Latest Tech News

Stay updated with the latest in technology, AI, cybersecurity, and more

Filtered by: cp Clear Filter

Building your own CLI coding agent with Pydantic-AI

Learning by doing Ben O’Mahony is Principal AI Engineer at Thoughtworks. He is a results-driven AI/Engineering leader with a track record of building high-performing teams and shipping business-critical AI, ML and data products and platforms at scale. He has deep expertise across the full Engineering and Data lifecycle from research to production deployment. Ben is adept at defining technical strategy, driving execution and partnering cross-functionally to deliver measurable impact. Recently Be

Topics: agent code mcp run tests

Launch HN: Dedalus Labs (YC S25) – Vercel for Agents

Hey HN! We are Windsor and Cathy of Dedalus Labs ( https://www.dedaluslabs.ai/ ), a cloud platform for developers to build agentic AI applications. Our SDK allows you to connect any LLM to any MCP tools – local or hosted by us. No Dockerfiles or YAML configs required. Here’s a demo: https://youtu.be/s2khf1Monho?si=yiWnZh5OP4HQcAwL&t=11 Last October, I (Windsor) was trying to build a stateful code execution sandbox in the cloud that LLMs could tool-call into. This was before MCP was released, a

Birth of 86-DOS – By Nemanja Trifunovic

Forty-five years ago, in April 1980, a young employee at Seattle Computer Products began developing a small disk operating system for the new Intel 8086-based board. Against all odds, this modest project evolved into software that would power the PC industry for over a decade: Microsoft’s MS-DOS. This is a story about development of 86-DOS, better known by its code name QDOS before it was sold to Microsoft. The two main sources I used are Tim Paterson's blogs from 2007 and Vintage Computer Fed

Honor launches the world’s thinnest foldable in Europe

is a news editor with over a decade’s experience in journalism. He previously worked at Android Police and Tech Advisor. Posts from this author will be added to your daily email digest and your homepage feed. Honor is bringing the Magic V5 — the world’s thinnest foldable phone, though only just — to Europe, where it’s available to order now following its Chinese launch last month. It’s joined by a new MagicPad 3 tablet and MagicBook Art 14 laptop. I’ve just reviewed the Magic V5, which is a w

Topics: 14 99 honor magicpad v5

Like Intel before it, AMD blames motherboard makers for burnt-out CPUs

AMD's X3D-series Ryzen chips have become popular with PC gamers because games in particular happen to benefit disproportionately from the chips' extra 64MB of L3 cache memory. But that extra memory occasionally comes with extra headaches. Not long after they were released earlier this year, some early adopters started having problems with their CPUs, ranging from failure to boot to actual physical scorching and burnout—the problems were particularly common for users of the 9800X3D processor in A

GMP damaging Zen 5 CPUs?

GMP damaging Zen 5 CPUs? Background We have fried two Ryzen 9950X CPUs in a few months by running GMP tests. This is not expected, of course. In this page, we provide as much information as possible to help analysing the problem. What causes these CPUs to die while running GMP is unknown to us. While similar, it is not the widely reported Asrock motherboard problem, as the motherboards we use are of a different make (see below). It might be that the Zen 5 CPUs pull more power than specified w

Topics: 2nd cpu cpus ddr5 mem

Over 28,000 Citrix devices vulnerable to new exploited RCE flaw

More than 28,200 Citrix instances are vulnerable to a critical remote code execution vulnerability tracked as CVE-2025-7775 that is already being exploited in the wild. The vulnerability affects NetScaler ADC and NetScaler Gateway and the vendor addressed it in updates released yesterday. According to the U.S. Cybersecurity and Infrastructure Security Agency (CISA) and Citrix, the security issue has been exploited as a zero-day vulnerability. The versions affected by CVE-2025-7775 are 14.1 be

Topics: 13 2025 citrix cve ndcpp

The McPhee method for writing deeply reported nonfiction

When I first started writing for a real publication, I taught myself “reporting” with a simple self-made curriculum unfolding over six or seven articles. The first two pieces I wrote from my head, with reference to things I already knew or to books I’d read. For the third, I actually got out of the house, but didn’t yet have to play the journalist; I just wrote about taking a flying lesson in a small airplane. The fourth article required more gumption: I decided to shadow a friend of mine for a

Like Intel before it, AMD blames motherboard makers for burnt-out CPUs

AMD's X3D-series Ryzen chips have become popular with PC gamers because games in particular happen to benefit disproportionately from the chips' extra 64MB of L3 cache memory. But that extra memory occasionally comes with extra headaches. Not long after they were released earlier this year, some early adopters started having problems with their CPUs, ranging from failure to boot to actual physical scorching and burnout—the problems were particularly common for users of the 9800X3D processor in A

MCP Gateway and Registry

MCP Gateway Model Context Protocol gateway & proxy - unify REST, MCP, and A2A with federation, virtual servers, retries, security, and an optional admin UI. ContextForge MCP Gateway is a feature-rich gateway, proxy and MCP Registry that federates MCP and REST services - unifying discovery, auth, rate-limiting, observability, virtual servers, multi-transport protocols, and an optional Admin UI into one clean endpoint for your AI clients. It runs as a fully compliant MCP server, deployable via P

