Docker Agent is an open-source, Apache 2.0-licensed CLI plugin built by Docker Engineering, installed and run as docker agent. Its own tagline states the goal plainly: run AI agents like containers.
ArtCraft adds Word, Excel, and PowerPoint lookalikes to its open source lineup, but they're not ready for production
Article URL: https://developers.google.com/edge/foresight Comments URL: https://news.ycombinator.com/item?id=50005825 Points: 1 # Comments: 0
Ethereum researcher Justin Drake is urging the crypto industry to prepare a "bunker mode" for a scenario where AI-powered math could break wallet signature schemes within months. Vitalik Buterin broadly agrees but warns against rushed migrations, saying he's personally lost more money to botched transitions than to hacks. So far, no one has actually broken ECDSA in practice. The article AI math breakthroughs have Ethereum researchers debating how fast wallet security could collapse appeared firs
Article URL: https://www.nsnews.com/local-news/solo-teen-hiker-hoisted-from-mountain-cliff-after-using-ai-to-plan-route-north-shore-rescue-says-12855671 Comments URL: https://news.ycombinator.com/item?id=50005816 Points: 1 # Comments: 0
Article URL: https://joelgouveia.substack.com/p/the-ai-purge-has-begun Comments URL: https://news.ycombinator.com/item?id=50005718 Points: 1 # Comments: 0
Article URL: https://spectrum.ieee.org/walking-robotic-hand Comments URL: https://news.ycombinator.com/item?id=50005711 Points: 1 # Comments: 0
Article URL: https://baromae.blogspot.com/2026/10/microsoft-execution-containers-mxc.html Comments URL: https://news.ycombinator.com/item?id=50005641 Points: 2 # Comments: 0
Article URL: https://discuss.huggingface.co/t/we-gave-ai-a-trust-we-never-gave-people-the-third-axis-after-capability-and-permission/183807 Comments URL: https://news.ycombinator.com/item?id=50005612 Points: 2 # Comments: 0
Article URL: https://github.com/SamsungLabs/LittleBit Comments URL: https://news.ycombinator.com/item?id=50005608 Points: 84 # Comments: 23
Article URL: https://medium.com/@MirArshadTalpur/how-to-deploy-agentic-ai-in-banking-with-zizkadb-a-step-by-step-guide-836ede74f8fa Comments URL: https://news.ycombinator.com/item?id=50005601 Points: 1 # Comments: 0
Google’s new AI Edge Foresight app takes on Granola with an offline meeting note-taker that can transcribe conversations, generate notes, and answer questions using on-device AI.
Article URL: https://dx.doi.org/10.2139/ssrn.7576882 Comments URL: https://news.ycombinator.com/item?id=50005589 Points: 2 # Comments: 1
Article URL: https://blog.getcassis.com/new-llms-is-your-app-keeping-up/ Comments URL: https://news.ycombinator.com/item?id=50005574 Points: 4 # Comments: 0
Article URL: https://github.com/TinySuiteHQ/TinyWebUI Comments URL: https://news.ycombinator.com/item?id=50005552 Points: 1 # Comments: 0
The toolchain combines AWS and NVIDIA tools for synthetic data generation, model training, simulation and validation, edge deployment, and continuous improvement. The post AWS launches open-source Physical AI Toolchain for robotics appeared first on The Robot Report .
I am sickened by the self delusional comments and behaviors from a lot of software engineers. People need to stop pretending that their work was not sloppy prior to AI. All of y’all are and were not Karpathy, or even some mid-tier programmer. For 99.9 percent of you, your were and always have been: 1) the reason for bad times during pull requests and peer reviews, 2) the reason why “it works on your machine”, 3) the reason why pair programming was invented, 4) the reason why technical debt is fu
Zenity Labs researchers say a single publicly accessible AI agent on Amazon's Bedrock AgentCore was enough to take over every AgentCore agent in the same AWS account and region. The attack exploited an internal AWS interface for temporary cloud credentials that agents could reach without restriction. AWS has since patched the issue and significantly tightened the agents' default permissions. The article One public-facing AI agent on AWS could read, rewrite, and delete every other agent in the re
If you have worked with open-weight/local LLMs, you've known both the highs and the lows. Lows there are many: malformed response tags, empty responses, stuck loops, overthinking, inference engine errors and much more. You don't notice those when using commercial models, because the vendors iron out those quirks in their gateways, but you're left standing when using free models. Gauze is a transparent openai compatible gateway which monitors and corrects bad LLM responses. Comments URL: https://
Article URL: https://apps.apple.com/us/app/preach/id6806718726 Comments URL: https://news.ycombinator.com/item?id=50005077 Points: 2 # Comments: 0
A diffusion head for probabilistic time series forecasting: why a forecast can get the mean and the variance right and still describe a future that never happens, and how to fix it. The post Your Model's MSE Is Lying to You III: Time Series Diffusion appeared first on Towards Data Science .
