Habr AI
AI news source. Articles are auto-selected and adapted by Hamidun News editors.
Latest publications
Asimov’s Three Laws Are Becoming Reality for Humanoid Robots
If in 1942 Asimov considered machine safety a philosophical problem, today humanoid robot engineers are solving the same problem in actual code — and it has turned out to be far more difficult than it seemed.
Hermes and OpenClaw: philosophy vs. functionality in AI agents
Two open frameworks for AI agents look similar in functionality, but stem from opposite design philosophies.
How Mozilla used Claude Mythos to find 271 vulnerabilities in Firefox
With the help of Claude Mythos Preview, Mozilla found and fixed a record number of hidden vulnerabilities in Firefox, demonstrating the effectiveness of AI in finding critical security bugs.
I handed development over to AI agents: the story of a self-evolving Telegram bot
A developer automated the evolution of a Telegram bot for learning Georgian by handing the code over to AI agents overnight. What actually happened.
Vibe coding is gambling: why AI-assisted development is becoming a game of chance
Developers are increasingly generating code with AI without checking it, relying on luck instead of analysis. This is no longer engineering and has turned into gambling with unpredictable consequences.
A million Claude monkeys: how vibe coding is changing the profession
When AI generates code by feel and the developer trusts intuition instead of a plan, it works — but only those who have learned to do it right survive.
Claude switches to HTML: why Markdown no longer works for AI agents
Markdown can no longer meet the demands of powerful AI agents. Claude Code is switching to HTML because agents need better presentation, interactivity, and an easy way to share finished results.
The censorship paradox: why neural networks were banned from generating the nude human body
Habr is discussing a philosophical paradox: why can't AI systems reproduce the nude human body if it is openly displayed in museums and used in education?
LazyWeb connects AI agents to the designs of 257,000 real apps
The LazyWeb MCP server gives Claude Code and other AI agents access to the visual context of 257,000 real apps to generate realistic interfaces instead of typical AI design.
How a frontend developer used Cursor to speed up onboarding
Cursor helps developers understand the structure of an unfamiliar project in days instead of months — developer Rodion explained how this works in practice.
Full Claude Code guide published on Habr: Anthropic features and practices
Habr has published a complete Claude Code guide from Anthropic, covering all features, updates, and development best practices as of March 2026.
LLM bots on Telegram can be hacked with 6 lines of code: engineer built a scanner and exposed a project
An engineer built the BarkingDog scanner and found that popular Telegram LLM bots can write keyloggers and provide hacking instructions. All issues can be fixed by editing the system prompt.
Why LLM text is immediately recognizable: architectural markers in model architecture
LLM text is recognized within five seconds thanks to architectural markers. This is not an error, but the result of the training corpus statistics. We explain how these markers emerge and how to weaken them.
Who is stricter with JSON: OpenAI, Gemini, and xAI tested for schema compliance
Habr checked how strictly OpenAI, Gemini, and xAI comply with JSON Schema and found unexpected limitations in Structured Outputs.
How a developer built an AI radio and encountered Tunio, a competitor
A solopreneur working out of a garage was building a music service with AI and unexpectedly came across a similar project, Tunio, on Habr. A story about how different paths led to the same results.
Local LLM on a 2017 Graphics Card: AMD RX 580 + Vulkan + Ollama
The aging AMD RX 580 can run modern language models — with Vulkan and Ollama, you can get 15–35 tokens per second right on your computer running Fedora.
From TF-IDF to Word2vec: Beeline Cloud released a collection on embeddings
Beeline Cloud has published free guides on embeddings and vector representations — from the basics of TF-IDF and Word2vec to the use of cosine similarity in semantic search.
Which code architectures suit AI agents best
Traditional approaches like TDD and OOP were designed for humans with full memory. AI agents are limited by context and memory, so some architectures suit them better than others.
This week in AI: UAE, Claude in Adobe, ElevenLabs, and the economics of neural networks
Digest: the UAE expands AI-powered government services across half of its portal, Anthropic integrates Claude into Adobe and Ableton, ElevenLabs launches AI-Spotify, and companies rethink the economics of neural networks
Language models don’t understand time, but they talk about it
A language model generates an answer in seconds, yet claims that the task will take weeks — revealing a deep problem in the model’s understanding of time.
A developer spent a year, not an evening, building a football management game. Here's why
AI speeds up development, but a full-featured game requires much more: architecture, design, assets, and manual product assembly.
How to run an AI agent for infrastructure diagnostics on a MacBook
A local AI agent can handle real infrastructure diagnostics tasks on a low-powered MacBook. A developer on Habr shared their experience: it works, but requires optimization for your hardware and system.
Google DeepMind to train AI in war and diplomacy in EVE Online
Google DeepMind will train AI in an offline version of EVE Online, teaching cooperation, war and diplomacy in a complex MMORPG simulation with a live economy.
The illusion of mastery: how generative AI makes beginners look like experts
Generative AI makes it possible to scale output almost without limit, but it creates two dangerous problems: beginners start producing work that looks expert-level without being able to judge quality, and users encounter
How an AI recruiter underestimated a Rust developer because of an old profile
A recruiter's AI assistant analyzed the programmer's digital footprint and rated him as Junior+/Middle, even though years of growth had made him a Senior and he had completed two complex projects.
Five vibe coding mistakes: why AI code generation is more dangerous than it seems
Vibe coding seems like magic, but it hides dangerous mistakes. We break down 5 critical pitfalls: architectural problems, vulnerabilities, low-effort prompts, and loss of context that developers using AI often miss.
From LLM to action: how to build an AI agent with Go and GigaChat
Inspired by a talk on AI agents, a developer built one in Go using LangChainGo and the Russian GigaChat. He shares his experience integrating tools, MCP, and the pitfalls involved.
Engineering agents instead of developers: six months of a coding revolution
In six months, AI agents for software development have gone from experiments to a standard tool. What seemed like a revolution in May was already a routine workflow by December.
Why people see a friend in AI: how language models imitate humans
Large language models imitate human communication so convincingly that users often forget they are talking to an algorithm — the trend of seeing AI as a friend is especially popular among young people.
NPUs in laptops: new requirements for corporate IT
Microsoft requires an NPU for Copilot+ PCs, while AMD and Intel are integrating neural processors into SoCs. Corporate IT is moving to a hybrid architecture: light AI tasks on the device, complex ones in the cloud.