Developers lose focus 1,200 times a day — how MCP could change that

Want smarter insights in your inbox? Sign up for our weekly newsletters to get only what matters to enterprise AI, data, and security leaders. Subscribe Now Software developers spend most of their time not writing code; recent industry research found that actual coding accounts for as little as 16% of developers’ working hours, with the rest consumed by operational and supportive tasks. As engineering teams are pressured to “do more with less” and CEOs are bragging about how much of their codeb

It is worth it to buy the fast CPU

In the past few years, CPUs have gotten really fast. Shockingly fast! Yet most people are stuck on previous generation mobile chips (whether by choice, or by their companies choice), at a huge detriment to their productivity. Meanwhile, AI coding subscriptions like Cursor are all the rage these days. I'll skip the debate on exactly how useful these tools are, and focus on the pricing. Cursor is $480/year for the team plan (the cheapest corporate plan), and other providers are around the same, s

Topics: 3x buy cpu cpus end

DeepCode: Open Agentic Coding

██████╗ ███████╗███████╗██████╗ ██████╗ ██████╗ ██████╗ ███████╗ ██╔══██╗██╔════╝██╔════╝██╔══██╗██╔════╝██╔═══██╗██╔══██╗██╔════╝ ██║ ██║█████╗ █████╗ ██████╔╝██║ ██║ ██║██║ ██║█████╗ ██║ ██║██╔══╝ ██╔══╝ ██╔═══╝ ██║ ██║ ██║██║ ██║██╔══╝ ██████╔╝███████╗███████╗██║ ╚██████╗╚██████╔╝██████╔╝███████╗ ╚═════╝ ╚══════╝╚══════╝╚═╝ ╚═════╝ ╚═════╝ ╚═════╝ ╚══════╝ DeepCode: Open Agentic Coding Advancing Code Generation with Multi-Agent Systems 🖥️ Interface Showcase 🖥️ CLI Interface Terminal-Based Dev

Acronis True Image costs performance when not used

Over two years ago I installed Acronis True Image for Crucial in order to migrate my data to a new SSD I had just purchased. It worked. I then left True Image installed “just in case”, and what harm could that possibly cause. Well, funny you should ask. I recently noticed that whenever I plugged or unplugged my external monitor Explorer.exe would consume a lot of CPU time – dozens of seconds of it. It was enough CPU time to make my computer noticeably sluggish until things calmed down which co

MCP-Universe benchmark shows GPT-5 fails more than half of real-world orchestration tasks

Want smarter insights in your inbox? Sign up for our weekly newsletters to get only what matters to enterprise AI, data, and security leaders. Subscribe Now The adoption of interoperability standards, such as the Model Context Protocol (MCP), can provide enterprises with insights into how agents and models function outside their walled confines. However, many benchmarks fail to capture real-life interactions with MCP. Salesforce AI Research developed a new open-source benchmark it calls MCP-Un

Does MHz Still Matter?

Does MHz still matter? Furkan Sahin Senior Software Engineer To provide VMs of any size, we slice bare metal into smaller VMs, sometimes even 1 vCPU. So, the performance of one fast core matters a lot. We evaluated new servers from Hetzner with AMD EPYC and Ryzen CPUs to add to our fleet. Ryzen is a CPU from AMD’s gaming line-up and it has better single core performance numbers compared to the EPYC which is a standard datacenter CPU. We weren’t sure if Ryzen’s single core edge would show up in

Universal Tool Calling Protocol (UTCP)

Universal Tool Calling Protocol (UTCP) 1.0.1 Introduction The Universal Tool Calling Protocol (UTCP) is a modern, flexible, and scalable standard for defining and interacting with tools across a wide variety of communication protocols. UTCP 1.0.0 introduces a modular core with a plugin-based architecture, making it more extensible, testable, and easier to package. In contrast to other protocols, UTCP places a strong emphasis on: Scalability : UTCP is designed to handle a large number of tool

Analysis of the GFW's Unconditional Port 443 Block on August 20, 2025

1. Introduction Between approximately 00:34 and 01:48 (Beijing Time, UTC+8) on August 20, 2025, the Great Firewall of China (GFW) exhibited anomalous behavior by unconditionally injecting forged TCP RST+ACK packets to disrupt all connections on TCP port 443. This incident caused massive disruption of the Internet connections between China and the rest of the world (source1 and source2). This report documents our measurements and analysis of this temporary, widespread blocking event. Our primar

Topics: ack flags ip length tcp

Docker container for running Claude Code in "dangerously skip permissions" mode

Claude Code Container A Docker container for running Claude Code in "dangerously skip permissions" mode. claude-container3.mp4 Build the docker container and execute run_claude.sh to run an isolated version of claude code with access to the current working dir ( readOnly:/workspace/input ). /workspace/ ├── input/ # Host input files (read-only mount of $PWD) ├── output/ # Analysis results (writable mount to host) ├── data/ # Reference data (optional read-only mount) ├── temp/ # Temporary file

