Zed: High-performance AI Code Editor
Article URL: https://zed.dev/blog/fastest-ai-code-editor
Comments URL: https://news.ycombinator.com/item?id=43912844
Points: 501
# Comments: 320 ⌘ Read more
9-9K Star AI 自動化瀏覽器 Stagehand 穩如「老司機」
Stagehand 是一個結合了 AI 代理、AI 工具和 Playwright 的瀏覽器自動化框架。 核心理念是：讓自動化任務既可控又智能。 與傳統工具不同，Stagehand 不僅僅依賴 AI 代理的 “黑箱操作”，而是通過與 Playwright 的深度結合，賦予開發者對瀏覽器會話的完全控制權。 這意味着，你可以輕鬆應對那些傳統工具難以解決的複雜場景，比如動態 DOM、UI ⌘ Read more
AI Powered Tabs in Firefox? But… Why?!
Plus: Firefox maker Mozilla finally admits they “May Be Forced to Scale Back Operations”. ⌘ Read more
Mark Zuckerberg has a creepy new way to invade your privacy
The new Meta app promises to be a more “personalised” form of AI. It is really a more disturbing version of ChatGPT. ⌘ Read more
IBM unveils the LinuxONE Emperor 5
Following the recent release of the IBM z17 mainframe, IBM today unveiled the LinuxONE Emperor 5, which packs much of the same hardware as the z17, but focused on Linux use. Today we’re announcing IBM LinuxONE 5, performant Linux computing platform for data, applications and your trusted AI, powered by the IBM Telum II processor with built-in AI acceleration. This launch comes at a pivotal time, as technology leaders focus on three critical imperatives: enabling … ⌘ Read more
Securing Model Context Protocol: Safer Agentic AI with Containers
Model Context Protocol (MCP) tools remain primarily in the hands of early adopters, but broader adoption is accelerating. Alongside this growth, MCP security concerns are becoming more urgent. By increasing agent autonomy, MCP tools introduce new risks related to misalignment between agent behavior and user expectations and uncontrolled execution. These systems also present a novel… ⌘ Read more
GhidraMCP 搭建及核心源碼閱讀
前言–手動逆向太費勁了 想找個 AI 助手幫我逆向一下 逛 github 的時候看到了一個 GhidraMCP 於是打算拿來用用 所以本文記錄一下 GhidraMCP 搭建以及源碼解析什麼是 MCP——-MCP（Model Context Protocol，模型上下文協議）是一種開放協議，旨在實現 大型語言模型（LLM） 應用與外部數據源、工具和服務之間的無縫集成，類似於網絡中的 HTT ⌘ Read more
圖解 AI 三大核心技術：RAG、大模型、智能體
大模型中的 Transformer 與混合專家（MoE）5 種大模型微調技術傳統 RAG 與 Agentic RAG 對比5 種經典的智能體設計模式5 大文本分塊策略智能體系統的 5 個等級傳統 RAG vs HyDERAG vs Graph RAGKV caching ⌘ Read more
The Data Surrender Trap: How Enterprises Are Losing Control in the AI Gold Rush—and the Simple Fix
Comments ⌘ Read more
(Updated)Modular Cerebro Clusterboard Supports Raspberry Pi CM4/CM5, Jetson, and Radxa CM5
Cerebro is an upcoming clusterboard platform launching on Kickstarter, designed for AI, edge computing, and embedded development. It supports a range of compute modules including Raspberry Pi CM4 and CM5, NVIDIA Jetson, and Radxa CM5, providing a modular base for scalable systems. The board can host up to four compute nodes and includes an onboard, […] ⌘ Read more
Introducing Docker MCP Catalog and Toolkit: The Simple and Secure Way to Power AI Agents with MCP Tools
Model Context Protocols (MCPs) are quickly becoming the standard for connecting AI agents to external tools, but the developer experience hasn’t caught up. Discovery is fragmented, setup is clunky, and security is too often bolted on last. Fixing this experience isn’t a solo mission—it will take an industry-wide effort. A secure, scalable, and trusted MCP… ⌘ Read more
Announcing the Automated Governance Maturity Model
We are entering an era where Governance is increasingly important; with AI systems generating code and becoming a critical part of application’s runtime infrastructure, we can produce outputs at an increasingly rapid pace. Organizations and individuals… ⌘ Read more
AI won’t steal your job, but you need to learn to work with it
You may be flummoxed by the bot you’re currently being asked to use, but soon your latest co-worker may be an AI agent. ⌘ Read more
AI won’t steal your job, but you need to learn to work with it
You may be flummoxed by the bot you’re currently being asked to use, but soon your latest co-worker may be an AI agent. ⌘ Read more
** AI-Powered Mystery Box Scams** ⌘ Read more
Will AI Replace Cybersecurity? The Truth About the Future of Cyber Defense ⌘ Read more
**Stop treating AGI' as the north-star goal of AI research**
[Comments](https://lobste.rs/s/kfadjc/stop_treating_agi_as_north_star_goal_ai) ⌘ [Read more](https://arxiv.org/abs/2502.03689)
So, the “AI” bots have reached my website. Looks like they’re just slowly crawling everything at the moment – no DDoS-like attack yet. I wonder if that has something to do with my website being 100% static HTML. There are no GET parameters they can tweak and, at the end of the day, there’s not that much data on my server anyway … And maybe they have no idea what stagit is, so it doesn’t trigger “standard behavior”, like “this is a Gitea instance, let’s crawl this like crazy!”?
