AI Dynamics

Global AI News Aggregator

About

CODE

  • pi-share-hf Updated with Enhanced Secret Detection and UI Improvements

    By

    @clementdelangue

    –

    Updated pi-share-hf, and so should you! As an additional gate, pi-share-hf now uses truffelhog to catch anything the built-in secret detection does not cover. Also cleaned up the UI/UX. Re-read README.md github.com/badlogic/pi-share… Mario Zechner (@badlogicgames) People who like sharing agent traces. I've just published all my pi-mono coding agent sessions on @huggingface so you get to laugh at or pwn me! huggingface.co/datasets/badl… I suggest you do the same, see thread below. Let's make this a community effort. Here's pi-share-hf: github.com/badlogic/pi-share… If you are working on tools that help identify PII/sensitive data, get in touch. The better the classification is, the more willing people will be to share their traces. — https://nitter.net/badlogicgames/status/2041151967695634619#m

    → View original post on X — @clementdelangue, 2026-04-07 00:17 UTC

  • Claude Code costs $200/month, Goose offers same features free

    By

    @craigbrownphd

    –

    Claude Code costs up to $200 a month. Goose does the same thing for free. venturebeat.com/infrastructu… [Translated from EN to English]

    → View original post on X — @craigbrownphd, 2026-04-07 00:01 UTC

  • pneuma-skills：AI与用户实时协作的智能创意工具
    pneuma-skills：AI与用户实时协作的智能创意工具

    By

    @elliotchen100

    –

    诸位都知道 @evermind 是 @shanda_group 系的吧，盛大下面好几个 AI Native 公司，这不来自 @TankaChat 的 bro 写了一个开源项目，觉得思路特别好，给大家科普一下。 先说一个你可能有过的体验： 你用 Claude Code 说"帮我做个网页"，AI 在终端里哗哗改代码，改完了你得自己开浏览器、找到文件、刷新页面才能看效果。觉得按钮颜色不对？切回终端，打字说"第二行那个蓝色按钮改成绿色"，AI 可能还不确定你说的是哪个按钮。改完再切回去刷新看。 整个过程就是：说 → 等 → 切 → 看 → 切回来 → 再说。来回跳，而且你用文字描述视觉问题本身就很不精确。 pneuma-skills 这个项目的做法是，把 AI 的工作区和你的预览区塞进同一个界面。AI 每改一行代码，你这边实时看到渲染结果。你觉得哪里不对，鼠标选中那个元素，AI 立刻知道你在说什么。 你可以理解成：你和 AI 在同一个 Google Docs 里协作，只不过 AI 负责写代码，你看到的是实时渲染出来的成品。 而且它不只能做一种东西。它内置了 8 个模式：网页设计、幻灯片、Markdown 文档、Excalidraw 手绘白板、draw.io 流程图、AI 插画，甚至还有一个"模式创建器"让你自己定义新的内容类型。 最让我觉得有意思的是两点： 一是它会记住你的审美偏好。你喜欢圆角、暗色系、大间距，用几次之后它就知道了，下次不用再说。这个偏好跨 session 持久化，换个项目也还在。 二是它有个叫 Evolution Agent 的东西，会分析你过去的操作，自动优化它自己的技能模板。意思是这个系统不是静态的，是会跟着你一起长的。 底层架构上，它抽象了三层契约，agent 后端是可插拔的，目前支持 Claude Code 和 OpenAI Codex。 我觉得这个项目指向了一个很重要的方向：AI 工具的下一个瓶颈不在模型能力，在交互界面。你和 AI 之间的沟通带宽越大，协作效率就越高。 这个项目盛大内部用了都觉得不错，推荐给诸位。 Ez Chan (@EzPandazki) 我本来觉得，做 PPT 应该早就每个人都有自己一套了。没想到这玩意儿好评度这么高～ 没什么好介绍的，反正 cc 天下无敌。如果有 cc 订阅（codex 也支持但是没测试过）的同学，评论自取吧。 — https://nitter.net/EzPandazki/status/2041184491490963550#m

