AI News Today

Hi HN, we posted here back in April and the most common request was to make the source code public. As of today, ctx is now open-source: https://github.com/ctxrs/ctx ctx is an Agentic Development Environment (ADE), similar to the Codex desktop app, but it works with any agent harness. I wrote more about why we are open sourcing it here: https://ctx.rs/blog/open-sourcing-ctx A few things contributed to the decision to do this: - We fell in love with Pi's extensibility model. In late 2025, we were

<p> Automatic customer context for product teams and agents. </p> <p> <a href="https://www.producthunt.com/products/propane?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/1174350?app_id=339">Link</a> </p>

Article URL: https://www.runagentrun.co.uk/articles/how-we-built-an-agent-run-news-site/ Comments URL: https://news.ycombinator.com/item?id=48570480 Points: 1 # Comments: 0

Article URL: https://www.ruxu.dev/articles/ai/build-an-ai-agent-human-in-the-loop-security/ Comments URL: https://news.ycombinator.com/item?id=48570377 Points: 1 # Comments: 0

"GRID" (Gaps, Risks, Inconsistencies, Discrepancies) is a small framework that I developed over time for my spec-driven development using coding agents. Comments URL: https://news.ycombinator.com/item?id=48570337 Points: 1 # Comments: 0

AI is pretty reliable at putting things on your calendar these days, but it hasn't quite cracked answering the related and all-important question of "What should I do this weekend?" Meta's new AI Mode in search could be a useful tool - if it ever learns to stop getting stuff wrong. AI Mode is a […]

Most LLM applications need a clear workflow, not an autonomous agent. Here's how to build one in plain Python. The post You Probably Don’t Need an Agent Framework appeared first on Towards Data Science .

Article URL: https://resources.kusho.ai/openapi-spec-analyzer Comments URL: https://news.ycombinator.com/item?id=48570226 Points: 4 # Comments: 2

I have a couple of personal app ideas that need simple cloud storage. I was hoping Claude/Codex would be able to help me put something basic together quickly, but I've been underwhelmed by tech stack suggestions they tend to suggest. They either push solutions that don't really fit (claude suggested claude artifacts) or are overkill for a single person app (e.g. "firebase + tauri + sveltekit"). Curious what stack people are using for personal projects/tools. Comments URL: https://news.ycombinato

Hey HN, I'm Jay, co-creator of Mira. An open-source, self-hosted AI code reviewer where you BYOK (bring your own key). Local models are getting really good. Hosted frontier models are getting really expensive. So, we built Mira. Mira has some snazzy features too: - It's really fast at reviewing. Average is 77s compared with Greptile's 5 minutes. Your PRs aren't going into a queue on a cloud somewhere. - Mira performs a blast radius and see what damage will be done with code change. - Learns your

Article URL: https://www.strangeloopcanon.com/p/llm-councils-show-groupthink Comments URL: https://news.ycombinator.com/item?id=48570090 Points: 3 # Comments: 0

Richard Sutton’s “Bitter Lesson” is usually read as a warning against building too much human knowledge into AI systems. Over the long run, the methods that win are not the ones that encode our clever intuition most directly, but the ones that scale: search, learning, and other general methods that can absorb more compute and data. Modern foundation model pre-training looks, at first glance, like a triumph of that lesson. We take a general architecture, expose it to massive data, and train it wi

Comments URL: https://news.ycombinator.com/item?id=48569970 Points: 3 # Comments: 4

Now that everyone and their little cousin can make apps - the next biggest hurdle is distribution for PMF validation/iterations. Besides the plethora of spammy solutions via automated personalized email and LinkedIn campaigns (which has existed ~20yrs now) what new agentic solutions are showing promise for bootstrapped startups? Comments URL: https://news.ycombinator.com/item?id=48569969 Points: 1 # Comments: 0

Hi HN, for the past few months, we’ve been working on Ferrix AI ( https://ferrix.ai/ ) As AI agents speed up engineering, deciding what to build has become the bottleneck. Developers got faster because agents fit into their workflow: tech design, code review, testing. They still make the key decisions, while AI handles mechanical work around them. At Ferrix, we are automating workflow for product managers to make product decisions efficiently. Agents handle the research synthesis, spec writing,

Sanctuary AI is not waiting for humanoid robots; it's applying physical AI to demonstrate production-ready performance. The post Sanctuary AI validates physical AI performance at Tier 1 automotive supplier appeared first on The Robot Report .

