AI News Today

<p><strong><a href="https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/">Introducing Muse Spark 1.1</a></strong></p> Following <a href="https://simonwillison.net/2026/Apr/8/muse-spark/">Muse Spark in April</a>, here's Muse Spark 1.1 - the first Spark model to offer an API. Meta claim significant improvements in agentic tool calling and computer use.</p> <p>There are a lot more details are in the <a href="https://ai.meta.com/static-resource/muse-spark-1-1-evaluation-report">Muse Spark

DesignOps is shifting from governing human-led process to orchestrating human and AI technology towards ethical, meaningful outcomes. Continue reading on UX Collective »

Article URL: https://ai-2040.com/ Comments URL: https://news.ycombinator.com/item?id=48848425 Points: 23 # Comments: 5

Article URL: https://twmrg.substack.com/p/the-quiet-overlap-how-personalized Comments URL: https://news.ycombinator.com/item?id=48848422 Points: 1 # Comments: 0

<p><strong>Release:</strong> <a href="https://github.com/simonw/llm-meta-ai/releases/tag/0.1">llm-meta-ai 0.1</a></p> <p>Let's LLM run prompts against the new <a href="https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/">muse-spark-1.1</a> model.</p> <p>Tags: <a href="https://simonwillison.net/tags/llm">llm</a>, <a href="https://simonwillison.net/tags/meta">meta</a></p>

Article URL: https://marketplace.visualstudio.com/items?itemName=Codium.codium Comments URL: https://news.ycombinator.com/item?id=48848246 Points: 1 # Comments: 0

<p>Centralized Git was always going to break under agent load. The protocol that Linus shipped in 2005 was designed for a handful of humans running <code>git push</code> from a coffee shop — not a swarm of coding agents each running shallow-clone → edit → push in a tight loop, thousands of times an hour, against the same repository. By 2026, that constraint is showing up as GitHub rate-limit emails, flaking CI, and "the agent pool is throttled" Slack messages. The fix has been talked about for y

Article URL: https://vixsound.com Comments URL: https://news.ycombinator.com/item?id=48848202 Points: 1 # Comments: 0

<p><strong>Release:</strong> <a href="https://github.com/simonw/llm/releases/tag/0.31.1">llm 0.31.1</a></p> <blockquote> <ul> <li>Fix for a bug with OpenAI Chat Completion endpoints where a tool call with empty arguments could result in a JSON error from some providers. <a href="https://github.com/simonw/llm/issues/1521">#1521</a></li> </ul> </blockquote> <p>This bug came up when I was testing <a href="https://github.com/simonw/llm-meta-ai">llm-meta-ai</a>.</p> <p>Tags: <a href="https://simonwil

The soft, weirdly sexualized home-chore robot has been given some very tactile hands.

Humanoid robots at UC San Diego just successfully completed two surgical procedures.

<p>Last week I open sourced <a href="https://github.com/ronak-create/FableCut" rel="noopener noreferrer">FableCut</a>,<br> a Premiere-style video editor that runs in the browser and that AI agents can<br> operate. It hit the front page of Hacker News<br> (<a href="https://news.ycombinator.com/item?id=48845422" rel="noopener noreferrer">thread</a>), and the questions<br> there made me realize the interesting part isn't the editor. It's one design<br> decision: <strong>the project file is the inte

<p>TLDR; I got tired of babysitting N terminal tabs of five different coding-agent CLIs. So I built agentproto — one daemon that drives Claude Code, Codex, Hermes, opencode, and Mastra through the same lifecycle, and actually supervises them.</p> <h1> Why I built a daemon to drive every AI coding agent from one interface </h1> <p>I have a confession: at any given moment I have Claude Code, Codex, and<br> Hermes running in parallel terminal tabs, and I cannot remember which flag<br> spawns which,

<pre style='white-space:pre-wrap;width:81ex'>fix(agents): isolated cron busts prompt prefix cache via per-run session id (#96686) * fix(agents): isolated cron busts prompt prefix cache via per-run session id Isolated cron runs carry a per-run :run:<id> session scope (#91685) rendered verbatim into the cached system-prompt Runtime line, re-busting byte-exact prefix caching for the tool catalog after it every run (#96677, #43148 class). buildRuntimeLine now renders the stable base session key and

Article URL: https://www.pangram.com/blog/ai-in-your-feed Comments URL: https://news.ycombinator.com/item?id=48847940 Points: 84 # Comments: 62

MIT researchers developed FloatForm, a swarm of small aquatic robots that snap together like ants forming a raft, assembling into reconfigurable structures on the water.

Article URL: https://github.com/MadsLorentzen/ai-job-search Comments URL: https://news.ycombinator.com/item?id=48847930 Points: 2 # Comments: 0

<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 .

<p> AI app builder that grows your revenue </p> <p> <a href="https://www.producthunt.com/products/assembly-7?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/1192171?app_id=339">Link</a> </p>

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