Chrome DevTools (MCP) for your AI agent | Blog | Chrome for Developers
Published: September 23, 2025 We're launching today a public preview for the new Chrome DevTools Model Context Protocol (MCP) server, bringing the power of Chrome DevTools to AI coding assistants. Coding agents face a fundamental problem: they are not able to see what the code they generate actually does when it runs in the browser. They're effectively programming with a blindfold on. The Chrome D
It turns out we've all been using MCP wrong. Most agents today use MCP by directly exposing the "tools" to the LLM. We tried something different: Convert the MCP tools into a TypeScript API, and then ask an LLM to write code that calls that API. The results are striking: We found agents are able to handle many more tools, and more complex tools, when those tools are presented as a TypeScript API r
Today, we’re announcing Claude 3.7 Sonnet1, our most intelligent model to date and the first hybrid reasoning model on the market. Claude 3.7 Sonnet can produce near-instant responses or extended, step-by-step thinking that is made visible to the user. API users also have fine-grained control over how long the model can think for. Claude 3.7 Sonnet shows particularly strong improvements in coding
Last updated: Apr 2, 2026 (added Gemma 4 in section 23) It has been seven years since the original GPT architecture was developed. At first glance, looking back at GPT-2 (2019) and forward to DeepSeek V3 and Llama 4 (2024-2025), one might be surprised at how structurally similar these models still are. Sure, positional embeddings have evolved from absolute to rotational (RoPE), Multi-Head Attentio
Announcing New Tools for Building with Generative AI on AWS | Amazon Web Services
Artificial Intelligence Announcing New Tools for Building with Generative AI on AWS The seeds of a machine learning (ML) paradigm shift have existed for decades, but with the ready availability of scalable compute capacity, a massive proliferation of data, and the rapid advancement of ML technologies, customers across industries are transforming their businesses. Just recently, generative AI appli
written on June 12, 2025 There is currently an explosion of people sharing their experiences with agentic coding. After my last two posts on the topic, I received quite a few questions about my own practices. So, here goes nothing. Preface For all intents and purposes, here’s what I do: I predominently use Claude Code with the cheaper Max subscription for $100 a month 1. That works well for severa
Another year passes. I was hoping to write more articles instead of just these end-of-the-year screeds, but I almost died in the spring semester, and it sucked up my time. Nevertheless, I will go through what I think are the major trends and happenings in databases over the last year. There were many exciting and unprecedented developments in the world of databases. Vibe coding entered the vernacu
GitHub - modelcontextprotocol/servers: Model Context Protocol Servers
Official integrations are maintained by companies building production ready MCP servers for their platforms. 21st.dev Magic - Create crafted UI components inspired by the best 21st.dev design engineers. 2slides - An MCP server that provides tools to convert content into slides/PPT/presentation or generate slides/PPT/presentation with user intention. ActionKit by Paragon - Connect to 130+ SaaS inte
Published Jun 13, 2025 Our Research feature uses multiple Claude agents to explore complex topics more effectively. We share the engineering challenges and the lessons we learned from building this system. Claude now has Research capabilities that allow it to search across the web, Google Workspace, and any integrations to accomplish complex tasks. The journey of this multi-agent system from proto
Get started with AWS MCP Servers and learn core features. The AWS MCP Servers are a suite of specialized MCP servers that help you get the most out of AWS, wherever you use MCP. What is the Model Context Protocol (MCP) and how does it work with AWS MCP Servers? The Model Context Protocol (MCP) is an open protocol that enables seamless integration between LLM applications and external data sources
The Astro Technology Company, creators of the Astro web framework, is joining Cloudflare. Astro is the web framework for building fast, content-driven websites. Over the past few years, we’ve seen an incredibly diverse range of developers and companies use Astro to build for the web. This ranges from established brands like Porsche and IKEA, to fast-growing AI companies like Opencode and OpenAI. P
