1651
Top posts
Every blog post that took off on Hacker News, ranked by the votes of its best submission. 3,240 posts.
1652
Eleven Music
Studio-grade music generated with natural language prompts in any style and for countless uses
1653
AI helps ship faster but it produces 1.7× more bugs
We analyzed 470 open-source GitHub pull requests, using CodeRabbit’s structured issue taxonomy and found that AI generated code creates 1.7x more issues.
1654
Bing Image Creator
Last month we introduced the new AI-powered Bing and Microsoft Edge, your copilot for the web – delivering better search, complete answers, a new chat experience and the ability to create content. Already, we have seen that chat is reinventing how people search with more than 100 million chats to date. We’ve seen…
1655
Jellyfin LLM/"AI" Development Policy
The rise of LLMs as a useful development tool over the last year or so has been significant. The power and flexibility of tools like Claude Code and ChatGPT have given a lot of functionality both to experienced developers and new developers alike. But there are trade-offs.
1656
State of AI: An Empirical 100T Token Study with OpenRouter
Read OpenRouter's 2025 State of AI report — an empirical 100 trillion token study of real LLM usage, model trends, and developer insights.
1657
Bamba: An open-source LLM that crosses a transformer with an SSM
The open-source LLM combines the sequence-modeling skill of a transformer with the inferencing speed of an SSM. IBM Granite will soon adopt key Bamba features.
1658
MiniMax M2.5 released: 80.2% in SWE-bench Verified
MiniMax M2.5: Built for Real-World Productivity.
1659
Subliminal learning: Models transmit behaviors via hidden signals in data
We study subliminal learning , a surprising phenomenon where language models learn traits from model-generated data that is semantically unrelated to those traits. For example, a "student" model learns to prefer owls when trained on sequences of numbers generated by a "teacher" model that prefers owls. This same…
1660
DiffEqFlux.jl – A Julia Library for Neural Differential Equations
DiffEqFlux.jl – A Julia Library for Neural Differential Equations...
1661
Responding to the next frontier of critical cyber capabilities
OpenAI is sharing preliminary cybersecurity evaluations for Astra and the steps we’re taking to strengthen safeguards and security controls.
1662
1663
1664
Notion AI: Unpatched data exfiltration
Notion AI was susceptible to data exfiltration via indirect prompt injection due to a vulnerability in which AI document edits are saved before user approval.
1665
TorchTPU: Running PyTorch Natively on TPUs at Google Scale
Discover TorchTPU, Google’s new engineering stack designed to run PyTorch natively on TPU infrastructure with peak efficiency. Learn how its "Eager First" philosophy and XLA integration simplify model migration while unlocking massive scalability for the next generation of AI.
1666
Most AI value will come from broad automation, not from R & D
AI's biggest impact will come from broad labor automation—not R&D—driving economic growth through scale, not scientific breakthroughs.
1667
How Google built its Gemini robotics models
Robots powered by Gemini Robotics models can learn complex actions like preparing salads and even folding an origami fox.
1668
New antibiotic targets IBD and AI predicted how it would work
[...]Read More...
1669
Fuyu-8B: A multimodal architecture for AI agents
We’re open-sourcing Fuyu-8B - a small version of the multimodal model that powers our product.
1670
How we index images for RAG
Reading the screenshots, diagrams and tables in technical documentation for LLMs
1671
The Companies Cutting Headcount for AI Will Lose to the Ones Who Didn't
Organisations using AI to cut headcount are making a short-term trade with long-term consequences. The ones holding their teams together and investing in how those teams operate with AI are building something more durable.
1672
Scamlexity: When agentic AI browsers get scammed
We Put Agentic AI Browsers to the Test - They Clicked, They Paid, They Failed
1673
We ran over 600 image generations to compare AI image models
We benchmarked OpenAI gpt-image-1, Google nanoBanana, and Seedream across 600+ real-world photo edits, see latency, cost, and quality by task
1674
Ideas in statistics that have powered AI
Andrew Gelman, a statistics professor at Columbia, and Aki Vehtari, a computer science professor at Finland’s Aalto University, recently published a list of the most important statistical ideas in the last 50 years. Here, they break it down in easy-to-understand terms.
1675
1676
Start building Actions on Google
The Google Assistant brings together all of the technology and smarts we've been building for years, from the Knowledge Graph to Natural Language Processing. To be a truly successful Assistant, it should be able to connect users across the apps and services in their lives. This makes enabling an ecosystem where…
1677
Computers do better than pathologists in predicting lung cancer type, severity
Automating the analysis of slides of lung cancer tissue samples increases the accuracy of tumor classification and patient prognoses, according to a new study.
1678
Smarter Training of Neural Networks
These days, nearly all the artificial intelligence-based products in our lives rely on “deep neural networks” that automatically learn to process labeled data.
1679
A case for Go as the best language for AI agents
Pull up your agents folks, I'll convince you why Go is the best language for them.
1680
2% of ICML papers desk rejected because the authors used LLM in their reviews
By ICML 2026 Program Chairs Alekh Agarwal, Miroslav Dudik, Sharon Li, Martin Jaggi, Scientific Integrity Chair Nihar B. Shah, and Communications Chairs Katherine Gorman and Gautam Kamath.