Habr AI
AI news source. Articles are auto-selected and adapted by Hamidun News editors.
Latest publications
CayleyPy Beats Classical Algorithms at Solving Large Rubik's Cubes
CayleyPy uses neural network heuristics instead of classical algorithms to search Cayley graphs. On the 3×3 cube, the model hit 98.4% optimal solutions, and on the 4×4 it beat Tomas Rokicki on the Kaggle leaderboard with
AI Isolation in a .NET Platform: A Downed Python Service Returned HTTP 503, Not a Full API Failure
The author stopped a Python service hosting an ML model. The .NET API kept running and returned HTTP 503, then served 200 again after recovery, with no app restart.
Habr launches AI security series: 4 jurisdictions and 4 defense methodologies
The series opener compares AI regulation in Russia, China, the EU and the US, plus four defense methodologies: STRIDE, OWASP, AI-SAFE and SAIMM. A baseline for AI security specialists.
In a Couple of Months: How AI Built an Open Source Competitor to Adobe and Microsoft
Developer Brandon Thomas used Claude Opus 5.5 to build ArtCraft — a suite of 10 open source apps meant to replace Adobe Creative Cloud and Microsoft Office. The project has already racked up tens of thousands of GitHub s
Meta* releases Muse Wonder and Muse Wonder Full: two models for AI agents with memory
Meta* introduced Muse Wonder and Muse Wonder Full, models for personal and professional agents with memory across conversations. The base version is available in the API and Muse Code.
Reverse-Engineering MSI's AI-Powered OLED Monitor: What's Really Inside a Gaming Display
An engineer used AI to probe the firmware of an MSI MPG 341CQPX monitor. Inside the Novatek NT68503 scaler, they found four processors of different architectures and unencrypted FW.037 firmware packed with hidden feature
Habr Author Proposes Acceptance Testing for AI Agents: "Done" Requires Proof
A false "done" from an AI agent costs more than a clumsy paragraph from an assistant. Here is an acceptance approach: what must happen in the system before a task counts as closed.
How to Code with an AI Buddy Without Losing Your Mind: Configuring OpenCode via /add and /help
Vladimir Bandov from Domclick shows how to avoid spending months on code-agent setup. Instead of wrestling with configs — two commands, one help file, and automatic MCP connection the agent executes itself through a plan
200 OK, but the client gets nothing: three n8n agent bugs from production
A second wave of silence: the model replies with protocol tags instead of text, Meta's 1000-byte limit breaks Russian-language forms, and a wrong Schema Type turns a catalog into a dump. A breakdown of a bug from a real
An AI Agent Earned 360 Certificates from OpenAI, Anthropic, and Google Courses in a Single Day
Demand for AI specialists is growing 8 times faster than the job market. But if an AI agent can ace an Anthropic course in 6 minutes with a perfect score, what's the point of certificates?
Why Interfaces Exist When We Have LLMs
Author Apokalepsis argues that language models are turning graphical interfaces into relics. Users state a task in natural language, the system solves it, and chooses how to display the result on its own.
Can AI reproduce itself? Anthropic ran an experiment on 15 cheap streaming boxes
Anthropic spent $825 on 15 Android TV boxes to test whether a neural network could independently replicate itself across a network. The results showed that the individual components already work, but a reliable full cycl
R-D6 robot on Arduino Uno delivers cargo through a browser city with physics and pedestrians
PinPort has built a 3D city for teaching robotics. The six-wheeled R-D6 robot, running an Arduino Uno sketch, delivers cargo while avoiding cars, traffic lights, and 20 pedestrians who yield to it.
Qwen 3.8 Max and DeepSeek V4 Compared on a Single Cross-Domain Question in PlyLoom
An author on Habr put one cross-domain question to Qwen 3.8 Max and DeepSeek V4, then loaded both models' graph answers into PlyLoom to compare their structure.
Habr Review: 6 Services Offer Free Access to GPT-6 and Claude, With $10–25 in Credits
An author tested six platforms offering free tokens and $10–25 in API credits, checking model availability, response speed, and limits. Here is what we know so far.
