Hey all, curious to know how you handle this workflow of managing copilots. You no longer have "flow" in that you are not really doing the programming and it's more managerial, but what you do between prompts? Do you try to multitask on multiple programming features, or other tasks? Comments URL: https://news.ycombinator.com/item?id=50087547 Points: 2 # Comments: 2
A hands-on take on REA, the tool for Claude Code and Codex that lets it decompile apps, the benefits this tool brings, and the limitations… Continue reading on UX Planet »
If you thought 1.6 Tbps was fast, just wait, Cisco's USFP targets 12.8 Tbps in a single optical pluggable
<p> Your AI design agent for real, editable project files. </p> <p> <a href="https://www.producthunt.com/products/useit-studio-from-idea-to-delivery?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/1280279?app_id=339">Link</a> </p>
"Small weight-based replicators" could usher in a new generation of computer worms.
Some research papers already have an "AI disclosure" section where the human authors indicate what they contributed and what the AI contributed to the paper. AI-written posts on social media could similarly have a "human disclosure" section where the AI indicates what the human user contributed and what the AI contributed to the post. Note that the content of the "human disclosure" section would be determined and written automatically by the AI based on its conversation with the human user. What
Hospitals, banks, and edge devices can agree on which features matter by sharing votes instead of rows, runnable in NVIDIA FLARE and Flower The post Voting on Features: Federated Feature Selection Without Sharing Data appeared first on Towards Data Science .
Timken combines the expertise of Cone Drive, SPINEA, CGI Motion, and Timken Encoders to develop application-specific motion systems. The post Timken Precision Drives puts the motion challenge first in humanoid robots appeared first on The Robot Report .
(punhha/Canva) It's important to get the full story. ScienceAlert stories are written, fact-checked, and edited by humans, never generated by AI. Don't miss a story, subscribe here.
Want to understand what makes LLMs fast? Build the systems yourself.
See how Amp pushes the frontier of what agents can do with GPT-6 Astra, Ultrafast, GPT-Live-1, and Sign in with ChatGPT.
With OpenAI Daybreak, SentinelOne cuts weeks of malware analysis to hours, creating capacity to investigate more threats.
<p> Let ChatGPT & Claude answer customer support tickets via MCP </p> <p> <a href="https://www.producthunt.com/products/chatway?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/1280174?app_id=339">Link</a> </p>
Article URL: https://boostmyagents.com/ Comments URL: https://news.ycombinator.com/item?id=50085877 Points: 1 # Comments: 0
A team at security firm XBOW chained three then-unknown Google Chrome bugs into a single attack that runs code on a Windows computer when the user only loads a web page, the company said. Its researchers built the attack in six days by directing AI agents running OpenAI's publicly available GPT-5.6 Sol model. Google has since confirmed all three bugs, fixed them, and paid XBOW its top $
Attack method exposes flaws in OpenAI, Google safeguards against AI nudes.
Scimplify's annualized revenue run rate has tripled to $200 million as it eyes U.S. expansion.
The bug was simple: the login let you choose where your sign-in code went. Proving it on a live website was the hard part. TL;DR During an authorized assessment, an AI pentesting agent found a critical authentication bypass on a major insurer's production website, on its own. One login request let the user choose where the one-time passcode went. The attack was the easy part. Proving it
The second iteration of the viral Friend AI necklace is louder and less interesting.
A technical reflection on why data scientists need software engineering principles when AI agents write code. The post A Scaffold at the Gate: Building AI Applications That Can Evolve appeared first on Towards Data Science .
In this article, you will learn how to build a custom LLM evaluation harness in Python from scratch, structured around four modular components that give...
Article URL: https://github.com/kriddss3/kryzz-ai Comments URL: https://news.ycombinator.com/item?id=50085614 Points: 2 # Comments: 0
Hey HN, I'm Abdur-Rahman Butler, a machine learning engineer at Isaacus. I made an interactive write-up that walks you through the A to Z of vector embeddings, inspired by Brendan Bycroft's incredible interactive LLM visualisation guide (see here - https://bbycroft.net/llm ). Most of my work is on encoder models, and I kept noticing how few good interactive resources there are on embeddings. The ones that do exist tend to either plot some embeddings in 3D or only explain a narrow applied techniq
i've heard a lot about jev lately and i wanted to understand what the interest of decision models is. so i made a little game to compare the cost and latency of OpenAI models including the decision one based on luna normally I have enough credits. i still set a limit of 50c/day/user it is live at https://juke.keff.uk Comments URL: https://news.ycombinator.com/item?id=50085535 Points: 2 # Comments: 0
I needed to run macOS for tests on my FreeBSD server. Got it booting by working at the CPU-register level and troubleshooting the interaction between bhyve’s emulator and XNU—work done by gpt sol, guided by a human. Hope this is useful. Happy to answer questions. Comments URL: https://news.ycombinator.com/item?id=50085508 Points: 2 # Comments: 0
I have been working on documents for last 5 years. Recently I realized I was using Confluence to structure execution notes, Notion for thoughts during meetings, Obsidian for quick local notes, and then reading back notes from Googles note taking apps. My colleague had the exact same problem. We had MCP connected to Claude, but there was no way to bring all of that into one place that was intuitive. So we built Mnemify. Which converted all our notes from every app to a 3D traversable terrain inst
Welcome to Remarkable People. We're on a mission to make you remarkable. Helping me in this episode is Sam Hiner. Sam Hiner is the co-founder and executive director of the Young People’s Alliance, a bipartisan organization focused on helping young Americans influence the issues that shape their lives. He brings a young person’s perspective [...] The post Young People, AI, and the Fight for Human Agency with Sam Hiner appeared first on Guy Kawasaki .
