LLM уверенно врёт про ваш микроконтроллер
Попросил ИИ написать прошивку для платы с экранчиком. Код идеальный: скомпилировался с первого раза, залился без ошибок. А на экране - цветной шум.…
Последние новости
⚑ Сообщить о проблемеTech news from the best sources
Все темы
- игры
AI
Gear
News
Tech
agents
ai
api
architecture
automation
beginners
career
database
devops
javascript
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
react
security
showdev
testing
tutorial
typescript
webdev
'Enshittified at a Surprising Clip': A Week of Hacker News on AI Coding Tools
Some fortnights the complaints about AI come from people who barely use it. This one they came from the people who use it most. Scroll Hacker News o…
How I Architected 84 Custom Skills for Claude Code to Automate My Daily Engineering
I've been using Anthropic's Claude Code and autonomous coding agents in production daily as an AI Product Manager & Full-Stack AI Engineer at a…
Anthropic’s AuditBench Signals a More Practical Test of AI Alignment Auditing
Anthropic’s AuditBench research points to a more demanding way of assessing AI alignment: testing whether evaluation tools help an investigator unco…
Как технический эксперт COMETAL за два месяца передал нейросетям 20% своей работы
Рутина в проверке конструкторской документации — головная боль: одни и те же проверки, одни и те же таблицы, одни и те же в…
Anthropic's frontend-design skill names the three cliché "AI looks", hex codes included
Anthropic ships an official Claude Code skill whose whole job is stopping your agent from designing the same page every other agent designs. It is c…
Claude Structured Outputs Refusal Handling: Stop Parsing HTTP 200 Refusals
Claude structured outputs refusal handling belongs before domain deserialization. A successful HTTP exchange only says the API accepted and processe…
Is “Please double-check before use” an honest safety boundary?
Ai can make mistakes... I understand why this warning exists. But I keep wondering whether we’ve normalized an impossible expectation. I use AI for…
Anthropic Opens MHS Research Preview for Unified AI Control of Lab Hardware
Anthropic has begun a research preview of the Model Hardware Standard (MHS) , an open standard intended to give AI agents a common way to discover,…
Anthropic Opens MHS Research Preview for AI Agents Operating Physical Hardware
Anthropic has opened a research preview of the Model Hardware Standard (MHS) , a shared specification intended to help AI agents safely operate phys…
Одна среда на шесть компьютеров вместо командной подписки Claude Code
Я настроил свою работу так, что у меня в одной среде - 6 компьютеров. Хочу подробнее описать как у меня устроена командная работа с Claude Code У ме…
How I Set Up Claude to Actually Work Like My Pair Programmer
For the first few weeks with Claude Code, I used it like an overqualified search engine paste an error, grab the snippet, fix whatever it broke, and…
Своя Linux-based ОС на Rust и QML: опыт создания Platinum OS One
Полгода назад я решил не кастомизировать очередной Armbian под конкретную плату, а собрать полноценную ОС: свой build-движок уровня Cargo, свою обол…
Claude Function Calling with API Gateway: Build a Secure Serverless LLM Endpoint
When Claude wants to run code, you need a webhook it can call. Most teams slam together a Lambda URL, but that skips critical security and versionin…
Claude Code в пентесте ТехВилла: где ИИ ускоряет работу, а где ошибается
Автор занимается пентестом в ТехВилл. Несколько месяцев он использовал Claude Code как часть рабочего security-workflow для проверки гипотез об уязв…
Claude Opus 5 API Access: Pricing, Setup, and Model Comparison (As of Aug 2026)
Claude Opus 5 API Access: Pricing, Setup, and Model Comparison (As of Aug 2026) As of Aug 2026, Claude Opus 5 API access is fully open to individual…
AI Infrastructure, Next.js & Software Architecture: 2 Breaking Dev Trends Developers Should Act On
The AI stack is no longer just about picking a model, and modern web development is no longer just about shipping features. This week, two developme…
I built an RPG that teaches Claude Code by making you actually use it
Most tool documentation teaches by just telling you things. You read a page about /model , or hooks, or subagents, nod along, and forget it by the t…
No signup. No card. Free GPT & Claude.
Just go to: https://Duck.ai Duck.ai (by DuckDuckGo ) lets you chat with several AI models for free. Your requests are anonymized, and chats aren’t s…
The Upgrade That Wasn’t: When ‘Newer’ AI Feels Like a Downgrade
Some fortnights the complaint is the bill. This one it was the product itself. Across the forums where paying customers of the big AI tools compare…
Feedback wanted
I've spent the last month building a fully automated video pipeline: Claude Code + Remotion + ElevenLabs v3 + WhisperX, going from a script idea → r…
ИИ поступает в ШАД в 2026
Автор: Лыков А., к.ф.-м.н., академический руководитель Школы Высшей Математики и ШАДХелпера. В статье смотрим, как большие языковые модели справляют…
Скилл, который учится на ошибках AI‑агента, или Как автоматизировать обучение скилла
Что если AI‑агент сможет не просто исправить ошибку, а извлекать из этого урок? В статье рассказываю как автоматизиров…
Опыт использования GigaCowork: разбираем агента с прокси к зарубежным LLM
Понадобилось мне тут для пары задач таки попробовать ИИ-шные ассистенты для написания кода. В процессе понял, что давно не брал в руки шашку в том ч…
Вгрызаемся в память World of Warcraft: дрифт ценой в 20 гигабайт
Разбор одной инженерной задачи: как приложение рядом с игрой читает чат прямо из памяти процесса, почему первый способ это делать сжи…
I Was Burning $1.20 a Night on Nothing: A Claude Code Skill Library That Harvests and Curates Itself
Going from ¥100k/month as a student to ¥1.2M/month wasn't a matter of working harder. It was a matter of building an environment that keeps running…
Using Your Claude Subscription in Pi Agent — At Your Own Risk
If you use Pi and you're willing to gamble your Anthropic account on it, here you go: https://github.com/spksoft/pi-sub-anthropic That sentence is n…
Four Alarm Slots, Three Failure Modes: Building a Nightly Drain That Survives Sleep, Races, and Timeouts
Every night my Mac quietly rewrites my long-term memory. Not metaphorically — a shell script drains that day's Claude Code conversation logs into an…
Claude Code Overtakes GitHub Copilot: What JetBrains' Survey of 15,000 Developers Says About AI Coding Agents in 2026
AI coding agents are no longer an experiment. According to JetBrains' Developer Ecosystem Survey 2026 , 90% of professional developers now use AI co…
I gave my AI a supervisor. It built a bureaucracy.
For about three months I have been running two AIs against each other on purpose. The setup first, because nothing below makes sense without it. I a…