<p>An AI tool is no replacement for a doctor, and regulation is essential. But together, physicians and AI could prove beneficial</p><p>A calf cramp should not be a brush with death. Mine almost was.</p><p>For five days, I had what felt like a stubborn muscle spasm in my left calf. It was tender, swollen and getting worse. I assumed it was a muscle problem and went to my chiropractor, who treated it as a muscle issue.</p><p>Gleb Tsipursky, PhD, serves as the CEO of the future-of-work work consul

The Cloudflare One stack is a library of agent skills that gives any AI agent the knowledge it needs to plan, deploy, and manage a Zero Trust environment — no migration calls required.

'The Hum' has been one of the most perplexing unsolved mysteries. ScienceAlert stories are written, fact-checked, and edited by humans, never generated by AI. Don't miss a story, subscribe here.

The new Google Home Speaker was made with Gemini in mind, and can take natural-language commands.

Arriving six years after Google’s last smart speaker, the new HomePod-style device was redesigned to play host to Gemini’s chatbot.

Upgrades include 360-degree audio and deeper integration with Google's Gemini.

The Canadian pension giant will acquire an 8.2% stake in CtrlS, a tech giant that operates more than 15 data centers across India.

Article URL: https://northwoodsystems.ai/blog/ai-token-economics Comments URL: https://news.ycombinator.com/item?id=48569539 Points: 3 # Comments: 0

I tried the new Siri on my Mac, and although it's off to a promising start, Apple still has more work to do.

On April 19, 2026, the Honor Lightning humanoid robot ran a half-marathon in 50 minutes and 26 seconds , beating the human world record by 7 minutes and the best robot time from 2025 by almost two hours. How did they do it? Is there some magical technology or technique that unlocked this performance? How did they beat the significantly better-known Unitree (who reportedly had to supply an ice backpack to try and complete the race without overheating)? My doctoral thesis involved building and con

Comments

Smart mowers are an expensive alternative to old-fashioned yard work, but they’re finally good enough to consider if you’d rather sip an iced tea and watch a robot tame your lawn.

Learn Codex by building small and practical projects step by step.

Enterprise Document Intelligence [Vol.1 #6b] - The five field families the parser reads straight from the user’s question, with the code that fills each one The post What the Question Parser Extracts from a User String: Keywords, Scope, Shape, Decomposition, Clarification appeared first on Towards Data Science .

Article URL: https://notaru.ai Comments URL: https://news.ycombinator.com/item?id=48568987 Points: 7 # Comments: 1

A set of skills to use with Claude Code, Opencode, Codex, etc to help make your open source project more popular. Comments URL: https://news.ycombinator.com/item?id=48568942 Points: 1 # Comments: 0

Article URL: https://ycao.net/posts/math-education-llm Comments URL: https://news.ycombinator.com/item?id=48568928 Points: 1 # Comments: 1

hey all, happy to share research i've been working on for islo.dev in recent months. ever since the cheating agents ( https://debugml.github.io/cheating-agents/ ) paper came out, revealing reward hacking was 4x more prevalent than previously estimated, i've been looking into how we can deal with the issue the common approach (taken by the tbench team) is post hoc trajectory analysis. i've been interested in the idea of reframing the problem as an endpoint security problem and tackling it via san

Article URL: https://orbitsuite.cloud Comments URL: https://news.ycombinator.com/item?id=48568909 Points: 1 # Comments: 0

On 14 April, the Trump administration quietly acknowledged the widespread use of AI to automate government processes. The office of management and budget (OMB) disclosed a staggering 3,611 active or planned use cases for AI across the federal government. The list has ballooned by 70% from the one published in the final year of the Biden administration, and includes many disturbing-seeming plans to hand over sensitive governmental functions to AI. Scanning this list, many readers may find many ca

New rules cover organic rankings, AI Overviews, and user-approved search data sharing

Here's what's known so far. ScienceAlert stories are written, fact-checked, and edited by humans, never generated by AI. Don't miss a story, subscribe here.

Pinterest has launched 'Ask Pinterest,' an experimental AI-powered shopping app that lets users seek recommendations and inspiration through a conversational interface.

This will be the second market to have an Uber robotaxi service outfitted with Lucid EVs equipped with a self-driving system from Nuro.