MCP tools with dependent types

August 17, 2025 MCP tools with dependent types This summer, I’ve been playing a bit with writing an MCP server for Defold editor. The idea was to give Claude access to evaluating Lua code in the editor scripting context, so it can use the APIs available for querying and modifying game content. The best word to describe the experience is entertaining — it has a very vague idea of the available APIs, and prefers to experiment by evaluating code instead of browsing documentation, which results in

MCP doesn't need tools, it needs code

Your MCP Doesn’t Need 30 Tools: It Needs Code I wrote a while back about why code performs better than MCP (Model Context Protocol) for some tasks. In particular, I pointed out that if you have command line tools available, agentic coding tools seem very happy to use those. In the meantime, I learned a few more things that put some nuance to this. There are a handful of challenges with CLI-based tools that are rather hard to resolve and require further examination. In this blog post, I want to

MCP Tools and Dependent Types

August 17, 2025 MCP tools with dependent types This summer, I’ve been playing a bit with writing an MCP server for Defold editor. The idea was to give Claude access to evaluating Lua code in the editor scripting context, so it can use the APIs available for querying and modifying game content. The best word to describe the experience is entertaining — it has a very vague idea of the available APIs, and prefers to experiment by evaluating code instead of browsing documentation, which results in

MCP Doesn't Need 30 Tools: It Needs Code

Your MCP Doesn’t Need 30 Tools: It Needs Code I wrote a while back about why code performs better than MCP (Model Context Protocol) for some tasks. In particular, I pointed out that if you have command line tools available, agentic coding tools seem very happy to use those. In the meantime, I learned a few more things that put some nuance to this. There are a handful of challenges with CLI-based tools that are rather hard to resolve and require further examination. In this blog post, I want to

An Argument for Increasing TCP's Initial Congestion Window Again

An Argument for Increasing TCP's Initial Congestion Window ... Again Published September 2, 2024 Introduction Google has a long history of performing networking research, making changes, and pushing those changes to the entire internet. In 2011, they published one of my favorite papers, which described their decision to increase the TCP initial congestion window from 1 to 10 on their entire infrastructure. This was soon followed by an RFC filed with the IETF, and eventually became an internet

Lessons learned from buying an open source repo

Our tiny startup recently acquired the most popular open-source Unity MCP repo on GitHub, and things didn’t quite go as planned. Here are the lessons we learned for anyone considering buying an open source repo. Why we bought the repo First, we like open source and want Unity MCP to stay relevant and open source indefinitely. Second, there’s distribution: being the name behind the project. If you don’t want to set up MCP yourself, you can one-click install Coplay for a premium experience. Wh

Show HN: MCP Security Suite

MCP Security Suite 🛡️ Unified security framework for Model Context Protocol (MCP) servers 📖 Quick Start Guide - Get up and running in 3 minutes! ⚠️ Important Note for Scanning This Project: This repository contains intentionally malicious test files in mcp_test_cases/ and tests/ directories to validate our detection capabilities. When scanning this project: To exclude test files : python3 mighty_mcp.py check . --profile production : To force fresh scan (bypass cache) : python3 mighty_mcp.py

Linux Address Space Isolation Revived After Lowering 70% Performance Hit to 13%

Several years ago Google engineers began exploring address space isolation for the Linux kernel and ultimately proposing Linux ASI for better dealing with CPU speculative execution attacks . While the hope was it would better cope with the ever growing list of CPU speculative execution vulnerabilities, the effort was thwarted initially by I/O throughput seeing a 70% performance hit . That level of performance cost was unsustainable. But now that I/O overhead has been reduced to just 13%.Google e

NeoLogic wants to build more energy-efficient CPUs for AI data centers

When NeoLogic started building its more energy-efficient CPUs for AI servers, folks in the industry told its founders Avi Messica and Ziv Leshem that their idea wasn’t viable. “Most of the people that we have met say it’s impossible,” Messica told TechCrunch. “Some of them told us, at the time, that the innovation is impossible because you cannot innovate in logic synthesis. You can’t innovate in circuit design. It’s too mature.” Israel-based NeoLogic nevertheless set out to prove them wrong,

Nexus: An Open-Source AI Router for Governance, Control and Observability

Today, we're excited to introduce Nexus - a powerful AI router designed to optimize how AI agents interact with multiple MCP tools and Large Language Models. Nexus serves as a central hub that aggregates Model Context Protocol (MCP) servers while providing intelligent LLM routing, security and governance capabilities. Nexus is an AI router that solves two critical challenges in the AI ecosystem: MCP Server Aggregation: Instead of managing connections to multiple MCP servers individually, Nexus

Operation Costs in CPU Clock Cycles (2016)

Author: “No Bugs” Hare Follow: Job Title: Sarcastic Architect Hobbies: Thinking Aloud, Arguing with Managers, Annoying HRs, Calling a Spade a Spade, Keeping Tongue in Cheek UPDATED: TLB and CAS/atomics (including different NUMA node) added Click to enlarge NB: scale is logarithmic! Premature Pessimization Easy on yourself, easy on the code: All other things being equal, notably code complexity and readability, certain efficient design patterns and coding idioms should just flow naturally