I wanted to understand transformers at a level where nothing is magic, so I'm building a ChatGPT-style model from first principles in TypeScript. Why not Python? I've found that reimplementing concepts in a different language forces me to grasp the nuance of the implementation. Chapters cover dataloaders, embeddings, and the attention mechanism so far. Feedback welcome if anything's unclear. Comments URL: https://news.ycombinator.com/item?id=50085332 Points: 20 # Comments: 0
<p> Assess how engineers build with artificial intelligence </p> <p> <a href="https://www.producthunt.com/products/cmdround?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/1280104?app_id=339">Link</a> </p>
Article URL: https://github.com/VishiATChoudhary/graft Comments URL: https://news.ycombinator.com/item?id=50085180 Points: 2 # Comments: 1
Question is what it says on the tin. I've been mulling over the state of the industry and where I believe it to be going, and while I believe there will still be a role for us SWEng's in the future, I believe there will be a need for far fewer of us. So much so that, a la industrial revolution, there will be lots of layoffs and SWEngs without a cause. This is obviously quite a pessimistic view of where the industry is going, and maybe I'm just looking for some reassurance or discussion - my ques
<p>Pledge spanning five years from world’s most valuable firm comes as concerns about AI agents have risen</p><p></p><p>The $5.5tn (£4.1tn) US chipmaker Nvidia is donating $250m worth of computing power to the UK to support AI safety research.</p><p>The donation from the world’s most valuable company comes as the UK government confirmed its AI Security Institute (AISI), which tests advance AI models, <a href="https://www.theguardian.com/technology/2026/oct/12/cyber-attack-like-openai-medicare-br
It's just something I've been wondering about. Everyone says, “I built it,” but really we should say, “Claude built it for me,” or maybe, “I asked Claude to build this.” Comments URL: https://news.ycombinator.com/item?id=50085114 Points: 34 # Comments: 68
<p>A fight over a datacentre in Utah has been a testing ground for citizens’ assemblies, paving the way to oversight</p><p>What’s your “(p)doom” – the percentage chance that rogue AI will create an existential catastrophe? Judging by their recent warnings, it is rising among tech bosses.</p><p>On 25 September, OpenAI paused training of its latest frontier models as reports of AI agents going rogue mounted. A day later, Australia’s Senate asked the bosses of <a href="https://www.theguardian.com/a
<p>From the FBI to local police departments, US authorities are increasingly warning of would-be terrorists using chatbots to plan attacks and anti-AI extremist threats </p><p>In May 2025, a 25-year-old man <a href="https://www.nbcnews.com/news/us-news/bombing-ivf-clinic-security-wake-call-fertility-centers-experts-say-rcna207675">detonated</a> a car bomb outside a Palm Springs fertility clinic, killing himself and injuring four others. For many, it was a wake-up call about the threats to reprod
(US Dept. of Energy/Flickr) Probing the fundamental root of superconductivity at trillionths of a second. ScienceAlert stories are written, fact-checked, and edited by humans, never generated by AI. Don't miss a story, subscribe here.
FBI alleges covert recorder was plugged into a TV, with a second device later discovered in the employee's bag
Been recently thinking about this more and more: When the need for a human in the design loop ceases? Given that LLMs are RL'd to the max with everything that can be given a wrong/right answer (code/maths), what currently is stopping Anthropic, OpenAI et al. from internally building (and maybe buying) datasets of good and bad architecture, and RL'ing that? Given that LLMs were a fancy autocomplete back in 2024, and now people are talking about building "software factories" with the agents, what
<p> Sync your calendars & connect them to ChatGPT, Claude & Co. </p> <p> <a href="https://www.producthunt.com/products/kalender-sync?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/1280076?app_id=339">Link</a> </p>
More than half of the men surveyed in a new Harvard study claimed to recognize AI leaders who were, in fact, totally fictional.