Copilot ask, edit, and agent modes: What they do and when to use them
An introduction to the three distinct modes of GitHub Copilot and a practical guide for integrating them effectively into your workflow.
The post Copilot ask, edit, and agent modes: What they do and when to use them appeared first on The GitHub Blog. ⌘ Read more
Prompt Injection in ChatGPT and LLMs: What Developers Must Know
Understanding the hidden dangers behind prompt injection can help you build safer AI applications.
[Continue reading on InfoSec Write-ups »](https://infosecwri … ⌘ Read more
Flume x JPEGMAFIA – AI Girlfriend
Vid directed by Logan Fields & JPEGMAFIA. We Live in a Society is out tomorrow… Continue reading… ⌘ Read more
The AI-Powered DevOps revolution: Redefining developer collaboration
Collaboration is crucial to successful software delivery. Let’s dive into how AI can help your development teams decrease their time to delivery, and foster better communication and collaboration using GitHub Copilot.
The post [The AI-Powered DevOps revolution: Redefining developer collaboration](https://github.blog/ai-and-ml/github-copilot/the-ai-powered-devops-revolution-redefining-de … ⌘ Read more
9 Security Threats in Generative AI Agents ⌘ Read more
“I use zip bombs to protect my server”
The majority of the traffic on the web is from bots. For the most part, these bots are used to discover new content. These are RSS Feed readers, search engines crawling your content, or nowadays AI bots crawling content to power LLMs. But then there are the malicious bots. These are from spammers, content scrapers or hackers. At my old employer, a bot discovered a wordpress vulnerability and inserted a malicious script into our server. It then turned the m … ⌘ Read more
From MCP to multi-agents: The top 10 open source AI projects on GitHub right now and why they matter
Get insights on the latest trends from GitHub experts while catching up on these exciting new projects.
The post [From MCP to multi-agents: The top 10 open source AI projects on GitHub right now and why they matter](https://github.blog/open-source/maintainers/from-mcp-to-multi-agents-the-top-10-open-source-ai-projects-on-git … ⌘ Read more
Mellum Goes Open Source: A Purpose-Built LLM for Developers, Now on Hugging Face
Comments ⌘ Read more
MCP 流式 HTTP 協議深入研究
MCP 引入了一個全新的流式 HTTP 傳輸層，相比原來的 HTTP+SSE 傳輸機制有了顯著改進。本文將詳細分析該協議的設計理念、技術細節及其實際應用場景。模型上下文協議（MCP） 是一種用於 AI 模型與工具之間通信的標準協議。隨着 AI 應用變得越來越複雜並廣泛部署，原有的通信機制面臨一系列挑戰。GitHub 上的 PR #206 引入了一個全新的流式HTTP傳輸層，相比原來的 HTTP+S ⌘ Read more
Docker Desktop 4.41: Docker Model Runner supports Windows, Compose, and Testcontainers integrations, Docker Desktop on the Microsoft Store
Docker Desktop 4.41 brings new tools for AI devs and teams managing environments at scale — build faster and collaborate smarter. ⌘ Read more
↳
In-reply-to
»
We havet an AI assistant at work, new version came out today "nearby restaurant recommendations" mentioned. Gotta try that!
⤋ Read More
@kat@yarn.girlonthemoon.xyz yes, both the newsletter and the podcast, from time to time.
@prologic@twtxt.net I was not expecting much, but since the list of restaurants near company buildings, was hard coded into it, I did expect it to at least copy the menu text, from the websites, in its database. Ironically, the only restaurant where it got something right, is the only one, where the websites has the text as a transparent PNG, the AI has to convert to text.
