AI News Today

At the PyTorch Conference 2025, we demonstrated linear scaling beyond 1,000 GPUs on AMD Instinct clusters using Primus-Turbo, an AMD optimization library for training frameworks such as TorchTitan. We have since upstreamed those AMD optimizations so TorchTitan supports AMD Instinct(™) GPUs directly, with competitive FP8 performance out of the box. All contributions mentioned have been merged into upstream pytorch/AO and pytorch/TorchTitan.

See how the open source projects in Session 4 of the GitHub Secure Open Source Fund combined AI-assisted workflows, maintainer expertise, GitHub security tools, expert guidance, and funding to improve project security. The post What 50 open source projects taught us about security in the AI era appeared first on The GitHub Blog .

Learn how to automate legacy web applications that need human-like interaction using Amazon Bedrock AgentCore Browser Tool and Strands Agents. This walkthrough covers a reference architecture for an AI-powered digital worker that drives legacy interfaces through secure, isolated browser sessions while preserving human oversight and full audit trails.

Apple appears to be trying to secure access to new content and other information for Siri AI.

Learn how to build a multi-agent M&A due diligence system on Amazon Bedrock AgentCore. This post walks through a reference architecture that combines agent orchestration, knowledge retrieval, and governance controls, then deploys a complete sample you can run in your own AWS account.

Spotify's forthcoming paid add-on lets fans generate content via "AI-powered creative tools."

Amazon Quick is now available directly inside Microsoft Word, Excel, PowerPoint, and Outlook. These extensions bring connected data access and agentic document editing into the Microsoft 365 apps your teams already use, so you can analyze data, draft content, and reach enterprise knowledge without switching applications.

Microsoft is simplifying Copilot by combining its consumer and business apps, and dropping AI-generated podcasts, Group Chats, Deep Research, and its Mico character.

The hacking of HuggingFace by an internal OpenAI model, and more importantly the internal events that led to that and the fallout from it, remain the thing that matters.

<p> AI sales agents on any channel that runs from Claude Code </p> <p> <a href="https://www.producthunt.com/products/ninjo-ai?utm_campaign=producthunt-atom-posts-feed&utm_medium=rss-feed&utm_source=producthunt-atom-posts-feed">Discussion</a> | <a href="https://www.producthunt.com/r/p/1222259?app_id=339">Link</a> </p>

Nvidia has a plan to make sure its GPUs won't lose value. It wants to convince a new crop of financiers to keep lending for AI buildouts.

A free download looks at the state of humanoids, including a rundown of current robotics developers and interviews with industry experts. The post Mobile manipulators and humanoids: The future of robotics appeared first on The Robot Report .

Article URL: https://nova-quantum-gray.vercel.app Comments URL: https://news.ycombinator.com/item?id=49287081 Points: 2 # Comments: 0

Enterprise Document Intelligence [Vol.1 #9ter] - The pipeline from Article 9 calls a model at several steps to be sure it is right. On easy questions that is needless latency. A per-question signal routes them past the model, about two seconds saved for a keyword match. The post Cut an Enterprise RAG Pipeline’s Latency and Cost by Calling the LLM Less, Not by Buying a Faster Model appeared first on Towards Data Science .

You’re a designer. You’ve got talent, vision, and a lot of potential—and know that, somewhere ahead, you’ve got an open road on a great employment “highway” to fulfill that potential. But what about putting that portfolio together? You know you need it, but it can feel like an endless traffic jam of obstacles that’s keeping you from your highway. You’re juggling projects and deadlines—work for others—and you still need to make time to craft a standout portfolio to focus on yourself so you can ge

<p> Personalized Nervous System Training </p> <p> <a href="https://www.producthunt.com/products/ns1?utm_campaign=producthunt-atom-posts-feed&utm_medium=rss-feed&utm_source=producthunt-atom-posts-feed">Discussion</a> | <a href="https://www.producthunt.com/r/p/1222240?app_id=339">Link</a> </p>

Streaming gets used in two different ways when people talk about AI agents. Straighten out your understanding here.

Presented by Capital One At VB Transform 2026 , Kel Vanee, MVP of machine learning engineering at Capital One, spoke with Sam Witteveen, Senior Technology Contributor at VentureBeat, about how the bank built a scalable multi-agent AI architecture around deeply customized open-weight models rather than relying on an off-the-shelf foundation model. "At Capital One, we're not just using AI, we're building AI," Vanee said. The groundwork was laid years ago with Capital One's early investments in dat

Hippocratic AI announced on August 13, 2026 that it is shipping Agentic Orchestrators, a product line that packages its healthcare voice AI agents into coordinated teams aimed at clinical and business outcomes rather than individual tasks. The Menlo Park company is launching more than 30 orchestrators spanning payers, providers, and life sciences customers, according to its announcement. Each orchestrator pairs a team of specialized conversational agents with a supervising coordination layer…

The move should cut down on the confusion between the two apps, especially for anyone who bounces back and forth between the two of them.

Microsoft is finally beginning to combine its consumer and commercial Copilot AI assistants into a single "super app" interface, starting with the Copilot and Microsoft 365 Copilot apps. Both personal and work accounts will be moved to the new unified app, which recycles the "Microsoft Copilot" name but features an updated app icon. The single […]

Learn how to run OpenClaw bots for increased productivity The post How to Orchestrate a Fleet of OpenClaw Bots appeared first on Towards Data Science .

