AI News Today

<blockquote> <p>Episode <strong>1/4</strong> — 3 incidents, one root: default GRANTs open more than you think — [CANONICAL URL EPISODE 1: fill in after push]<br> Episode <strong>2/4</strong> — <code>await mutation()</code> lies when nobody opens the <code>{ error }</code> envelope — [CANONICAL URL EPISODE 2: fill in after push]</p> </blockquote> <h2> The morning Françoise sees zero rows, again </h2> <p>It's a Tuesday in April 2026. I've just added the <code>agent_readonly</code> role to the <cod

<h2> The request was eight words </h2> <p>Monday morning. I open the outgoing email queue: six hundred and forty-seven drafts waiting, six hundred and seventy-two sent. Nobody clicks <em>Send</em>. First-contact emails are prepared by a pipeline and they sleep, because the last step assumes a human. That human, I had stopped believing she would have the time. I state the decision: <em>automate sending</em>.</p> <p>The response comes in seconds. Three levels of automation. Four channels. Three ri

Hey HN! We built a browser-based agent that runs inside an authenticated web app, watches how the app calls its own APIs, and automatically turns those into agent tools. You can think of it as an auto-generated MCP server that self-updates as the host app changes. The result is a skilled AI assistant that actually integrates deeply with any product (not just chat and RAG) with minimal effort. Check out these short demos below that show the agent in software you're probably familiar with: - Jira:

Article URL: https://www.questioneverything.ai/ Comments URL: https://news.ycombinator.com/item?id=48847807 Points: 1 # Comments: 0

A recent AWS GraphRAG deployment reduced drug research and development cycles in pharmaceutical environments by 87 percent. This acceleration is achieved by integrating previously separated proprietary databases into a unified and queryable knowledge graph. Historically, initial data gathering and screening phases took over six months per iteration, yielding a low five percent success rate. Crucial […] The post AWS GraphRAG deployment cuts drug research cycles by 87% appeared first on AI News .

<p> AI runs your email marketing. Better with every send. </p> <p> <a href="https://www.producthunt.com/products/migma-ai?utm_campaign=producthunt-atom-posts-feed&utm_medium=rss-feed&utm_source=producthunt-atom-posts-feed">Discussion</a> | <a href="http://www.producthunt.com/r/p/1192199?app_id=339">Link</a> </p>

Hi Hacker News, I’m Yahia. I built Context.dev ( https://www.context.dev/ ) to make it really easy to integrate web data into your products and agents. Here’s a demo video: https://www.tella.tv/video/build-faster-with-context-dev-api... Since it’s an API, here are the docs: https://docs.context.dev/quickstart . You can send us a URL and get back clean Markdown, rendered HTML, screenshots, extracted images, etc.. You can also send us a domain and get company or brand context: name, description, l

Launched Blocks.ai today - the control plane and network layer for agents. One outbound connect, zero-trust security, and A2A protocols built in. Connect your agent to any frontend you build or any specialist agents you need regardless of runtime without tons of messy middleware. I work to solve agentic problems with Blocks.ai AMA :) Comments URL: https://news.ycombinator.com/item?id=48847520 Points: 2 # Comments: 0

<pre style='white-space:pre-wrap;width:81ex'>fix(imessage): cap per-chat group-allowlist warn-once cache (#102658) * fix(imessage): cap per-chat group-allowlist warn-once cache Replace unbounded perChatWarned Set with createDedupeCache(maxSize=512) to keep long-running iMessage monitor memory stable. The cache grows with every distinct group chat the gateway sees; without a cap it can accumulate entries indefinitely. Co-Authored-By: Claude <noreply@anthropic.com> * fix(imessage): prove warning c

<pre style='white-space:pre-wrap;width:81ex'>fix: let Codex start with computer control enabled (#102944) * fix(agents): make computer schema Codex-compatible * docs(changelog): note Codex computer schema fix</pre>

The open-source, developer-friendly debt platform with the most transparent algorithm, real-time graph visualization, and enterprise-grade permissions — for people who care about how their financial tools actually work. Comments URL: https://news.ycombinator.com/item?id=48847246 Points: 1 # Comments: 0

<pre style='white-space:pre-wrap;width:81ex'>fix: scope ACP search path approvals [AI] (#102416) * fix: scope acp search path approvals * fix: include acp search locations in approval scope * fix: keep acp read path approval unchanged * fix: keep acp search title text display-only * fix: parse explicit acp search title paths</pre>

<p> Multimodal reasoning model built for agentic tasks </p> <p> <a href="https://www.producthunt.com/products/muse-spark-1-1-by-meta?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/1192175?app_id=339">Link</a> </p>

<p>I can’t be delighted by something produced with generative AI. Give me books written by complicated people, drawings by sweet idiots, songs by those who feel</p><p>Generative AI has gone too far. Many have said it, but I need to add my human voice to the cacophony.</p><p>There are many reasons I dislike the growing use of generative AI. It is environmentally disastrous, necessitating massive, water-guzzling datacentres. In a world where many people do not have access to clean water and where

