Habr AI
AI news source. Articles are auto-selected and adapted by Hamidun News editors.
Latest publications
Google AI Ultra: how to turn a subscription into a pool of parallel agents and model consensus
Google AI Ultra is being proposed as the foundation for a multi-agent stack: run parallel Gemini workers, delegate routine tasks, and cross-check decisions with a second model.
OpenAI released GPT-5.4 Pro: new records in ARC-AGI-2, FrontierMath, and logic
OpenAI introduced GPT-5.4 Pro — a model that made sharp gains on difficult benchmarks, solves reasoning tasks better, and handles unconventional logic more confidently.
nullClaw on Zig outperformed OpenClaw in memory and startup in local AI agent tests
nullClaw, a lightweight AI runtime on Zig, showed near-instant startup and several times lower memory usage in a local comparison with OpenClaw, even in a scenario with 10 parallel coding tasks.
OpenAI's ChatGPT 5.4 beat Claude Opus 4.6 and Gemini 3.1 Pro in a Habr comparison
Habr published a comparison of three flagship models in routine tasks: ChatGPT 5.4 ranked first by total score, Gemini 3.1 Pro was the cheapest, and Claude Opus 4.6 was the most expensive.
Study: Cursor speeds up early development, but later adds to the team's technical debt
A study of Cursor found that the AI assistant sharply accelerates code delivery in the first weeks, but then increases complexity, the number of warnings, and slows the team down.
Yandex at AI Dev Day Showed How AI Is Already Changing Development at Avito, Ozon, and T-Bank
At AI Dev Day, companies Yandex, Avito, Ozon, T-Bank, and Sber demonstrated where AI is already accelerating development and where the effect is still limited by metrics, processes, and quality control.
How AI is changing indie development: it's getting harder for solo developers to compete
The columnist argues that AI has sped up MVP launches, but at the same time raised the barrier to entry, intensified marketing competition, and weakened solo developers' advantages.
A company without managers: three traps companies fall into when implementing AI
Of 50 executives at ProIT Fest, only three said AI had actually made decision-making easier — even as companies have fewer and fewer managers.
Bitrix24 showed how to add four automation robots to a business portal
Bitrix24 released the next part of its practical series and showed how to integrate four robots into a business portal: for cleaning phone numbers, normalizing names, and collecting data on tasks and deals.
Anthropic explained how to build skills for Claude Code and why teams need their own marketplace
Anthropic showed which skills actually work in Claude Code, how to write them without extra noise, and why large teams need their own extensions marketplace.
Mentorpiece launched a free course on non-functional testing of AI applications
Mentorpiece released a free course on how to test cost, reliability, traceability, and data leaks in AI applications before they go to production.
Claude Opus 4.6 Detected a Hidden Trap in PDF and Revealed New Hiring Rules
Claude Opus 4.6 discovered a hidden instruction in a PDF test task, warned the candidate about the trap, and showed how hiring checks are changing in the LLM era.
Habr AI named seven free Telegram bots with GPT for work, study, and content
Habr AI compiled seven Telegram bots with conditionally free access to GPT and other neural networks: the selection includes services for text, images, video, and quick tasks without VPN.
ChatGPT Search and Google AI Overviews are changing SEO: Habr AI released a guide to GEO
Habr AI has published a practical guide to GEO — a new form of optimization for LLM search, where what matters is not keywords, but the structure, authority, and citability of content.
OTUS: why language models hallucinate and what measures reduce the risk of errors
OTUS explains why LLMs confidently make up facts, references, and advice, and which engineering measures help reduce the risk of errors in product, support, analytics, and code.
A2A Protocol: How Google Standardizes Orchestration of Multi-Agent AI Systems
A2A—an open protocol from Google for inter-agent communication that solves the key problem of multi-agent systems: context loss, infinite loops, and uncontrolled token consumption.
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.