Article URL: https://tech.yahoo.com/ai/articles/china-longcat-2-0-becomes-134258951.html Comments URL: https://news.ycombinator.com/item?id=48791362 Points: 6 # Comments: 1
<!-- SC_OFF --><div class="md"><p>As someone who is <strong>not affiliated</strong> with any of the big tech companies, I find it particularly difficult to have the confidence or enthusiasm to approach any ML problem with an attitude that my professors probably had at my stage in life. I'm sure I am not the only one having the following thoughts:</p> <ul> <li>"My research is currently being done better at companies."</li> <li>"ML problem I set out to solve is already solved and in fact turned in
<pre style='white-space:pre-wrap;width:81ex'>feat: animate the OpenClaw mascot across web, iOS, and Android Ports the openclaw.ai hero mascot animation (body float 4s, eye blink 3s, antenna wiggle 2s, staggered claw snaps 4s) to every product surface that shows the logo: - web: ui/public/favicon.svg now carries SMIL animations, so every <img> usage (login gate, sidebar brand, agent avatar fallback) animates with no markup changes; CSS animations do not run in <img>-loaded SVGs. - iOS: new OpenCl
Article URL: https://www.utilix.tech/ Comments URL: https://news.ycombinator.com/item?id=48790934 Points: 1 # Comments: 1
<pre style='white-space:pre-wrap;width:81ex'>[AI-assisted] fix(android): polish Voice text truncation (#100060)</pre>
I kept hitting the same wall: AI assistants are great until they need my context — the email thread, the calendar, the iMessage, the file on my disk. Cloud connectors can only reach things with a public API, so they physically can't touch the stuff that lives only on my machine. So I built Local MCP — a native macOS app that connects Claude Desktop, Claude Code, Cursor, and ChatGPT to your real local apps over MCP: Mail, Calendar, Contacts, iMessage, Microsoft Teams, Slack, WhatsApp, Notes, Remi
<h2> Osloq — ใช้ AI หาสาเหตุ bug แทน </h2> <p>เวลา AI coding tools เสนอจะ "fix bug ให้" — เราได้แต่กด Accept หรือไม่ก็ Reject สองปุ่ม สองทางเลือก</p> <p>แต่เราไม่เคยรู้ว่า:</p> <ul> <li>AI รู้ได้ยังไงว่า bug เกิดจากตรงนี้?</li> <li>มัน reproduce แล้วหรือแค่อ่านโค้ดแล้วเดา?</li> <li>ถ้าเรา accept — มันจะพังของอย่างอื่นไหม?</li> </ul> <p><strong>Osloq</strong> เลือกทางที่สาม: ไม่ใช่ "fix ให้" — แต่ "<strong>หาให้เจอแล้วบอกว่าเกิดอะไรขึ้น</strong>"</p> <h2> Osloq คืออะไร </h2> <p>Osloq เป็น AI agen
<pre style='white-space:pre-wrap;width:81ex'>fix(agents): surface Claude CLI thinking token progress</pre>
<pre style='white-space:pre-wrap;width:81ex'>fix(tui): isolate embedded event listener failures (#100117) * fix(tui): suppress unhandled rejection from async agent event handler * fix(tui): isolate embedded event listener failures --------- Co-authored-by: Peter Steinberger <steipete@gmail.com></pre>
<p>Ask ChatGPT or Perplexity "what's the best note-taking app" and you get a shortlist of three to five names. Either you're on it or you don't exist in that channel. And buying research keeps moving there.</p> <p>People call measuring this GEO or AEO tracking now. The way most teams do it is pasting questions into chatbots by hand and eyeballing the answers. That stops scaling at about ten questions, and you can't trend it week over week.</p> <h2> Doing it programmatically </h2> <p>Don't scrape
<p>I just opened 3 security issues on two of the most popular AI agent frameworks on GitHub (combined 110K+ stars).</p> <h2> The Issues </h2> <p><strong><a href="https://github.com/microsoft/autogen/issues/7917" rel="noopener noreferrer">microsoft/autogen#7917</a></strong>: Docker code executor mounts host filesystem into sandboxed containers without trust boundary validation — container escape vector.</p> <p><strong><a href="https://github.com/microsoft/autogen/issues/7918" rel="noopener norefe
<p>I scanned three of the most popular AI agent frameworks with AgentGuard v0.6.1. The results were worse than I expected.</p> <h2> The Scan </h2> <div class="table-wrapper-paragraph"><table> <thead> <tr> <th>Framework</th> <th>Files</th> <th>Findings</th> <th>CRITICAL</th> <th>HIGH</th> <th>MEDIUM</th> </tr> </thead> <tbody> <tr> <td><strong>LlamaIndex</strong></td> <td>2,951</td> <td>1,003</td> <td>252</td> <td>558</td> <td>193</td> </tr> <tr> <td><strong>AutoGen</strong></td> <td>549</td> <td
Article URL: https://claude.ai/new Comments URL: https://news.ycombinator.com/item?id=48790577 Points: 2 # Comments: 0
Article URL: https://murderszn.github.io/sprout/ Comments URL: https://news.ycombinator.com/item?id=48790523 Points: 2 # Comments: 0
Article URL: https://github.com/tadelstein9/two-tier-memory Comments URL: https://news.ycombinator.com/item?id=48790505 Points: 1 # Comments: 0
15 years in remission. ScienceAlert stories are written, fact-checked, and edited by humans, never generated by AI. Don't miss a story, subscribe here.