TLDR; Software development, as it has been done for decades, is over. LLM coding tools have changed it fundamentally for the better or worse. “Talk is cheap. Show me the code.” — Linus Torvalds, August 2000 When Linus Torvalds, the creator of Linux, made this quip in response to a claim about a complex piece of programming in the Linux kernel, [1] I was an oblivious, gangly, fledgling teenage n00b
はじめに 本記事では、LLM研究で注目を集めるエージェント型強化学習（Agentic Reinforcement Learning、Agentic RL）のサーベイ論文 「The Landscape of Agentic Reinforcement Learning for LLMs: A Survey」[1]を読み、私なりの理解と要点を整理して紹介します。500件以上の文献を引用するボリュームのある論文ですが、ここでは重要だと感じたトピックに絞って取り上げます。Agentic RLに興味がある方や、LLMに対する強化学習の最新動向を知りたい方の参考になれば幸いです。 本記事の前提 PPOやGRPOといったRLアルゴリズムの解説は他の多くの記事で既に説明されているため、本記事では割愛します。 DeepSeek-R1[2]の研究を前提とする箇所がいくつかあります。未読の方は原著論文や解説記事
Cerebras-GPT: A Family of Open, Compute-efficient, Large Language Models - Cerebras
GLM-4.7 from Z.ai is live on Cerebras at 1,000 TPS! Frontier intelligence for coding, tool-driven agents, and multi-turn reasoning. >> Mar 28 2023 Cerebras-GPT: A Family of Open, Compute-efficient, Large Language Models - Cerebras @ � ��AbstractState-of-the-art language models are extremely challenging to train; they require huge compute budgets, complex distributed compute techniques and deep ML
Learn how Replit trains Large Language Models (LLMs) using Databricks, Hugging Face, and MosaicML IntroductionLarge Language Models, like OpenAI's GPT-4 or Google's PaLM, have taken the world of artificial intelligence by storm. Yet most companies don't currently have the ability to train these models, and are completely reliant on only a handful of large tech firms as providers of the technology.
Beyond agentic coding
I'm generally pretty pro-AI with one major exception: agentic coding. My consistent impression is that agentic coding does not actually improve productivity and deteriorates the user's comfort and familiarity with the codebase. I formed that impression from: my own personal experiences Every time I use agentic coding tools I'm consistently unimpressed with the quality of the results. my experience
A Guide to Claude Code 2.0 and getting better at using coding agents
Table of Contents Intro Why I wrote this post The Map is not the territory This post will help you keep up in general Lore time - My Love and Hate relationship with Anthropic Timeline My Codex era Anthropic Redemption Arc + Regaining mandate of heaven Why Opus 4.5 feels goooood This post is not sponsored Pointers for the technically-lite The Evolution of Claude Code Quality of life improvements in
2025: The year in LLMs
31st December 2025 This is the third in my annual series reviewing everything that happened in the LLM space over the past 12 months. For previous years see Stuff we figured out about AI in 2023 and Things we learned about LLMs in 2024. It’s been a year filled with a lot of different trends. The year of “reasoning” The year of agents The year of coding agents and Claude Code The year of LLMs on th
Understanding Spec-Driven-Development: Kiro, spec-kit, and Tessl
Understanding Spec-Driven-Development: Kiro, spec-kit, and Tessl Birgitta is a Distinguished Engineer and AI-assisted delivery expert at Thoughtworks. She has over 20 years of experience as a software developer, architect and technical leader. This article is part of “Exploring Gen AI”. A series capturing Thoughtworks technologists' explorations of using gen ai technology for software development.
※2024/5/11 13:29追記DifyのLuyu Zhang CEOから直接コメントをいただきましたので、この記事の最後に追記いたしました。 Difyはテンセント系企業？使用して大丈夫？最近注目を集めているLLMOpsプラットフォームのDify.aiですが、中国のテンセントがバックにいるのではないかとの憶測がネット上で広がっていました。以下はXで話題の投稿です。 Difyは中国のテンセントがバックです。 DifyのWEB版（サブスク版）は使うべきではありません。裏側からあなたの作ったシステムも、プロンプトも、APIキーも丸見えですから。Gitからシステムをおろし、ローカルで開発し、GCPなどのクラウドで運用するなら、ありと思います。 — 平岡 憲人(HIRAOKA, Norito) Stand with Ukraine (@onokoro48) May 9, 2024 この記事では、
31st December 2024 A lot has happened in the world of Large Language Models over the course of 2024. Here’s a review of things we figured out about the field in the past twelve months, plus my attempt at identifying key themes and pivotal moments. This is a sequel to my review of 2023. In this article: The GPT-4 barrier was comprehensively broken Some of those GPT-4 models run on my laptop LLM pri
GitHub - punkpeye/awesome-mcp-servers: A collection of MCP servers.