↳
In-reply-to
»
We havet an AI assistant at work, new version came out today "nearby restaurant recommendations" mentioned. Gotta try that!
⤋ Read More
@thecanine@twtxt.net do you read ed zitron’s newsletter? he writes in depth about how AI is a crock of shit it makes me feel normal for once
We havet an AI assistant at work, new version came out today “nearby restaurant recommendations” mentioned. Gotta try that!
Ask it where I can get a burger, knowing there’s 3 spots that had it on the menu, AI says there’s none. Ask it to list all the restaurants nearby it can check… it knows 3, of the 10 or so around, but 1/3, even has a burger, on the menu.
Ask it to list the whole menu at restaurant 1: it hallucinates random meals, none of which they had (I ate there).
Restaurant 2 (the one most people go to, so they must have at least tested it with this one): it lists the soup of the day and ¾ meals available. Incomplete, but better than false.
Restaurant 3: it says “food” and gives a general description of food. You have to be fucking kidding me!
“BuT cAnInE, tHe A(G)i ReVoLuTiOn Is NoW”
Is this AI’s Version of Moore’s Law? - Computerphile ⌘ Read more
How businesses are using agentic automation to thrive
The next generation of AI technology, agentic automation, is enabling organisations to deliver enterprise efficiencies that improve customer care, provide faster service and significantly cut costs. ⌘ Read more
MINIX Elite EU715-AI Mini PC Combines Meteor Lake Performance and dual 2.5GbE Ports
The MINIX Elite EU715-AI is a compact mini PC based on Intel’s Meteor Lake-H processor architecture. It features integrated Intel Arc Graphics, Wi-Fi 6E, dual 2.5G Ethernet ports, and quad-screen display support. The system runs Windows 11 Pro and comes equipped with 32 GB of DDR5 SO-DIMM memory, configured as two 16 GB modules. For […] ⌘ Read more
↳
In-reply-to
»
Someone has started to run
⤋ Read More
git pull on one of my repos – once every two minutes. This is a very pointless endeavour. I push new code a couple of times per month.
@movq@www.uninformativ.de oi, that has to be a bot. AI bot? Maybe not, but still a bot. I see this becoming more and more of an issue, sorry to say…
Someone has started to run git pull on one of my repos – once every two minutes. This is a very pointless endeavour. I push new code a couple of times per month.
So far, this isn’t causing any issues. I think this is just a regular human being who misconfigured some automation. And I hope this doesn’t mean that the “AI” bots have finally discovered my page …
GitHub for Beginners: Building a REST API with Copilot
See how you can use GitHub Copilot to build an API.
The post GitHub for Beginners: Building a REST API with Copilot appeared first on The GitHub Blog. ⌘ Read more
簡潔架構設計：如何設計一個合理的軟件架構？
提示：本文摘自: 「雲原生 AI 實戰營」 知識星球「Go 項目開發中級實戰課」的第 04 | 簡潔架構設計：如何設計一個合理的軟件架構？[1] 節課。 本文介紹的實戰項目 GitHub 地址爲：https://github.com/onexstack/miniblog 在開發項目之前，需要先設計一個合理的軟件架構。一個好的軟件架構不僅可以大大提高項目的迭代速度，還可以降低項目的閱讀和 ⌘ Read more
4 大類 AI Agent 協議框架全面綜述
對現有的 LLM AI Agent 通信協議進行了系統性的概述，並將其分爲四大類，以幫助用戶和開發者爲特定應用場景選擇最適合的協議。一、AI Agent 協議的發展AI Agent 協議的定義：代理協議是標準化框架，定義了代理之間以及代理與外部系統之間結構化通信的規則、格式和程序。與傳統交互機制（如 API、GUI 或 XML）相比，協議在效率、操作範圍、標準化和 AI 原生性方面具有顯著優勢。代 ⌘ Read more
OpenBSD 7.7 released
Another six months have passed, so it’s time for a new OpenBSD release: OpenBSD 7.7 to be exact. Browsing through the long, detailed list of changes, a few important bits jump out. First, OpenBSD 7.7 adds support for Ryzen AI 300 (Strix Point, Strix Halo, Krackan Point), Radeon RX 9070 (Navi 48), and Intel’s Arrow Lake, adding support for the latest x86 processors to OpenBSD. There seems to be quite a few entries in the list related to power management, from work on hibernation and suspend … ⌘ Read more