What I learned building a Claude Code plugin for MV3 Chrome extensions
Claude Code writes extension code fine. That was never the problem. Ask it for a content script that highlights matched text, or a background service …
Latest Web news from Tech News
All topics
AI
Tech
agents
ai
api
architecture
automation
aws
beginners
career
claude
database
devchallenge
devops
javascript
linux
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
react
security
showdev
tutorial
typescript
webdev
I stopped trusting Claude's code reviews, so I built a skill that puts my code on trial
Every time I asked Claude to review my branch, I got one of two answers: a cheerful "Looks good! 👍" or a vague list where I couldn't tell a real bug f…
Not Your Weights, Not Your Workflow
I left a multi-agent refactor running overnight. By morning the model was gone, pulled out from under me by a government I don't even vote for, on the…
Fable 5 dropped and I'm suddenly a lot more paranoid about my VS Code extensions
Three days ago, Anthropic released Claude Fable 5 — their first publicly available Mythos-class model, sitting above the entire Opus tier. It benchmar…
The claude -p playbook for June 15 — rebuilding your AI workflows inside interactive sessions
On June 15, Claude's claude -p (headless mode) and the Agent SDK stop drawing from your subscription and move to a separate metered credit. If you've …
His Today Was Yesterday: a timezone bug, a blast radius, and what AI missed
I lead a multi-tenant booking platform where venues sell activities. There's a customer-facing website where users book them. On the main page we show…
Loopers, Robovacs and the Death of the /Prompt
A Weekend Gonzo Field Guide to /loop Engineering Another weekend piece of satire, devoid of real-life advice but stacked with enough cyberpop residue …
Linkloom - AIWebReader
LinkLoom A web scraping and content extraction toolkit for TypeScript/Bun. Pass a URL, get clean markdown. That's the core. But LinkLoom also handles …
Two unrelated Claude Code Opus 4.8 failures hit the same week: token burn and fabricated tool results
In late May 2026, operators running Claude Code on Opus 4.8 ( claude-opus-4-8 ) filed two structurally different failures within the same few days. On…
Anthropic’s Claude in 2026: When Frontier AI Stopped Being Just Software
In 2026, Claude stopped looking like a normal AI product and started looking like infrastructure. Anthropic’s latest models are no longer interesting …
The Claude Code hook that ended --no-verify commits forever
Here's a small thing that drove me up the wall using Claude Code on a real codebase. I have a pre-commit hook. It runs the linter and the type-checker…
Claude Fable 5 Scores 95% on SWE-bench, Then Hands Off to Opus 4.8
The headline number is 95% on SWE-bench Verified. That's the score attached to Claude Fable 5, Anthropic's new general-access model in the Mythos clas…
Where Claude Code Tokens Actually Go (and How to Cut the Waste)
If your Claude Code API bill feels high, the cause is rarely too many turns. It is a handful of measurable patterns: re-reading the same files, oversi…
HTML/CSS Animation to Video (MP4): the Headless, Deterministic Way (incl. Claude)
So you asked Claude to animate something. Maybe a logo, a loading screen, a data viz. It spat out a neat HTML file with CSS keyframes, everything look…
Stop explaining yourself to Claude
You're wasting tokens. Not a little -a lot. Here's a prompt I see constantly: "I have a React app and I'm using the useState hook. My component re-ren…
AgentForge – 28 production grade skills that make AI agents ship reliable code
AgentForge is a control system for AI coding agents. Instead of hoping your agent "writes good code," you give it structured engineering workflows — t…
MCP Apps vs OpenAI Apps SDK: are they competing standards?
If you have started building tools for AI chat hosts, you have probably hit the same fork in the road. There are two ways to add a user interface to a…
I watched an AI agent refactor 14 files, fix failing tests, and open a PR, while I was in a meeting. Here's what that actually means for us.
It was a Tuesday afternoon in March 2026. A senior engineer, let's call her Priya, was three slides into a quarterly planning meeting when her phone b…
ChatGPT vs Claude for Infrastructure Engineers
Both ChatGPT and Claude are excellent. But they have different strengths, and infrastructure engineers feel those differences more than most users — b…
Claude Can Do All of This. Most People Have No Idea.
Claude can do a lot more than most people think. This guide covers all of it—where to find each feature, how to turn it on, and a prompt you can use i…
How I Ship 10x Faster with Claude Code: The 5-Layer Workflow System
After 8 months of daily Claude Code use, I've distilled my workflow into a 5-layer system. Each layer builds on the previous one. Skip one, and the wh…
Diagnose Node.js CommonJS vs ESM Errors with Claude: A Copy-Paste Prompt Kit (ERR_REQUIRE_ESM, ERR_MODULE_NOT_FOUND)
By the end of this article you'll have a small Node.js script that pipes a module-resolution error ( ERR_REQUIRE_ESM , ERR_MODULE_NOT_FOUND , Cannot u…
We scanned 17,000 Claude Code skills. 39% run shell commands - only 4% say so up front.
An AI skill is a Markdown file your coding agent reads and obeys. GitHub code search currently finds 74,192 SKILL.md files installed under .claude/ski…
Why everyone is talking about loop-engineering and how is it changing agentic ai workflows? Claude Code and Web Scraping examples
A couple of weeks ago I published a walkthrough of my agentic coding setup , the plan-first discipline, the four-agent team, the model routing, the CL…
PDLC 1.1: two things v1.0 got wrong about artifact shape
Three months after starting a project with PDLC, a team member asked a simple question: "What does the system look like right now?" There was no good …
Три мега-IPO за один месяц: поглотит ли рынок SpaceX, OpenAI и Anthropic?
В этом году фондовый рынок может столкнуться сразу с тремя крупнейшими первичными размещениями акций в истории. Как пишет The Economist, 11 июня Space…
ИИ бизнес-партнер в агентстве
Я руковожу небольшим диджитал-агентством. У меня есть команда — специалисты на аутсорсе, которые занимаются SEO, рекламой и соцсетями. Но вся стратеги…
Writing a CLAUDE.md that Claude actually follows
TL;DR — CLAUDE.md is powerful, but most people fill it with vague preferences that Claude acknowledges and then ignores. The instructions that stick a…
Stop sending every AI coding request to the expensive model
AI coding tools are powerful. But they’re also wasteful. A tiny helper-function question does not need Claude Sonnet. A huge architecture review proba…
Claude Fable 5 Is Here. Here's What Actually Matters for Developers 👨🏾💻
Anthropic dropped two models today. Most people are focused on the wrong one. What launched: Fable 5 — the public-facing Mythos-class model. Available…