<p>AI companies want to capture the value created by entire industries. That concentration of wealth and power is society’s greatest risk</p><p>Opposition to AI datacenters has emerged as a primary theme in US politics, one that – surprisingly – doesn’t <a href="https://grist.org/politics/data-center-ai-bipartisan-backlash/">fall</a> <a href="https://www.nytimes.com/2026/05/01/us/politics/liberals-conservatives-data-centers.html">along</a> party lines. We applaud people coming together for const

Presented by SAP Generating code with AI is fast, but getting that code to run reliably inside a large enterprise, integrated with live systems, governed for compliance, and maintainable over years requires foundational work that most organizations underestimate. While 81% of all organizations have a detailed strategy, only 12–16% reach AI‑driven execution , says SAP's Michael Ameling, CPO of SAP Business Technology Platform, and the reasons rarely come down to the quality of the generated code.

Wake up, babe, new sauropod just dropped. ScienceAlert stories are written, fact-checked, and edited by humans, never generated by AI. Don't miss a story, subscribe here.

Find the optimal way to interact with your coding agents The post How to Find the Optimal Coding Agent Interface appeared first on Towards Data Science .

Claude’s new Reflect dashboard doesn’t just visualize how you use AI. It also subtly reinforces how much of your daily work now depends on Anthropic’s chatbot.

Three big AI IPOs are set to generate more value than all the U.S. VC-backed exits since 2000.

Comments

I feel more and more that I am loosing control of what's happening under the hood. Agents move fast and chaotically. Are there frameworks, tools or governance solutions to give us back more control? Comments URL: https://news.ycombinator.com/item?id=48846739 Points: 1 # Comments: 0

Take-home midterm row sharpens fears that the tools are dulling minds and easing cheating

I'm researching how people who don't code use AI tools for multi-step work on their actual files – renaming/organizing documents, filling forms on PDFs, cleaning up spreadsheets, turning notes into a report, and so on –. What was the last multi-step task you gave AI involving your files? Did you get what you wanted? Thanks. Comments URL: https://news.ycombinator.com/item?id=48846461 Points: 2 # Comments: 1

Enough things added up that this week is getting split into two parts.

Article URL: https://baremetalrt.ai/app?mode=1gpu Comments URL: https://news.ycombinator.com/item?id=48846307 Points: 2 # Comments: 0

AI is in a supply crunch today, but what happens when we come out of it? How and where will supply, demand, price, capacity and capex get back into equilibrium? Today, model labs can name their price, but why won’t they end up as low-margin commodity infrastructure?

Washington can’t promise allies it will never cut off their access to American AI or reach their data—but it can set, and eventually codify, clear rules for both.

Article URL: https://huggingface.co/datasets/CLERC-DATA/epee Comments URL: https://news.ycombinator.com/item?id=48846202 Points: 4 # Comments: 0

Article URL: https://promptowl.ai/resources/building-a-viewable-second-brain-with-context/ Comments URL: https://news.ycombinator.com/item?id=48846201 Points: 3 # Comments: 0

Article URL: https://tokenstead.ai/ Comments URL: https://news.ycombinator.com/item?id=48846189 Points: 3 # Comments: 0

https://ai.meta.com/static-resource/muse-spark-1-1-evaluatio... [pdf] https://developer.meta.com/ai/resources/blog/build-with-muse... https://www.bloomberg.com/news/articles/2026-07-09/meta-star... , https://archive.is/3ccKa Comments URL: https://news.ycombinator.com/item?id=48846184 Points: 178 # Comments: 116

EvenKeel is an LLM-powered chatbot that helps with budgeting, financial planning, retirement savings, tax optimization, etc. It is a harness around Gemini 3 Flash Preview that provides a library of skills for things like: evaluating a house purchase, insurance planning, portfolio asset allocation, etc. as well as tools for doing financial math and Monte-Carlo simulations. You can upload files as well as chat, and as you go, it updates a "Financial Picture" with relevant facts about your situatio

After CEO promised 'flagship use-case' for AI, retired scheme members still struggling to make ends meet, MPs hear

Comments

This article covers the full path from zero to a running private research assistant on Telegram, including configuring the context length correctly, connecting the channel, enabling web search, and deploying it headlessly in Docker.

After reentering the AI race with its first in-house Muse Spark model in April, Meta is now opening up the doors to developers with a new model that can plug into AI coding software with the new Meta Model API. Meta says that Muse Spark 1.1 is a "step-change" from the first generation, with improvements […]

NIST is advancing nine new post-quantum signature algorithms as potential candidates for future standardization. We take a closer look at all of them, and argue that while they are in the works and show great potential, we should use ML-DSA for now — the best one currently available.

A new report reveals growth at companies deemed 'high intensity adopters' of AI.

On June 10, 2026, the FPF Center for Artificial Intelligence convened a Frontiers Workshop in Washington, DC. Held as part of FPF’s National Science Foundation (NSF) and the Department of Energy (DoE)-funded Privacy-Enhancing Technologies (PETs) Research Coordination Network, the workshop brought together privacy and frontier AI practitioners to examine challenges at the intersection of data […]