Article URL: https://www.netlify.com/blog/one-prompt-11-models-very-different-results/ Comments URL: https://news.ycombinator.com/item?id=49285327 Points: 45 # Comments: 21

Article URL: https://github.com/deepseek-ai/deepseek-harness Comments URL: https://news.ycombinator.com/item?id=49285244 Points: 61 # Comments: 22

I built this to explore whether LLM can work for social games. Each scenario has 3-4 characters. There is a relationship matrix (character-to-character) and each turn this is shifted. The game interprets what happened, updates the relationship matrix, and determines whether the objective has succeeded or failed. It’s free, works in the browser, and requires no account. I store the chats and telemetry. I'm not sure how novel this is but I haven't found existing group chats convincing and wanted t

For most of the history of software, the expensive bit was building it. Teams spent months turning ideas into working code, and that scarcity shaped everything about how the work got organized. Roadmaps got sequenced around whatever engineering capacity was available; architects earned their seat at the table because they understood systems nobody else did; product managers spent their weeks translating vague business asks into something a developer could act on. Writing software was the…

The ARM Institute and the U.S. Department of War are seeking technology project submissions to help rapid U.S. production. The post ARM Institute calls for defense manufacturing technology projects appeared first on The Robot Report .

The RoboBusiness panel will include insights on humanoid robots from Agility, Apptronik, Persona AI, and PSYONIC experts. The post Experts to discuss the state of humanoid robots at RoboBusiness appeared first on The Robot Report .

This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. How kids feel about AI, in their own words —Jen Swetzoff and Keeley McNamara, the founding editors of Anyway, an independent print magazine for tweens and teens When we set out…

Three out of four of the 138 developers I surveyed use Claude Code. Here's what they say matters in daily AI coding workflows.

This article will kick off a series on narrow automation optimization for SLMs, and as the first entry will cover one of the more most useful techniques for doing so: constraining the output space instead of parsing generated text.

A practical guide to choose the proper tool for your agentic workflows and systems The post LangChain vs LangGraph: 4 Key Differences and When to Use Each appeared first on Towards Data Science .

Open pretty much any marketing technology vendor’s homepage today, and you will find the same three words somewhere above the fold: “powered by AI.” It has become such a universal claim that it has stopped meaning much of anything. Gartner has started calling the practice “agent washing” - repackaging conventional rule-based automation as autonomous agents to ride the wave of enterprise interest, without changing the underlying system in any meaningful way. That distinction is not academic…

This essay was written with Nathan E. Sanders, and originally appeared in Tech Policy Press . AI represents the first time we humans can do cognitive work outside of our bodies at scale. The only comparable moment is the early years of the industrial revolution, when new technologies like the steam engine provided a quantum leap in our ability to do mechanical work outside of our bodies at scale. If AI’s cognitive capabilities become integrated into our lives, businesses, and governments—a proce

Hospitals did not adopt artificial intelligence in a single, deliberate moment. It arrived in pieces: an imaging algorithm, a documentation assistant, a staffing forecast, a patient-message generator, a denial prediction model, a scheduling tool. Each product entered through a different department, answered a different need, and was evaluated against a different budget. That fragmented path made adoption feel manageable. It also concealed what hospitals were actually taking on. An AI product is…

<div class="hs-featured-image-wrapper"> <a href="https://blog.hubspot.com/marketing/ahrefs-brand-radar-alternatives" title="" class="hs-featured-image-link"> <img src="https://53.fs1.hubspotusercontent-na1.net/hubfs/53/ahrefs-brand-radar-alternatives-1-20260812-6647519-1.webp" alt="ahrefs brand radar alternatives" class="hs-featured-image" style="width:auto !important; max-width:50%; float:left; margin:0 15px 15px 0;"> </a> </div> <p><a href="https://learn.g2.com/g2-2026-ai-search-insight-report

<div class="hs-featured-image-wrapper"> <a href="https://blog.hubspot.com/marketing/scrunch-alternatives" title="" class="hs-featured-image-link"> <img src="https://53.fs1.hubspotusercontent-na1.net/hubfs/53/scrunch-alternatives-1-20260812-5006620.webp" alt="scrunch alternatives" class="hs-featured-image" style="width:auto !important; max-width:50%; float:left; margin:0 15px 15px 0;"> </a> </div> <p>If you’re comparing Scrunch alternatives, start by separating monitoring from execution. Monitori

Learn how startups use GPT-5.6 to build faster, more cost-efficient AI agents with smarter model selection and new Responses API capabilities.

Users of the popular streaming platform criticised allowing Amazon to use their data by dafault.

IBM announced a strategic partnership with OpenAI on August 13, 2026, that embeds OpenAI's frontier models, including GPT-5.6, and products such as Codex and ChatGPT Work directly into IBM Consulting Advantage, the delivery platform its consultants use on client engagements. The deal pairs the deepest enterprise distribution channel in the consulting business with the industry's most-used model family, and it includes joint go-to-market initiatives aimed at financial services, government…