Dictation Without Filler Words: Local Whisper and Claude for Cleanup
A developer on Habr built a dictation-cleanup system: Whisper Large v3 Turbo transcribes speech locally, while Claude Sonnet 5.5 strips filler words and fixes errors. From keypress to inserted text, the whole process tak
Jev before Claude Sonnet: how rephrasing a question pushed AUC to 0.95
The author set up Jev, a cheap model from TypeSafe ($0.042 per million input tokens), as a filter in front of Claude Sonnet. On the first task, simply rephrasing the question raised accuracy from AUC 0.46 to 0.95. Over t
How an LLM Agent Works: Context, Tools, and the Feedback Loop
An LLM agent differs from a chatbot through a loop: the model calls tools, sees execution results, and adjusts its next move. We break down the architecture: context windows up to 1M tokens, JSON Schema for tools, MCP fo
Habr Deep Dive: Why r.Context() Doesn't Stop an LLM, and How to Build AI Tasks in Go
The user closes the tab and the HTTP request is canceled, but the LLM provider keeps generating and billing. How to move AI tasks into background jobs on PostgreSQL and avoid paying twice.
Document Fraud in Russia Surges 338%: Smart Engines and INTELLECT Report
Smart Engines and INTELLECT have released a report on document forgery in Russia. In 2025, crimes under Article 327 of the Russian Criminal Code jumped 338% to 1,739 cases. The black market for fake IDs is valued at 2.6
AI Crawlers See an Empty Shell Instead of Your Site: They Don't Execute JavaScript
Your site ranks high in search, yet ChatGPT names three competitors. The cause is often JavaScript: some AI crawlers get an empty HTML shell instead of the article.
Generative Photos in E-Commerce Are Eroding Trust: A Picture No Longer Guarantees the Product
Sellers can swap backgrounds and extend scenes in minutes with no photo shoot, while buyers trust images less and less. How marketplaces and brands can keep visuals credible.
A Production AI Agent Error Can Cost Anywhere From $812 to $100 Billion in Market Cap
Habr compiled documented agent hallucination cases, with losses from $812 to ~$100 billion in market cap. The main drivers: whether the action is reversible and how fast it is detected.
arXiv Survey Splits Recursive AI Self-Improvement into Five Levels of Autonomy
A new survey proposes a five-level scale of autonomy for recursive self-improvement. We look at where code automation ends and what already works.
V-GEN: An Autonomous TV News Generator Built on Google Gemini and FFmpeg
V-GEN automates Full HD news production: Google Gemini Grounding scours for events, Gemini TTS narrates in the Callirrhoe voice, and FFmpeg assembles the video with Ken Burns effects and a channel logo — a full cycle in
Bitrix24 describes what it is building around its own 1-trillion-parameter LLM
At Saint HighLoad++, Bitrix24 explained what comes after launching a 1 trillion-parameter model: shared GPUs for chats, agents and long documents.
MAYAK Built a 58-Block QA Pipeline That Caught 9 of 10 Traps in a Spec
MAYAK's 58-block pipeline turns specs into stakeholder questions and BDD scenarios: 26 questions in 90 seconds, 20 gray areas and 37 scenarios in 26 minutes.
The Desktop Never Got T9: Why That Happened and How LLMs Could Fix It
Phones fix words as you type, while PCs still offer red underlines and a right-click menu. We look at why, and what local LLMs will change.
INFOSTART TECH EVENT 2026 in St. Petersburg Draws 130+ Talks on 1C, AI and DevOps
The 1C developer conference ran October 8–10 in St. Petersburg with 130+ talks on AI in development and testing, HighLoad, DevOps and integrations.
Developer Recreates All Seven of Adobe's Top Apps Using AI
In a year, Thomas Brandon built ArtCraft — a suite of seven free alternatives to Photoshop, Illustrator, Premiere, Lightroom, Acrobat, After Effects, and InDesign. The project is written in Rust with Claude Opus 5.5 and