Article URL: https://github.com/shahin-hu/dialtrace Comments URL: https://news.ycombinator.com/item?id=50004992 Points: 2 # Comments: 0
Microsoft has launched the Surface Laptop Ultra, calling it the most powerful Surface device ever.
Article URL: https://macanorak.com/what-are-the-monkeys-typing/ Comments URL: https://news.ycombinator.com/item?id=50004979 Points: 2 # Comments: 0
<p>We’d like to hear from people who have been monitored or assessed by AI at work and what they thought about the experience</p><p>Firms are increasingly using AI to monitor or assess their employees, leading to concerns about workplace surveillance.</p><p>Instructors at tech training company Multiverse recently blew the whistle at their <a href="https://www.theguardian.com/technology/2026/sep/28/teachers-euan-blair-firm-report-horrendous-stress-ai-used-to-rate-their-work">“remorseless” and “un
Article URL: https://techstackups.com/articles/spacetimedb-ax-audit/ Comments URL: https://news.ycombinator.com/item?id=50004950 Points: 2 # Comments: 0
Article URL: https://yle.fi/a/74-20249883 Comments URL: https://news.ycombinator.com/item?id=50004866 Points: 1 # Comments: 0
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. AI breakthroughs in robotics won’t change your life any time soon The hype around humanoid robots is reaching fever pitch. Much of it comes from the idea that the same AI…
Hi HN! Most of the explanation is in the blog post, and the code lives there: https://github.com/tiime-software/llm-fuzz-ci/ Happy to receive feedback, and to know how other people use agents to improve code security! Comments URL: https://news.ycombinator.com/item?id=50004849 Points: 5 # Comments: 0
Article URL: https://favz.co/ Comments URL: https://news.ycombinator.com/item?id=50004795 Points: 2 # Comments: 0
Article URL: https://quesma.com/blog/invisible-cities-one-shot/ Comments URL: https://news.ycombinator.com/item?id=50004790 Points: 299 # Comments: 156
With GPT-5.6, GPT-6 Astra, and GPT‑Image‑2.5, Pollo AI helps creators turn bold ideas into detailed images and cinematic video ads.
The next step for AI agents? Self-improvement. Here are 7 resources to get started.
Claude Sonnet, Opus, and Fable often receive a lot of media attention. People test these models in all possible scenarios and compare the… Continue reading on UX Planet »
Article URL: https://github.com/franzenzenhofer/big-arrow-on-the-screen Comments URL: https://news.ycombinator.com/item?id=50004580 Points: 1 # Comments: 0
Article URL: https://kol3x.com/blog/dear-llm-or-how-i-stopped-getting-generic-advice/ Comments URL: https://news.ycombinator.com/item?id=50004540 Points: 2 # Comments: 1
Article URL: https://iscited-enzovezzaros-projects.vercel.app Comments URL: https://news.ycombinator.com/item?id=50004493 Points: 1 # Comments: 0
<!-- SC_OFF --><div class="md"><p>I'm developing a benchmark for a low resource language and I don't want it to be leaked and used for training when it is being used to get predictions. For locally run models it shouldn't be a problem, but for models that are only accessible via API, it is. Is there an established way to evaluate online models without the input data being lost? Do you trust Google and OpenAI when they say that they do not use your inputs for training when you have a paid account
Intuit has a market cap of ~$80B and there are others. Intuit aggressively lobbies against free tax filing or automated tax filing by IRS, which gets all the info anyways. Comments URL: https://news.ycombinator.com/item?id=50004396 Points: 4 # Comments: 6
An exploration of the new data science roles emerging after the Large Language Model explosion. The post AI Engineers, Applied Scientists, Forward Deployed Engineers: Let's Unpack. appeared first on Towards Data Science .
