[Перевод] Руководство, считающее, что ИИ заменит персонал — это фиговое руководство
За последние три месяца я сталкивался с четырьмя случаями сумасшествия CEO из-за искусственного интеллекта. Поразительным для меня было сходство всех …
AI & ML
⚑ Report a ProblemLatest AI & ML news from Tech News
All topics
AI
News
Tech
agents
ai
api
architecture
automation
beginners
career
claude
database
devchallenge
devops
javascript
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
react
security
showdev
testing
tutorial
typescript
webdev
Anthropic уничтожает бумажные книги ради Claude?
Тут в твитторе разгорелся очередной скандал вокруг Anthropic. Под катом я постарался разобраться в сути и пересказал вам. В 2024 году Anthropic з…
Внедряем Claude Code нативно в Cursor IDE. Или как 9Router позволяет платить меньше
Думаю все, кто начинал использовать claude code, рано или поздно ощущали на себе его недостатки. Не удобно навигироваться по чекпоинтам, не удобно смо…
8 способов сделать AI-агента дешевле: опыт реального продукта и готовые промпты для вайбкодеров
Всем привет! Я Юля Гончарова — продакт, дизайнер и... «вайбкодер». Последний год я строю продукты в одиночку с помощью Claude Code — от идеи и UX до к…
I was maxing my Claude 5-hour limit daily and still wasting weekly quota every night, so I built a tool that spends it while I sleep
Like a lot of you I hit the 5-hour cap most days. What actually annoyed me was realizing the weekly limit doesn't line up with that. Even capping out …
Как устроена Kimi K3: 2,8 трлн параметров, линейное внимание и агенты на миллион токенов
Moonshot AI выпустила веса Kimi K3 — мультимодальной MoE‑модели с 2,8 трлн параметров, из которых на каждом токене активируются 1…
Sir Shortoken: Bullet Mode, Local Expansion, and What Actually Held Up
TL;DR: Tested whether representing Claude's responses as bullets instead of prose loses any information. Ran it across 14 technical topics — 24-78% to…
[Перевод] Занимаются ли разработчики ИИ‑моделей пеликанмаксингом?
Последние несколько лет Саймон Уиллисон тестировал каждый крупный релиз LLM одним и тем же промптом: «Сгенерируй SVG с пеликаном, сидящим на велосипед…
freee + MCP: I Automated My Japanese Tax Return With Claude Code — 3 Things That Broke in Production
Context for readers outside Japan Japan's kakutei shinkoku is the annual self-employed tax return — the local equivalent of the US Schedule C or the U…
The Best Prompt Engineering Lesson I Did Not Expect to Learn
A few weeks ago, I completed Anthropic Education's AI Frameworks and Fluency course. I joined out of curiosity. One part of the course stayed with me …
Building a Financial Document OCR with Claude Vision API: Lessons from Production
After processing thousands of bank statements, invoices, and receipts through Claude Vision API, I've learned that financial document OCR is harder th…
Лучшие модели для разработки с ИИ на 1С (бенчмарк v2)
Claude Opus 5, Claude Fable 5, GPT 5.6 Sol, Kimi K3, Claude Opus 4.8, Grok 4.5, Composer 2.5, GPT 5.5, DeepSeek v4, GLM 5.2, Qwen 3.8 Max, Claude Sonn…
Conducting agents like an orchestra: how agents-concerto works
For months I had the same problem with coding agents: the session drops a pile of changes, and by review time I no longer know what it touched or why.…
How to Connect Claude to the dev.to API and Build a Reusable Skill
MCP (Model Context Protocol) connectors extend Claude's reach into external services, but connector coverage is uneven across platforms. dev.to is one…
I couldn't find a simple agent framework, so I wrote one
I keep finding a new agent skill I want to add to my library. Each one is a good addition on its own, and that is exactly the trap. Skills are not fre…
I vibe coded an LM Arena for AI companion apps with Claude Code.
I can't write code. I've never written a line of it by hand. I still wanted something that didn't exist: a leaderboard for AI companion sites that sho…
From Bug Found to Bug Filed: A Bug-Reporter Skill for Claude Code
Part 8 of the "Automating Playwright with Claude Code" series. Our pack from Part 6 catches problems (flaky tests, locator issues); this post adds a S…
AI Slop🤮
There's a term developers have started using for what's piling up in their pull requests: AI slop. Not an insult to the tools. A name for the specific…
CMS Битрикс и сайты на российских серверах через Claude Code. Мой опыт, лайфхаки и подводные камни
Пробовали работать с Битриксом через AI-агента? Если ещё нет, то вам будет интересно узнать, как это :-) Читать далее
How to structure CLAUDE.md, Skills and Agents
Hi friends Here's a tip for when you're setting up Claude Code (or any coding agent) in a real codebase, this came in clutch for me when I discovered …
Opus 5 вышел: стал ли Fable 5 лишним? Сравниваем цену задачи, агентные сценарии и ограничения
Opus 5 не делает Fable 5 ненужным: благодаря вдвое более низкой официальной цене за токен, управляемому effort и близкому уровню возможностей Opus под…
Claude Opus 5: beats Fable 5 at half the price — and 'awakens' in its own system card
Claude Opus 5 is here. At half the price, it beats Fable 5 on most benchmarks; it scored a perfect 42/42 at IMO 2026 with no external tools; and it's …
460 ГБ, свободно 14: археология диска разработчика
TL;DR : после каждого проекта на диске остаётся 2–40 ГБ мусора, который никто никогда не убирает. Я раскопал свой Mac (460 ГБ, из них свободно было 14…
How to host an app your AI built: its own URL and saved data
Claude can write a working app right inside a chat. Close the chat and it's gone: no URL, no saved data, nothing to open tomorrow. This is how you tur…
Making a launch video for Claude Opus 5
Anthropic shipped Claude Opus 5 today. Nobody asked us for a video, so we made one anyway — fifty-five seconds, twelve beats, every claim on screen li…
Your agent knows your preferences. It just never uses them
There is a way for agent memory to fail that is worse than forgetting, and it took me a while to even recognize it as a failure. The preference is sit…
Claude Lawfare
CN: Death I. The letter My father died in November. Sometime between the 16th and the 19th — the death certificate gives a range, not a date, which is…
Claude Code hooks explained: config structure, matchers, and a copy-paste PreToolUse guard
If you have only ever used Claude Code's permission prompts, hooks are the next layer down: deterministic shell commands (or HTTP endpoints, MCP tools…
I benchmarked Claude Code skills against a placebo — and half of mine failed
There's a whole ecosystem of "agent skills" now — reusable instruction files you drop into Claude Code (or Cursor, or Copilot) to make the model write…
Connect Google Sheets to Claude Code in 5 minutes
I wanted Claude Code to read a Google Sheet while it worked. Some of my test fixtures and a small config table live in a spreadsheet a teammate mainta…