Servers for accessing many apps and tools through a single MCP server. 1mcp/agent 📇 ☁️ 🏠 🍎 🪟 🐧 - A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one. tadas-github/a2asearch-mcp 📇 ☁️ - MCP server to search 4,800+ MCP servers, AI agents, CLI tools and agent skills. Install: npx -y a2asearch-mcp. Ask Claude: "Find MCP servers for database access"
A Language For Agents
Last year I first started thinking about what the future of programming languages might look like now that agentic engineering is a growing thing. Initially I felt that the enormous corpus of pre-existing code would cement existing languages in place but now I’m starting to think the opposite is true. Here I want to outline my thinking on why we are going to see more new programming languages and
The Go Blog Using go fix to modernize Go code Alan Donovan 17 February 2026 The 1.26 release of Go this month includes a completely rewritten go fix subcommand. Go fix uses a suite of algorithms to identify opportunities to improve your code, often by taking advantage of more modern features of the language and library. In this post, we’ll first show you how to use go fix to modernize your Go code
6 Weeks of Claude Code
It is wild to think that it has been only a handful of weeks. Claude Code has considerably changed my relationship to writing and maintaining code at scale. I still write code at the same level of quality, but I feel like I have a new freedom of expression which is hard to fully articulate. Claude Code has decoupled myself from writing every line of code, I still consider myself fully responsible
Prompt Engineering
Date: March 15, 2023 | Estimated Reading Time: 21 min | Author: Lilian Weng Prompt Engineering, also known as In-Context Prompting, refers to methods for how to communicate with LLM to steer its behavior for desired outcomes without updating the model weights. It is an empirical science and the effect of prompt engineering methods can vary a lot among models, thus requiring heavy experimentation a
Can AI do theoretical physics? In this guest post, professor of physics Matthew Schwartz decided to find out by supervising Claude through a real research calculation, start to finish, without ever touching a file himself. His account of what happened is below. SummaryI guided Claude Opus 4.5 through a real theoretical physics calculation, encapsulating the complexity of code and computations behi
The Llama 4 herd: The beginning of a new era of natively multimodal AI innovation
The Llama 4 herd: The beginning of a new era of natively multimodal AI innovation We’re sharing the first models in the Llama 4 herd, which will enable people to build more personalized multimodal experiences.Llama 4 Scout, a 17 billion active parameter model with 16 experts, is the best multimodal model in the world in its class and is more powerful than all previous generation Llama models, whil
antirez 6 days ago. 335349 views. I love writing software, line by line. It could be said that my career was a continuous effort to create software well written, minimal, where the human touch was the fundamental feature. I also hope for a society where the last are not forgotten. Moreover, I don't want AI to economically succeed, I don't care if the current economic system is subverted (I could b
I've used many content formats over the years, and while I love Markdown, I run into its limitations daily when I work on larger documentation projects. In this issue, you'll look at Markdown and explore why it might not be the best fit for technical content, and what else might work instead. Markdown Lacks the Structure You Need Markdown is everywhere. It's human-readable, approachable, and has j
Masato Hagiwara Open in Recto Pad Google Colab Github Recto Pad TL;DR Recto is a 2D programming language that uses nested rectangles as its core syntax, encoding structure and recursion directly in space instead of a linear stream of text. Recto explores new ways to write, parse, and reason about code—and even natural language—spatially. Introduction Open in Recto Pad Virtually all the languages w
Edit: A lot of folks have been asking what worfklows I used to write these apps. I used GitHub Copilot in VS Code with a custom agent prompt that you’ll find toward the end of this post. Context7 was the only MCP I used. I mostly just used the built-in voice dictation feature and talked to Claude. No fancy workflows, planning, etc required. The agent harness in VS Code for Opus 4.5 is so good - yo
