AI News Today

Article URL: https://homebutler.dev/ Comments URL: https://news.ycombinator.com/item?id=48727396 Points: 1 # Comments: 0

Article URL: https://pdf-insight.com/ Comments URL: https://news.ycombinator.com/item?id=48727255 Points: 2 # Comments: 0

Article URL: https://www.getforay.ai/ Comments URL: https://news.ycombinator.com/item?id=48727207 Points: 2 # Comments: 0

<pre style='white-space:pre-wrap;width:81ex'>fix(cron): scope agent wake targets (#97949) * fix(cron): scope agent wake targets * fix(cron): refresh prompt snapshots</pre>

Article URL: https://www.404media.co/tidal-says-it-wont-pay-royalties-for-ai-generated-music/ Comments URL: https://news.ycombinator.com/item?id=48727144 Points: 3 # Comments: 4

I'm a solo founder building AMA2, a messaging runtime made for AI agents. This is my first Show HN, so I'd really appreciate your feedback. What brought me this idea: At first, I was building an AI agent for solo creators that knows everything about you and can do business chore on your behalf. When I tried to plug it into normal chat tools like Telegram, Discord, Slack... , they all felt wrong for agents: 1. They don't care about an agent's context. To follow a thread, the agent has to pull the

Article URL: https://github.com/azhakhan/dribble Comments URL: https://news.ycombinator.com/item?id=48727039 Points: 2 # Comments: 0

Article URL: https://github.com/SMJAI/open-memory-protocol Comments URL: https://news.ycombinator.com/item?id=48726966 Points: 5 # Comments: 1

OpenAI engineers used large-scale core dump analysis to debug rare infrastructure crashes, uncovering both a hardware fault and a long-standing software bug.

Vercel Agent pricing is changing. You no longer need to pre-load credits or manage a separate wallet for Vercel Agent. Instead of a $0.30 per-request fee, you now pay a Vercel Token Rate of $0.25 per million tokens, plus provider inference costs at the underlying token rate. The new Vercel Token Rate scales with the actual work each task requires. A quick question costs less than a deep investigation that reads your logs, deployments, configuration, and runtime data, spins up sandboxes, and writ

Claude Sonnet 5 from Anthropic is now available on AI Gateway . Sonnet 5 improves on Sonnet 4.6 across coding and agentic work, reaching outcomes on many tasks that previously needed an Opus model, at Sonnet pricing. The model is more agentic and follows instructions more closely. Document parsing and long-context memory use are also stronger. Sonnet 5 also uses an updated tokenizer, like the recent Opus models, which can map the same input to more tokens. Launch pricing of $2 per million input

Vercel Private Blob is now generally available for all plans. Store sensitive files like user-uploaded photos, invoices, and agent memory, and control exactly who can read them. Private stores, Signed URLs, and OIDC authentication all graduate from beta with this release. Vercel Private Blob uses the same Blob API as public blobs. Specify access: 'private' when uploading a blob: OIDC authentication Functions running on Vercel now authenticate to Vercel Private Blob with a short-lived, auto-rotat

Today, we're launching expanded capabilities for Vercel Agent in public beta. Vercel Agent now lives in your dashboard and can investigate production issues, answer questions about your projects, and take action on your behalf. Because Agent runs inside the platform that deploys and serves your app, it has access to the signals around it: deployments, logs, metrics, project configuration, usage, and connected repositories. That context is what turns a question into an answer and a problem into a

Nano Banana 2 Lite from Google is now available on AI Gateway . This Flash-Lite-tier image model is built for fast, low-cost generation. It generates images alongside text in <4s and can edit existing images across multiple turns. The cost is also lower than previous Nano Banana models. Nano Banana 2 Lite generates 1K images at $0.034 each, about half the cost of Nano Banana 2 and roughly a quarter of the cost of Nano Banana Pro at the same resolution. This model is multimodal. Use streamText or

Introducing GeneBench-Pro, a new benchmark testing AI performance in genomics, biology, and scientific research using complex, real-world datasets.

Article URL: https://reliable-ai.review/posts/2026-05-priviledge_erosion/ Comments URL: https://news.ycombinator.com/item?id=48726902 Points: 3 # Comments: 0

Hi all, As there are more and more agents in the internet; Security is going to be a big problem. Currently, the problem is solved using a LLM to guard Agent but this creates the problem of hallucination and latency, so I coded a firewall in rust that runs under five miliseconds. This works by creating a plan and enforcing the plan; for per action call, this enforces using the Model context protocols list and for sequence it tracks every single tool call and data flow; there is also a taint mech

Article URL: https://github.com/Higangssh/yocto-agent-skills Comments URL: https://news.ycombinator.com/item?id=48726866 Points: 3 # Comments: 0

<p>Hi, I'm <a href="https://x.com/ryantsuji" rel="noopener noreferrer">Ryan</a>, CTO at airCloset.</p> <p>In <a href="https://dev.to/ryantsuji/building-one-knowledge-graph-across-46-repositories-with-static-analysis-part-1-egm">Part 1</a>, I wrote about unifying 46 repositories of production code into a single knowledge graph via static analysis. The graph itself got built, but I closed the post with <strong>four open issues</strong>: no semantic search, node explosion, having to open the file t

<p>Online clothing returns cost the industry over $816 billion a year. The root cause is simple: shoppers can't see how clothes look on <em>their</em> body before buying. We built <strong>StyleSense</strong> to fix that — an AI-powered virtual wardrobe where you upload a selfie, add clothes from any product URL, and instantly see yourself wearing them.</p> <p>Here's how we built it, and why Amazon Aurora PostgreSQL and Vercel were the right choices for a 72-hour hackathon build.</p> <h2> The Sta

Comments URL: https://news.ycombinator.com/item?id=48726787 Points: 2 # Comments: 0

Article URL: https://github.com/harveer10x/earned-vs-burned-skill Comments URL: https://news.ycombinator.com/item?id=48726771 Points: 1 # Comments: 0

OpenClaw's iOS and Android apps are companion nodes, not standalone chatbots. Each phone pairs to a self-hosted Gateway over WebSocket. This adds device hardware — camera, location, voice, and Canvas — to a local-first AI agent. Here is the architecture, the capabilities, and the trade-offs for builders. The post OpenClaw Releases iOS and Android Companion Node Apps That Connect a Phone to a Self-Hosted AI Agent Gateway appeared first on MarkTechPost .