<p>I wrote about the <a href="https://simonwillison.net/2026/Jun/21/sqlite-utils-40rc1/">sqlite-utils 4.0rc1</a> release a couple of weeks ago. Since we only have Claude Fable on our Max subscriptions for a few more days, I decided to see if it could help me get to a 4.0 stable release that I felt truly comfortable about, since I try to keep to <a href="https://semver.org">SemVer</a> and like my incompatible major versions to be as rare as possible.</p> <p>I started with this prompt, in Claude C
<p><strong>Release:</strong> <a href="https://github.com/simonw/sqlite-utils/releases/tag/4.0rc2">sqlite-utils 4.0rc2</a></p> <p>See <a href="https://simonwillison.net/2026/Jul/5/sqlite-utils-fable/">sqlite-utils 4.0rc2, mostly written by Claude Fable (for about $149.25)</a>.</p>
Article URL: https://github.com/BotCoder254/limboo Comments URL: https://news.ycombinator.com/item?id=48790218 Points: 2 # Comments: 0
Article URL: https://www.scmp.com/tech/big-tech/article/3359335/alibabas-elements-claw-ai-agent-unearths-four-new-superconductors Comments URL: https://news.ycombinator.com/item?id=48790160 Points: 6 # Comments: 0
Article URL: https://ridgetext.com/blog/mapbox-llm-composition Comments URL: https://news.ycombinator.com/item?id=48789986 Points: 2 # Comments: 0
Article URL: https://fusionauth.io/articles/ai/ai-authentication-authorization Comments URL: https://news.ycombinator.com/item?id=48789910 Points: 1 # Comments: 0
Infinite money glitches, "artificial intelligence", massive stock buybacks, space companies, magnificent sevens, ++ See: https://www.youtube.com/watch?v=wKXgeNwNRJ4 Comments URL: https://news.ycombinator.com/item?id=48789829 Points: 7 # Comments: 9
<p><strong><a href="https://lucumr.pocoo.org/2026/7/4/better-models-worse-tools/">Better Models: Worse Tools</a></strong></p> Armin reports on a weird problem he ran into while hacking on Pi:</p> <blockquote> <p>The short version is that newer Claude models sometimes call Pi’s edit tool with extra, invented fields in the nested <code>edits[]</code> array. And not Haiku or some small model: Opus 4.8. The edit itself is usually correct but the arguments do not match the schema as the model invents
Article URL: https://www.windowscentral.com/microsoft/windows-11/microsoft-copilot-os-revealed-in-leaked-video-lightweight-windows-os-exploration-features-new-desktop-ui-built-entirely-around-copilot-and-agentic-ai Comments URL: https://news.ycombinator.com/item?id=48789807 Points: 1 # Comments: 0
Article URL: https://github.com/Vage91/Kortex Comments URL: https://news.ycombinator.com/item?id=48789790 Points: 2 # Comments: 0
Article URL: https://www.surgeos.app/ Comments URL: https://news.ycombinator.com/item?id=48789760 Points: 1 # Comments: 1
Article URL: https://github.com/iamapsrajput/agent-budget-protocol/blob/main/RFC.md Comments URL: https://news.ycombinator.com/item?id=48789750 Points: 1 # Comments: 0
She watched me look at model rankings and asked what do the numbers mean... I literally had no good way of explaining it to her so I just came up with something that is approximately in the same ballpark as some of the benchmarks out there lol Comments URL: https://news.ycombinator.com/item?id=48789647 Points: 1 # Comments: 0
<p>Admissions inboxes are a grind. Most of what lands in <code>admissions@yourschool.edu</code> is some variation of the same three questions — <em>what's the deadline, what documents do I still need, did you get my transcript</em> — interleaved with the documents themselves arriving as PDF attachments. A human reads each one, looks up the applicant in the SIS, checks which docs are still outstanding, and writes back. Then, a week before the deadline, someone exports a spreadsheet and manually n
