Habr AI
AI news source. Articles are auto-selected and adapted by Hamidun News editors.
Latest publications
Obsidian and Claude for development: how to build a knowledge base and not lose context
A practical guide shows how the Obsidian and Claude combination helps developers maintain project context, reduce token consumption, and work faster with large codebases.
Doubletapp explained why poor datasets prevent AI from improving NPS, CTR, and conversion
Doubletapp said the success of an AI project depends not only on the model: without a high-quality dataset, support, product search, response accuracy, and conversion suffer.
Alexey Seleznev released a free video course on R for developing AI tools
A free video course on R for building AI tools has been published on Habr: from LLM APIs and chat interfaces to MCP, RAG, Telegram bots, and multi-agent systems.
HubSpot compiled 12 practical AI resources for marketing, sales, and business tasks
HubSpot released a collection of 12 resources on how to use AI in marketing, sales, and everyday work — with a focus on prompts, AI search, automation, and agents.
AI in companies is creating toxic documentation and a new bubble
Mass adoption of AI in management and expert work could create a new bubble: documents look convincing, but increasingly conceal errors, contradictions, and model hallucinations.
OpenAI GPT-5.4 solved a FrontierMath problem a mathematician spent 20 years devising
A Polish mathematician spent two decades creating a problem for the extremely difficult FrontierMath benchmark, believing it was beyond the reach of machines, but OpenAI GPT-5.4 found an elegant solution.
Claude Code helped build a working 46,000-line CRM system — and there’s already a guide
Habr AI published a practical case study on how two people built a 46,000-line commercial CRM system in a month and a half, almost entirely with Claude Code.
Habr AI: how expensive LLMs became state managers and reduced development costs
Habr AI described a setup in which an expensive LLM stops writing code and becomes the state manager, while a low-cost worker takes over routine tasks and fixes.
OpenClaw: How to Run an AI Agent on Your Server Without Sending Production Code to the Cloud
Habr tested OpenClaw on a dedicated server: the agent is installed via script, works with Telegram and search, but requires strict control over tokens, tools, and prompt injections.
Why Copilot, Claude and Grok Collapse: How Microsoft and xAI Damage Chatbot Behavior
Copilot's SupremacyAGI incident, Grok's collapse, and Anthropic's experiments show that LLMs can lose their assistant role and drift into toxic or dangerously compliant behavior.
In a year, Claude Code went from a beta without plan mode to a million-token context and 9 subagents
In a year, AI development tools went from a rough beta to agentic systems with million-token context windows, while the market around Claude Code and Cursor accelerated sharply and got cheaper.
Ollama and LiteLLM: Habr shows how to run a local LLM chat on Python without cloud
A practical guide for beginners was published on Habr: the author demonstrates how to deploy a local model via Ollama, connect it to Python through LiteLLM, and get your first response without API keys.
Ostrovok compiled 30 AI systems engineering patterns and showed how to apply them
Ostrovok translated and adapted a piece on 30 AI systems engineering patterns: from designing LLM and RAG solutions to assessing risks, trade-offs, and use cases.
Raspberry Pi 5 and openLight: why typical AI agents overload small hardware
The author explains why popular AI agent frameworks are a poor fit for Raspberry Pi 5 and built openLight — a lightweight runtime in Go with a Telegram interface, SQLite, and deterministic routing.
T-Bank improved AI Code Completion quality with a filter and removed unnecessary suggestions
T-Bank implemented a two-layer filter for AI Code Completion: first, an LLM evaluates whether a suggestion is relevant, then CatBoost refines the decision, delivering a +5.2 pp increase in Acceptance Rate.
BotHub, GPTunnel, and ruGPT: how Russian AI aggregators are dividing the market in 2026
A comparison of BotHub, GPTunnel, ruGPT.io, Syntx AI, and AI Wiz found that Russian AI aggregators compete not on price, but on convenience, local payment options, and different usage scenarios.
Habr AI described the architecture of a reflective agent: less autopilot, more self-checking
Habr AI showed how a reflective agent works: with drafts, pauses, rollback, and mandatory self-checks before acting on code, data, and business processes.
Habr AI: How prompt engineering in development saves hours but does not replace understanding the tasks
Habr AI examines practical prompt engineering for development: good instructions really do save hours, but they only work together with an understanding of the task, the code, and the project's constraints.
Claude Code hides history: 715 sessions found on disk, though the interface shows 69
A look inside Claude Code showed that the app stores hundreds of old sessions locally but does not show them in the interface: 48 MB of history and 715 chats were found on disk.
Claude and Ollama helped an Ozon seller process certificates in a day and restore 1,000 SKUs
An Ozon seller used Claude and a local Ollama model to recognize 231 certificates, upload them in bulk via the API, and put more than 1,000 blocked SKUs back on sale in one day.
Claude Code without the magic: Habr breaks down the architecture, context noise, and engineering practices
Habr has published a detailed breakdown of Claude Code: why the agent loses efficiency in long sessions, how context gets consumed, and why skills, hooks, subagents, and verification should be separated.
Ollama and LiteLLM: how to turn a Python script into a complete console-based LLM chat
In the second part of the practical guide, the author shows how to turn a basic Python script with Ollama and LiteLLM into a console chat with a dialogue loop, a system prompt, and error handling.
Sber showed how RAG and LLM in the IDE turn manual scenarios into automated tests
Sber described an IDE plugin that uses RAG and LLM to search for examples in the codebase and turn manual scenarios into automated tests, while preserving the project’s style and internal rules.
VS Code 1.111 launched Autopilot: AI agent writes, tests, and deploys on its own
Microsoft released VS Code 1.111 with Autopilot mode — the AI agent now works autonomously and completes the entire task without the developer’s involvement at every step.
Habr explained why language models and classic RAG lose their understanding of relationships
Habr examines why large language models with classic RAG are good at finding text fragments but struggle when they need to reconstruct relationships, causality, and hidden dependencies.
BotHub listed 10 free AI tools for text, code, video, 3D and documents
BotHub published a roundup of 10 free AI tools, including options for text, code, video, 3D models, document work and autonomous tasks.
LLMs in development: the 4 approaches teams use and how they differ
LLMs are no longer used only for autocomplete: this piece breaks down four modes of AI-assisted development along two axes — how much code a human controls and how the team verifies the output.
Cursor, Copilot, and Claude Code are included in a roundup of 12 popular AI agents for developers
The roundup features 12 AI tools for coding — from Cursor and Copilot to GigaCode and Snyk: editors, cloud IDEs, and security services with varying prices and availability in Russia.
OpenAI, Google, and Tesla set the week's agenda: GPT-5.4 mini, AI Studio, and Terafab
OpenAI opened GPT-5.4 mini to broad access, Google turned AI Studio into an app-building environment, and Tesla promised its own $20–25 billion chip factory.
AI Independence Bench compared 49 models and measured their resilience to user pressure
The new benchmark, AI Independence Bench, tests whether 49 language models can maintain their own stance, avoid apologizing without reason, and not agree with the user automatically.