If you want a picture of the future of LLM security, imagine Whac-a-Mole meets Groundhog Day

<h2> TL;DR </h2> <p>Build AI-agents in 5 lines of code. Skip the set up & infrastructure. Live and running.<br> </p> <div class="highlight js-code-highlight"> <pre class="highlight python"><code><span class="kn">from</span> <span class="n">custodian_labs</span> <span class="kn">import</span> <span class="n">Custodian</span> <span class="n">app</span> <span class="o">=</span> <span class="nc">Custodian</span><span class="p">(</span> <span class="n">model</span><span class="o">=</span><span class=

<p> Claude Code & Codex in your Mac notch </p> <p> <a href="https://www.producthunt.com/products/agentpeek?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/1184157?app_id=339">Link</a> </p>

<p><em>I built Kajota Pulse and wrote this article as my entry for the **AWS × Vercel "H0: Hack the Zero Stack"</em>* hackathon (<strong>#H0Hackathon</strong>). Live app: <a href="https://kajota-pulse.vercel.app" rel="noopener noreferrer">kajota-pulse.vercel.app</a> · Code: <a href="https://github.com/KaJota-inc/kajota-pulse" rel="noopener noreferrer">github.com/KaJota-inc/kajota-pulse</a>*</p> <h2> The problem nobody builds for </h2> <p>Across African micro-commerce, "co-sellers" buy stock from

<p>A GitLab API token appeared in a README.md file. It was committed, pushed, and reviewed by two engineers before merging. Nobody caught it.</p> <p>This was not a junior developer's mistake. Both reviewers were experienced. The token was on line 47 of a 200-line file, sandwiched between installation instructions. At the end of a sprint, with three other reviews queued, it looked like documentation. It was a secret sitting in plain sight.</p> <p>We caught it the next day during a routine audit.

<p>Most content advice for AI search treats writing as an SEO problem with new rules. It is not. It is a citation problem with old rules, applied differently. Ranking on Google was about earning the click. Getting cited by ChatGPT, Perplexity, or Google’s AI Overviews is about earning the quote, a discipline known as answer engine optimization when it focuses on direct-answer citations.</p> <p>This guide breaks down what AI engines actually look for in a piece of content, the seven writing moves

<p>An exception queue is the next agent interface to embed.</p> <p>Dull. An exception queue is fundamentally simple. All enterprise autonomy requires is for the agent to create a review item (e.g. an Approval item) and park its state. Then it waits for someone to make a decision, and resumes execution when done. If the AI agentic workflow depended on someone physically being present to “review” the AI (e.g. by staring at chat) then it would simply be another chat app, dressing up in a hard hat f

See how Intel's Arc G3 Extreme processor performs inside the MSI Claw 8 EX AI+ and what kind of gaming performance you can expect.

We built Hawkeye because grep, IDE, TC search broke down on our internal codebase (~500k files). Every "find all references" took long enough to break focus — now with AI agents spending more time re-grepping the same files than actually writing code. Comments URL: https://news.ycombinator.com/item?id=48726376 Points: 2 # Comments: 0

<pre style='white-space:pre-wrap;width:81ex'>fix: Ollama Cloud tool calls fail on second turn (#96474) Tested and it works.</pre>

<p>Google's Agent2Agent protocol, usually shortened to A2A, had a strange first year.</p> <p>When Google announced A2A in April 2025, the pitch was clear: AI agents built by different vendors, frameworks, and teams needed a standard way to communicate. The protocol promised agent discovery, task delegation, message exchange, streaming updates, and artifact sharing. The reaction, however, was considerably less clean than the announcement.</p> <p>Some developers saw A2A as the missing agent-to-age

Wall Street pays up to $30k/year for terminals. They have access to better data & faster intel than most investors. That's one of the reasons why they win big. The playing field is finally changing... We built a Wall Street terminal for retail investors. Finally, retail investors can see breakouts in real-time breakouts, run AI predictions on any stock, see what stocks institutions are buying... PLUS A Lot More! All in one place, at a fraction of the cost. We spent years building it... hope you

I need some character voice acting for an animation I'm making. The response from people when I used Elevenlabs was that it felt flat and characters were inconsistent. I was previously using the voice reference on seedance 2.0, but obviously that's limited to 15 seconds, and I have 40 lines I have to go through Finally I just spent $75 on a human voice actor for subpar work that I can't use Anyways, is there anything better than elevenlabs right now to carry emotional tone or is it still SOTA? C

Article URL: https://github.com/chain-shield/ai-agent-audit Comments URL: https://news.ycombinator.com/item?id=48726182 Points: 2 # Comments: 0

Brennand Pierce, founder and CEO of Kinisi Robotics, discusses the company's approach to physical AI and its acquisition by Bear Robotics. The post Insights behind Kinisi’s acquisition by Bear Robotics appeared first on The Robot Report .

What does it mean? ScienceAlert stories are written, fact-checked, and edited by humans, never generated by AI. Don't miss a story, subscribe here.