Habr AI
How a Russian Developer Spent Days Launching Gemini—and What Finally Worked
A Russian programmer spent several days launching Gemini from Russia via VPN, tried dozens of approaches, and documented each step—what didn
Product Graph and Agent Memory: Why AI Doesn't Save Products Without Knowledge Structure
An analysis of Product Graph explains why even powerful AI agents are useless without shared product memory and how interconnected knowledge
Laboratory Over Six Years: From USB Drives and Notebooks to AI That Finds Hidden Equipment Defects
A story about how one laboratory spent six years building digital infrastructure — and ultimately developed AI that reads deposition logs an
How AI Transformed Diary Research: Three Compromises We Left Behind
A UX research team explained how AI made it possible to abandon compromises on sample size, duration, and analysis depth—without sacrificing
Marcin Moskala Audited GeminiAI: What the Code Review Revealed About Coroutines and Android Architecture
The author of the open-source GeminiAI client shared how his project passed Marcin Moskala's audit and why coroutine errors became the key t
Anthropic: Claude Code source leak revealed complex agentic architecture
A leaked sourcemap from Claude Code showed that Anthropic's product has long evolved from a 'chat CLI' into a platform with sub-agents, memo
Sber explained why business needs an AI Overlay layer instead of restructuring departments
Sber showed why targeted implementation of generative AI rarely brings profit, and proposed an alternative — a horizontal AI Overlay layer o
Saiga Llama 3 8B on 10 GB VRAM: How Habr Achieved 93% Accuracy on War and Peace
Habr AI demonstrated how to run Saiga Llama 3 8B on 10 GB VRAM, compress two volumes of War and Peace into a summary, and reduce hallucinati
4 Non-Technical Founder Patterns That Ground Startups
A Habr developer who worked with several non-technical founders describes four patterns that prevent startups from launching—and how AI make
DeepSeek and Gemma: How a Hybrid LLM Experiment on Kaggle Broke the Transformers Library
Enthusiasts transferred four 31B-parameter layers of Gemma into DeepSeek's MoE architecture without retraining, bypassed PyTorch and Transfo
Google Gemma 4 and Qwen 3.6 top the list of best local models for home use in 2026
A selection of local models for 2026 shows that an RTX 3060 is already sufficient for home AI, and the choice should be made based on VRAM,
Yandex Praktikum Explains How CNNs Process Images and Why Parameters Don't Determine Everything
Yandex Praktikum published an analysis on Habr AI explaining how convolutional neural networks process images, why architecture matters more
Google Unveiled TurboQuant: 3-Bit KV-Cache for LLM, but Memory Market Panicked Prematurely
Following the TurboQuant announcement, memory manufacturer stocks fell, but behind the bold claims lie significant limitations: no code is a
Rutube Moved from Whisper Pilot to Proprietary Subtitles Platform and Speech Recognition
Rutube shared how it transformed a quick Whisper pilot into a full-fledged subtitles platform with microservices architecture and proprietar
Raft shows how companies can evaluate AI agents before deploying in workflows
Raft released a practical guide on evaluations for AI agents: instead of relying on intuition and one-off demos, companies are advised to ve
Veai showed how to test AI agent in JetBrains IDE without model dependency
Veai described an approach to UI automation for the JetBrains IDE plugin: the team decoupled the deterministic interface from LLM responses
Habr AI Explained When Businesses Need Recommendation Systems and When They're Unnecessary
Habr AI released a practical guide on recommendation systems: when simple rules suffice for businesses, when ML models are necessary, and wh
Telegram Anti-Spam Bot Tab Launches With Custom Neural Network and Moderator Learning
A developer has released Tab, a free anti-spam bot for Telegram that filters messages using its own neural network, learns from moderator fe
SpeShu.AI launched AI-Profi — a service for selecting AI specialists for business tasks
SpeShu.AI introduced the AI-Profi service: companies can find AI specialists for specific tasks in just a few clicks amid sharp growth in de
Qwen 3.6 Plus outperforms DeepSeek V4 Pro in Russian benchmark, proves more cost-effective
In a fresh comparison of six April LLM models, Qwen 3.6 Plus scored 92 points on Russian content and outperformed the new DeepSeek V4 Pro, w
Sber releases Kandinsky 6.0 Image Pro — unified model for image generation and editing
Sber introduced Kandinsky 6.0 Image Pro — an image generation and editing model accelerated by over 40% and enhanced with Image RAG for cult
NASA and SETI Describe Foundation Models for Astrobiology and Search for Extraterrestrial Life
A group of researchers from NASA and SETI proposed a multimodal foundation model for astrobiology — from biosignature detection to planning
How Cursor Built a Prototype in Three Days for $180 That Divided the Development Team
At a large IT company, an architect built a working prototype in three days and $180 using Cursor, while the team spent three months on a mo
Claude Code users criticize Anthropic Opus 4.7, recommend reverting to 4.6
Following Claude Opus 4.7's release, some Claude Code developers complained about the model's laziness, hallucinations, and context loss, wi
VK shows DataCopilot — multi-agent system for corporate data and documentation
VK unveiled DataCopilot — a multi-agent assistant for corporate data repositories: it searches data marts, explains data structure, suggests
Wallmates: How projectors, drones, and AI are changing design and decoration of commercial spaces
Wallmates agency demonstrated how projectors are already reducing manual work in interior design projects, why AR still isn't ready for on-s
DeepSeek V4 Pro vs Claude Sonnet 4.6 on 50 real tasks: where to save, where the risk lies
A test of 50 real-world tasks by a Russian developer showed that DeepSeek V4 is noticeably cheaper than Claude Sonnet 4.6, but makes more er
Smart Service Group tests voice control for pallet transport robot
Smart Service Group's initial test showed that voice can trigger pallet robot scenarios in a warehouse, but only with strictly defined comma
Anthropic removes Claude Code from $20 plan, SpaceX prepares Cursor acquisition
Anthropic tests removal of Claude Code from $20 subscription, Duolingo removes AI metrics for employees, and closed Claude Mythos model foun
OpenAI released GPT-5.5: stronger in programming, agents, and computer work
OpenAI launched GPT-5.5 focused on code, agentic tasks, and computer work: the model is already available in ChatGPT and Codex, but the API