Spec27
Hi HN! We’re a team of ML validation specialists and we’ve been building /Spec27, a tool for testing whether AI agents still do their job safely and reliably as models, prompts, tools, and surrounding systems change. We started working on this because a lot of current LLM evaluation work seems aimed at scoring general model behavior, while many teams are deploying systems that have a specific mission to fulfill. Many of the tools also assume you have full access to the agent stack and traces so you can place SDKs and Gateways, but a lot of agents are being created on vendor platforms where this isn’t possible. As a result, we approaches it from the outside in: all tests just run to the primary interfaces of an Agent and don’t assume anything about internals. The other important things about the approach is spec-driven. Instead of treating testing as a one-off benchmark or static eval set, we let teams define reusable specifications for the behavior they want from an agent, then generate tests against those specs. With this you can automatically generate adversarial and robustness checks, so you can see what an agent is sensitive to and what kinds of changes cause it to fail. We’ve worked on validation for other AI systems before, including vision and tabular workflows, and /Spec27 is our new product for language-model-based agents. Currently in early access, so we’d love feedback! The current version is strongest for single-turn agent and application validation. We do not fully support multi-turn interactions yet, and better telemetry/tool-call integration is still on our roadmap. We’ve made the product open to try for HN readers, with a sample flow so it’s easy to poke around without much setup. We’d especially love feedback from people deploying internal agents, vendor agents, or other AI systems where reliability matters more than benchmark scores.
AI-анализ
Анализ скоро появится.
Похожие продукты
Capgo
Мгновенные обновления для Capacitor-приложений. Выпускайте исправления за минуты, а не недели. Отправляйте OTA-обновления пользователям без задержек App Store.
OpenAlternative
OpenAlternative — каталог open-source альтернатив проприетарному софту. На сайте собраны проекты из разных категорий с информацией о возможностях, стеке технологий и метриках GitHub. Платформа монетизируется через платные размещения и партнёрские ссылки.
A free curl API for IP data (we scan the IPv4 space in <24h)
The curl API for WorldIP is now live and completely free to use. You can hit it right from your terminal: curl worldip.io — returns information about your requesting IP. curl worldip.io/8.8.8.8 — returns details on any specific IP. The main differentiator here is that we aren't just wrapping another provider's API and reselling their data. We built and run our own global infrastructure capable of scanning the entire IPv4 space in about a day. Happy to answer any questions about the scanning infrastructure or the stack!
Vivari
Show HN: Vivari – Open-Source WebContainer for Node, Bun, and Python
Flashpaper
Hi everyone! This is my first HN and I’m very new to the scene. My name is Min from Bangkok. At first, I just want to create a dead man's switch for personal use and for fun. then, I think about information that self destruct like a spy movie. after that, I try to come up with the better version of Privnote or Bitwarden with self-destruct and some kind of censoring or blocking download ability. Somehow, end up with this product. :O Flashpaper is for sending any information that would be burned after reading (with counting down timer like Mission Impossible movie ! or after 24 hrs max if not opened) Encryption happens in browser and because the key stays after # in the link; server never sees the key (Zero-knowledge for web use) and— because I’m a newbie. I don’t want to connect to database because I don’t have the money and I want things light and simple. So, that’s why Flashpaper keeps things in RAM-only, no database. For AI Agent side, Flashpaper provides a REST API and an MCP server so agents can create secret links easily in dead-drop style that can be claimed only once. The second claim would get a 404 which means someone already took it. However, for the agent API flow, the server sees the plaintext for a moment before encrypting, so this flow is not zero-knowledge like the web flow. Overall, I think it work quite well for web use, but for agent API use, I am not sure this is enough security. All the limitations are listed in SECURITY.md. Some feedback would be appreciated. I make it open source with MIT license, with honorware policy for Enterprise use, like self-hosted docker. Here is my repo https://github.com/mmmpym/flashpaper and you can try it here https://flashpaper.app Again ! Please feel free to tell me what I missed. Min