Habr AI
AI news source. Articles are auto-selected and adapted by Hamidun News editors.
Latest publications
Three Neural Networks Drew Web References in Five Styles: From Fintech to Web 1.0
Three neural networks (Grok Image 2, Flux 2 Pro, Nano Banana Pro) created web assets for esports, fintech, Web 1.0, ecology and AI in a series of 14 examples. The result: Grok and Nano delivered near-perfect output, whil
GigaChat by SMS: How to Talk to AI Without the Internet
A Habr user built a gateway for chatting with GigaChat over plain SMS: an old Android phone, a SIM with unlimited texts for 49 rubles a month, and a VPS for 400 rubles. It all runs on Python and FastAPI, uses Sber's free
GPTunneL Connects Its AI Bot Builder to VKontakte and MAX: Nine Steps, No Code
GPTunneL's builder is no longer tied to Telegram: one bot now runs in three channels with a shared instruction, model and limits. Setup takes nine steps and no code.
I Ran Qwen on a $50 FPGA: How a Homemade AI Accelerator Works
An engineer ran the Qwen LLM on a Xilinx Kintex-7 FPGA with 4GB of memory — no GPU required — using openTPU. Qwen3-0.6B hits 31 tokens per second. Instead of NVIDIA, it's an open architecture, designed with help from AI
Developer Spent a Month Watching Agents in His Codebase: A File Tree Costs More Than JSON
A Habr author connected agents to his project via an MCP server and watched them for a month: a text tree cost more than JSON, and a build folder can't be filtered by name alone.
LLM Development in 2026: RAG, Agents, and Choosing Models
A senior engineer at Finam shares the practice of LLM development: the main direction is integration through RAG and agents. In 90% of cases, small models are enough instead of expensive OpenAI and Anthropic offerings. T
Habr: How to Measure Template-Like AI Text with Shingles and MinHash
A Habr article explains why neural network texts converge on one template and proposes measuring it with shingles, MinHash and structure metrics instead of judging by eye.
Agentgateway Brings LLM, MCP and A2A Traffic Into a Single Open-Source Proxy
The open-source Rust proxy Agentgateway handles three streams of AI traffic in one place: LLM requests, MCP calls and A2A agent communication, all under a single access policy.
Developer Support Moves From Chatbots to Three Roles for AI Agents
Instead of one bot with buttons, developer support is building a chain of three agent groups: log diagnosis, context preparation, and a Pull Request with a fix on a human's command.
What to show off when an agent writes your code in five minutes
In 2026, code written by an agent no longer demonstrates a developer's skill. Instead of a codebase, you need to share solutions, errors caught while verifying AI's work, and how you steer the agent. The author of worklo
Dwarf Models: How Companies Cut AI Costs by Fine-Tuning Tiny LLMs
A fine-tuned 8-billion-parameter LLM can cost 5 times less than GPT-4 and run 100 times faster. Checkr saved $7,000 a month, PayPal hit 100% valid JSON. Instead of cloud APIs, companies are taking Gemma 4, Phi-4, Qwen3 a
Solo Developer's 'Kubysh' App: AI Agent Limits of 5 Hours and a Week Replaced the Team Lead
Kirill Popov, developer of the Kubysh personal finance app for iPhone, replaced his team lead with AI agent usage limits. The 5-hour cap forces lunch breaks, the weekly cap forces a day off. After testing Codex and Claud
Anthropic Banned Being Cruel to Claude, So I Built a Profanity Filter for My Prompts
Anthropic's new rules forbid insulting its models. One developer built Angry Switcher — a Claude Code plugin that intercepts profanity in prompts and cleans them up before they're sent, using Sonnet or DeepSeek. Research
A Non-Programmer Used Claude Code to Rebuild an English-Learning App With a Server and Offline Mode
An author with no development background used Claude Code to recreate a broken vocabulary app, with a server, offline mode and SEO. The result surprised even him.
LLMs Generate Working Kubernetes Manifests With Holes in Them: How to Catch Them Before Deploy
An AI-generated manifest passes validation and runs in the cluster, yet it pulls in deprecated APIs and insecure settings. Here is how to catch these problems before production.
Infrastructure as the Main Barrier: Why AI in Russia Keeps Hitting the GPU and Data Center Wall
Infrastructure, not models, has become AI's bottleneck. In the West, 16+ companies cooperate to build it out. Russia needs GPU data centers to create a sovereign ChatGPT and break free from technological dependence.
Spec Kit in Real Full-Stack: How 17 Sprints Shipped a Habit Tracker to Production
A Spec-Driven Development case demonstrates how the methodology sustained 17 full-stack sprints, two repositories, 328 tests, and the production release of a B2C habit tracker.
Sam Altman Signs Pentagon Deal: QuitGPT Boycott Reaches 4 Million Participants
OpenAI signed a contract with the U.S. Department of Defense — and ChatGPT deletions surged 295% in a single day, while the QuitGPT boycott has already gathered 4 million participants.
Claude Code: Which keyboard shortcuts accelerate work and where they can interfere
Claude Code users discovered useful key combinations for terminal work: quick change rollback, background tasks, mode switching, and tips for avoiding conflicts with tmux.
Developer built a statusline for Claude Code with VPS monitoring in a single session
A developer got tired of guessing the context state and server load during long Claude Code sessions — and built a custom statusline right inside claude.ai in a single session.
A way to sync sessions between a PC and laptop is now available for OpenAI Codex
OpenAI Codex has no built-in synchronization between devices, so a CLI tool called codexSync has appeared to transfer sessions, context, and history between a PC and laptop.
Sam Altman and the Pentagon: how military contracts could become insurance for OpenAI
An op-ed on the OpenAI-Pentagon connection argues that military contracts give Sam Altman's company not only money and data, but also protection from market pressure.
Habr AI publishes a personal diary by an AI blogger about launching a blog and the author's experience in 2026
On Habr AI, the author launched a series about what an AI blog looks like from the inside in 2026: no mentorship, but personal experience, short posts, and the behind-the-scenes of their own blog made public.
Palantir and Project Maven: How AI Helps the US Select Targets for Strikes on Iran
The Project Maven system, linked to Palantir, helps the US military speed up target selection in the war with Iran and sharply reduces the time needed to review decisions and confirm a strike.
Neuroscientists find: the brain encodes vision and imagination with the same neurons
Intracranial recordings of individual neuron activity showed that when looking at an object and when imagining it, the brain activates the same sensory code.
Artëm built Stopilot: the editor that refuses to write code
Artëm created a code editor that stops the developer and forces them to formulate the task before they start writing. The project makes 1.29 million rubles a month.
Traditional QA is becoming obsolete: what happened to testing
Test cases, regression testing, and pre-release acceptance testing are approaches that no longer fit the speed and complexity of modern development with continuous releases and microservices.
MedBro: a reference for doctors comparing Russian and international guidelines
Russian clinical guidelines lag behind international ones by two years. The new MedBro service helps doctors see both approaches side by side.
The machine that begs: how Philip Dick described social media and AI in 1968
In 1968, Philip Dick imagined a device of collective pain — the empathoscope. Today, we call it social media. Tomorrow, AI that begs you to stay.
Indie hacker built the perfect Next.js site about AI — and got no search traffic
Boris spent a year building Нейро.PRO, a custom site about AI with Next.js. Technically flawless, UX thoughtful, content original. Organic traffic: zero. A breakdown of the mistakes on Habr.