    → View original post on X — @elliotchen100, 2026-04-06 23:41 UTC

  • VoxCPM: GitHub Repository and Project Resources

    By

    @datachaz

    –

    2/ GitHub Repo: github.com/OpenBMB/VoxCPM/ [Translated from EN to English]

    → View original post on X — @datachaz, 2026-04-06 22:59 UTC

  • Symbolic Learning vs Curve-Fitting: Reverse-Engineering Generative Programs

    By

    @fchollet

    –

    With curve-fitting, you are recording a lossy approximation of the output of some generative program. With symbolic learning, you are losslessly reverse-engineering the source code of the generative program. Symbolic learning won't be the best fit for all problems, but for the ones where the latent program is reasonably simple, it will outperform by many orders of magnitude.

    → View original post on X — @fchollet, 2026-04-06 22:06 UTC

  • Harmonic-27B: Exceptional distilled model with impressive tool calling abilities

    By

    @clementdelangue

    –

    Okay, I have no clue how he did it but this is the best 27B distill I've used to date. @DJLougen absolutely cooked with this one. Note: this is *NOT* the Hermes Agent reasoning-trace distilled version, but it works incredibly well with Hermes. I haven't had a single failed tool call and it is SMART. This one feels different. It's GOOD. Like, really, really GOOD. I don't even know if a Hermes distilled version would be better. It's THAT good. I'm curious if anyone else has tried it – this is an incredible model! huggingface.co/DJLougen/Harm…

    → View original post on X — @clementdelangue, 2026-04-06 21:52 UTC

  • Simplified Sign-In and Free API Access Needed

    By

    @steipete

    –

    Now they just need to ship a "sign in with X" mode with some free readonly quota. Current setup way is so painful.

    → View original post on X — @steipete

  • Warp Decode: Advanced AI Decoding Technology Research

    By

    @cursor_ai

    –

    Read about our work on warp decode:

    → View original post on X — @cursor_ai

  • LangChain announces Agent Infrastructure track at AI Council 2026
    LangChain announces Agent Infrastructure track at AI Council 2026

    By

    @langchain

    –

    Very excited to talk about file systems in agents at the @AICouncilConf this May! Grab tickets now before they sell out: AI Council (@AICouncilConf) Shipping an agent is the easy part. Keeping it alive while you ship 10 more? That's where things fall apart. At AI Council this year we're dedicating an entire track to the people actually solving this. Presenting the "Agent Infrastructure" lineup, curated by @tristanzajonc (Co-Founder & CEO of @continual_ai): → @BraceSproul, Head of Applied AI at @LangChain : “The File System Is All You Need” → @thesephist, Head of AI at @ThriveCapital: “Context Engineering at the Frontier” → @felipehuici, Co-Founder & CEO at @UnikraftCloud: “Running Millions of (Millisecond) AI Sandboxes without Breaking the Piggy Bank” → @glcst, CEO at @tursodatabase: “Agents will need trillions of databases. Let's give it to them!” → @MeryemArik9, CEO at @Doubleword_: “Inference for Async Agents in Production” → @jacopotagliabue, Founder at @Bauplan_labs: “Forgiveness, Not Permission: Running Agents On Production Data” → @TheParminderS , Co-Founder & CEO at Redscope AI: “Building Durable, Long-Running Autonomous Agents” Big thanks to Tristan for pulling these cracked engineers together to share what’s actually working in production. See you at AI Council 2026 in SF, May 12-14! 🎟️ aicouncil.com — https://nitter.net/AICouncilConf/status/2041254177058496866#m

    → View original post on X — @langchain, 2026-04-06 20:58 UTC

  • Grok API Integration Limitations for List Analysis

    By

    @scobleizer

    –

    Unfortunately Grok still isn't completely hooked up to lists, so you gotta use the X API to really do good analysis of them.

    → View original post on X — @scobleizer