Article URL: https://econlab.substack.com/p/we-can-finally-say-ai-isnt-killing-jobs Comments URL: https://news.ycombinator.com/item?id=48789554 Points: 1 # Comments: 0
Article URL: https://www.juanslozano.com/blog/ai-aes Comments URL: https://news.ycombinator.com/item?id=48789544 Points: 1 # Comments: 0
<p>Active Directory is where most internal compromises happen and where most AI tools give up. Darkmoon runs the AD attack path autonomously and shows every step.</p> <h2> Why AD is hard for AI </h2> <p>AD attack paths are stateful and multi step. A single prompt cannot hold the whole graph. You need an agent loop that enumerates, reasons and pivots while keeping state.</p> <h2> Playbooks as the state engine </h2> <p>In Darkmoon the AD methodology is a Markdown playbook you can read and fork. Th
<h3> The nature of an AI API </h3> <p>Somebody built this thing before you ever touched it. A lab trained it on an enormous amount of text, aligned it, wrapped it behind an endpoint, and rented it to you. You don’t own the model. You inherit the interface: its capabilities, its limits, its context window, and its cost.</p> <p>When you send a prompt, the model has two sources of information: what it learned during training and the context you provide. Training is fixed. Context is yours. From tho
<p>An AI finding you cannot reproduce is a liability, not a result. Darkmoon attaches the exact commands and raw tool output to every finding so a human can peer review it.</p> <h2> The trust problem </h2> <p>Most AI security tools return a confidence score and a paragraph. In offensive security that is not enough. If you cannot show the command that proved a vulnerability, you cannot defend it in a report or a remediation meeting.</p> <h2> What an evidence trail actually contains </h2> <p>For e
Article URL: https://arxiv.org/abs/2605.14460 Comments URL: https://news.ycombinator.com/item?id=48789488 Points: 2 # Comments: 0
<p>The point became clear to me while working on the GitHub adapter (a more or less simple GitHub gateway for AI agents creating PRs).</p> <p>At first, creating a pull request looks like one write. A branch is created, commits are pushed, and a PR appears. The API call is concrete, and the result is easy to name.</p> <p>But after building around it for a while, the word "write" started to feel too imprecise. A pull request is not only a technical object. It changes the state of a repository and
opens a port on 1977 to forward traffic to 1976, which is serving Apple's local foundation model. makes it possible to code in Xcode using Apple Intelligence with no cloud dependencies by repairing the bugs in apple's internal regex in macOS 27 and Xcode-beta. Comments URL: https://news.ycombinator.com/item?id=48789471 Points: 1 # Comments: 0
<h2> Introduction </h2> <p>Through <a href="https://dev.to/hiroki-kameyama/multi-agent-implementing-the-orchestrator-x-worker-pattern-38gd">Chapter 7 (Multi-Agent)</a>, we have a complete, functioning AI system. The final step is building <em>organizational</em> infrastructure to operate AI safely over time.<br> </p> <div class="highlight js-code-highlight"> <pre class="highlight plaintext"><code>[Before] Technical safety Security → Block malicious input Evals → Measure quality [Now] Organizatio
<p>I'm pleased to share <strong>Career</strong> <strong>Agents</strong>, an open-source initiative designed to help students, developers, and professionals navigate key stages of their career journey through AI-powered guidance.</p> <p>Career development often involves multiple challenges — crafting an effective resume, preparing for interviews, optimizing professional profiles, and identifying growth opportunities. Career Agents aims to simplify these processes by providing specialized AI assis
