URL: https://news.ycombinator.com/item?id=44109257
Points: 33
# Comments: 8
ive spent the past few months designing a framework for orchestrating multiple large language models in parallel — not to choose the “best,” but to let them argue, mix their outputs, and preserve dissent structurally.
It’s called Maestro heres the whitepaper https://github.com/d3fq0n1/maestro-orchestrator (Narrative version here: https://de

Article URL: https://arxiv.org/abs/2505.17989
Comments URL: https://news.ycombinator.com/item?id=44106842
Points: 44
# Comments: 3

Article URL: https://mistral.ai/news/agents-api
Comments URL: https://news.ycombinator.com/item?id=44107187
Points: 85
# Comments: 12

Article URL: https://aaronson.org/blog/square-theory
Comments URL: https://news.ycombinator.com/item?id=44107942
Points: 121
# Comments: 25
Article URL: https://blog.edward-li.com/tech/comparing-pyrefly-vs-ty/
Comments URL: https://news.ycombinator.com/item?id=44107655
Points: 69
# Comments: 29
Hey HN community! We're Preston and Eitan, and we're building Relace (https://relace.ai). We're trying to make building code agents easy and cheap.
Here’s an example of our apply model vs. whole file edits: https://youtu.be/J0-oYyozUZw
Building reliable code agents is hard. Beyond simple prototypes, any app with code generation in production quickly runs into two problems -- how do you reliably app