State of AIAn Empirical 100 Trillion Token Study with OpenRouter Malika Aubakirova*Alex Atallah†Chris Clark†Justin Summerville†Anjney Midha* AbstractThe past year has marked a turning point in the evolution and real-world use of large language models (LLMs). With the release of the first widely adopted reasoning model, o1, on December 5th, 2024, the field shifted from single-pass pattern generatio
Generate an entire app from a prompt using Together AI’s LlamaCoder
Generate an entire app from a prompt using Together AI’s LlamaCoder Together AI, the leading AI acceleration cloud, empowers developers and businesses to seamlessly design, develop, and manage their entire generative AI lifecycle on open source models like Llama. To inspire developers who build on Llama, Together AI built the LlamaCoder app—an open source web app that allows people to generate an
18th December 2025 In all of the debates about the value of AI-assistance in software development there’s one depressing anecdote that I keep on seeing: the junior engineer, empowered by some class of LLM tool, who deposits giant, untested PRs on their coworkers—or open source maintainers—and expects the “code review” process to handle the rest. This is rude, a waste of other people’s time, and is
Patterns for Building LLM-based Systems & Products [ llm engineering production 🔥 ] · 66 min read Discussions on HackerNews, Twitter, and LinkedIn “There is a large class of problems that are easy to imagine and build demos for, but extremely hard to make products out of. For example, self-driving: It’s easy to demo a car self-driving around a block, but making it into a product takes a decade.”
A few months ago I went through a bit of a mental slump. I've always been confident of my abilities as an engineer, but I couldn't help but feel like my skills were falling hopelessly behind as I scrolled places like LinkedIn and Twitter. If these sources were to be believed, engineering had moved on from the medieval practice of typing code into an editor. Real engineers were now 10-100x more pro
An Economy of AI Agents Gillian K. Hadfield* Johns Hopkins Andrew Koh† MIT This version: September 3, 2025 Prepared for the NBER Handbook on the Economics of Transformative AI Abstract In the coming decade, artificially intelligent agents with the ability to plan and ex- ecute complex tasks over long time horizons with little direct oversight from humans may be deployed across the economy. This ch
When my son was born last April, I had ambitious learning plans for the upcoming 5w paternity leave. As you can imagine, with two kids, life quickly verified this plan 🙃. I did eventually start some projects. One of the goals (sounding rebellious in the current AI hype cycle) was to learn and use neovim for coding. As a Goland aficionado, I (and my wrist) have always been tempted by no-mouse, OSS
Magistral | Mistral AI
Announcing Magistral — the first reasoning model by Mistral AI — excelling in domain-specific, transparent, and multilingual reasoning. The best human thinking isn’t linear — it weaves through logic, insight, uncertainty, and discovery. Reasoning language models have enabled us to augment and delegate complex thinking and deep understanding to AI, improving our ability to work through problems req
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
Code Mode: the better way to use MCP
Claude 3.7 Sonnet and Claude Code
The Big LLM Architecture Comparison
Agentic Coding Recommendations
Databases in 2025: A Year in Review
How we built our multi-agent research system
Welcome to AWS MCP Servers | AWS MCP Servers
Astro is joining Cloudflare
Code is cheap. Show me the talk.
LLM×強化学習の新しいパラダイム: Agentic RLの研究紹介
Replit — How to train your own Large Language Models
Difyは使用して大丈夫？テンセント系企業？安全なの？｜Kyutaro
Things we learned about LLMs in 2024
Using go fix to modernize Go code - The Go Programming Language
Vibe physics: The AI grad student
Don't fall into the anti-AI hype - <antirez>
Issue 45 - Markdown is Holding You Back
Recto — a truly 2D language
Opus 4.5 is going to change everything
State of AI 2025: 100T Token LLM Usage Study | OpenRouter
Your job is to deliver code you have proven to work
Patterns for Building LLM-based Systems & Products
No, AI is not Making Engineers 10x as Productive
An Economy of AI Agents
The (lazy) Git UI You Didn't Know You Need