Поэзия агентной разработки или как теперь писать код
Я к вам пишу — чего же боле? Агент все может написать. Но за ошибки поневоле Придется вам же отвечать. (Письмо инженера Татьяны к вайбкодеру Евгению…
Architecture
⚑ Report a ProblemLatest Architecture news from Tech News
All topics
agents
ai
api
architecture
automation
aws
backend
beginners
career
database
devchallenge
devops
javascript
llm
machinelearning
mcp
news
opensource
performance
productivity
programming
python
react
security
showdev
softwareengineering
systemdesign
tutorial
typescript
webdev
ИИ-ревью, или как я себя чуть не уволил
AI-ревьюер для GitLab, который проверяет не отдельный merge request, а всю задачу сразу, во всех сервисах, которые она задела. И почему для этого по…
Multi-agent work in three spoonfuls: what worked for me and what did not
This started as a practical annoyance: long tasks interrupted by quota limits, conversations that became too heavy, and reviews that required copyin…
Архитектор, параноик, фантазёр и другие сотрудники IT‑компании будущего
За последние пару лет произошло странное: написать работающий код стало почти неприлично легко, а построить хорошую программную систему наоборот - с…
Codex vs CodeRabbit: Choose the Ownership Boundary, Not the Review Score
I defined the comparison framework and the decision criteria. AI helped re-check the current official documentation and rewrite the Japanese draft f…
Cumora Makes Agent Coordination the Product, Not a Chat Feature
Cumora’s public repository presents a cross-platform team chat application in which AI agents occupy the same conversational spaces as people: direc…
How I use scheduled Codex jobs to build daily reports
Most of my analytics job should not be done by an LLM. The source metrics, dates and repeatable transformations should stay exact. I used to think t…
Мой опыт онбординга разраба с амнезией
Давай признаем, ты чуть ли не 90% кода пишешь с помощью клода, кодекса или еще какого агента. Ты выпускаешь несколько мр-ов в день, пушишь несколько…
We Got the Prompt Cache Working. Our Pipeline Got Slower.
"You're spawning a fresh codex exec for every single call? Just run the app-server and reuse a thread. The prompt cache alone will pay for it." That…
Teaching Codex to Paint: A Stateful Image-Editing Skill Built on Gemini's Interactions API and MCP
TL;DR: nb2lite-skill-codex wraps Google's gemini-3.1-flash-lite-image model (NB2Lite) in a tiny FastMCP server and packages it as a Codex skill. You…
Two AI models that attack each other beat one that agrees with itself
Two AI models that attack each other beat one that agrees with itself Four times I asked the same question. Four times I got a confident answer. All…
Swarming Claude Code and Codex in Parallel: Running Multiple Agents at Once with tmux and Git Worktrees
In my previous post about a cost budget advisor , I built a mechanism that checks how much quota is left before it runs anything. This time I want t…
Did Codex Overtake Claude Code? The 7M-User Question
Did Codex Overtake Claude Code? The 7M-User Question Codex hit 7 million active users on July 13, 2026 — up from 600,000 at the start of the year. T…
Five ways your AI coding agent wastes tokens (and how to fix each one)
On a metered API key, token waste shows up as a bill. On a subscription plan, Claude Code, Codex, "5x" and "20x" tiers, it shows up as a lockout. Yo…
AIналитик v2 по BABOK: как я переписал AI-платформу для бизнес-анализа, чтобы она работала c любыми LLM
Спойлер: архитектура AIналитика полностью переписана, теперь Платформу можно запускать практически под любым харнесом (OpenCode, Kodik, Codex, Claud…
Treat AI coding sessions as project infrastructure
Most AI coding workflows treat the current session as the important part. That makes sense while you are in the loop. You ask Claude Code to inspect…
Run OpenAI Codex CLI on Claude, Gemini, or Llama — in 50 lines of C#
OpenAI's Codex CLI ships with a great editor-agent UX: shell tool, apply_patch , plan tracking, the lot. The catch — as of February 2026 it only spe…
Sharing memory between three AI agents: Claude Code, Codex, and Hermes
Turkish version: blog.arasmehmet.com What's in here: Hot-swap pain Why not just X? Setup at a glance The hub, INDEX.md Agent workflow rules Privacy…
Why every Claude Code-built site looks the same — and the image layer that breaks it
TL;DR: AI-built sites look uncannily similar because they share the same defaults — Tailwind + shadcn/ui + Lucide + the same gradients. It's not a p…
Вайбкодинг как управляемая разработка на примере личного опыта
Есть популярная фантазия, что вайбкодинг - это когда человек написал одну фразу , ушёл пить кофе, а ИИ через час выкатил продукт. На практике всё чу…
How Codex Can Drive Verifiable SketchUp Modeling
This is not a step-by-step tutorial. Until the demo path is fully verified, I do not want to package it as something readers can simply follow and r…