Habr AI
AI news source. Articles are auto-selected and adapted by Hamidun News editors.
Latest publications
"Advanced Payment Solutions" Launched Voice AI Assistant for Calls to Pilot Without ML Team
"Advanced Payment Solutions" brought a voice AI assistant for calls to pilot in six months, despite assembling the team from 12 backend developers with no ML experience.
Habr Explained How to Force LLMs to Calculate Without Errors Through Python Code Generation
Habr analyzed why language models regularly make arithmetic mistakes and demonstrated a working approach: LLM writes Python code, while the program handles calculations and generates Excel reports.
Paperclip Promises a Company of AI Agents but Drowns in Bureaucracy During Testing
A Habr author tested Paperclip — a system for managing teams of AI agents — and instead of accelerating development, got two days of coordination, delays, and rollbacks.
Krok Shows How It Built an Internal RAG Assistant for Corporate Data
Krok explained how it assembled an internal RAG assistant for searching corporate data with on-prem deployment, ACL control, quality benchmarks, and vendor platform customization.
Sergey Smirnov explained how to prepare an AI agent for reliable operation in production
AI engineer Sergey Smirnov outlined a roadmap for deploying an AI agent to production: from concept and initial launch to reliable, predictable operation for real users.
Google NotebookLM Helps Build a Personal AI Prompt Engineer in 15 Minutes
Instead of endless prompting courses, the author proposes creating a personal assistant in Google NotebookLM that answers only based on selected sources and doesn't make up parameters.
Microsoft GraphRAG and Ollama: How Graph-Based RAG Performed on Local Models
The author tested Microsoft GraphRAG with Ollama on the "Johnny Mnemonic" narrative and concluded: graph-based RAG delivers more relevant answers, but demands significant resources and manual configuration.
Habr AI Breaks Down Gradient Descent in C++ and CUDA Through MNIST Model Training
In the fourth part of the 'From MNIST to Transformer' series, Habr AI explains how gradient descent works and demonstrates training a digit recognition model in C++ and CUDA without PyTorch.
Google Turns Gemini Into Smartphone Infrastructure as Apple Steps Back From Siri
Google through Gemini claims the foundational AI layer role for both iPhone and Android simultaneously, while Apple effectively acknowledges that Siri in its current architecture cannot support the new era of mobile agen
Claude AI in Four IDEs: Why the Developer Became the Main Bottleneck for Agents
A Habr AI author described how working with Claude AI and multiple IDEs accelerates development, but makes the human the main bottleneck: they switch context, control agents, and ultimately lose time and sleep.
EU AI Act and EU Sanctions Intensify Pressure on Russian SaaS Companies in Europe
The EU and Russia are almost simultaneously moving AI regulation into a practical phase, and for Russian SaaS companies this becomes a double compliance barrier on top of already existing sanctions.
"First Form" showed how to maintain a company map so AI doesn't make mistakes
"First Form" demonstrated why corporate AI systems start confidently making errors if the data map isn't updated, and how to solve this with two loops—automatic and expert.
Veai 5.7 for JetBrains IDE adds directories to chat and auto-retry for agent tasks
Veai updated its AI agent for JetBrains IDE: version 5.7 brings directories to chat, model selection directly in the dialog, auto-retry, and a less intrusive terminal.
Habr AI: METR and Google Cloud See No Promised Developer Acceleration from AI
Habr AI compiled findings from several studies: AI assistants make developer work more comfortable, but data from METR, Google Cloud, and PyPI analysis do not yet confirm productivity growth.
KodaCode 0.8.0 adds secure chat mode, dialog branching, and image support
KodaCode 0.8.0 migrates chat to secure agent logic with read-only tools, adds session branching, JSON export, and image uploads for multimodal models.
SberDevices and ruGPT-3 XL: Developer Restores Forgotten Russian-Language Model from 2021
Developer brought back ai-forever/rugpt3xl — a Russian-language SberDevices model with 1.3 billion parameters, created in 2021 and trained from scratch for text continuation.
Habr AI Shows How to Build an SEO System for a Niche and Prepare Your Site for AI Search
Habr AI analyzed why LLMs don't replace SEO strategy: you must first design demand, clusters, and page types, then launch content generation.
Albumentations explained how to systematically select augmentations for computer vision models
Albumentations released a practical guide on selecting augmentations: don't gather them randomly, but test them as hypotheses about data, transformation strength, and label invariance.
MiniMax Replaces Claude API: AI Agent Costs Cut from $200 to $20
Developer migrated social media AI agent from Claude API to MiniMax and Kimi, cutting monthly model costs from $200+ to approximately $20 with no noticeable quality loss.
Habr AI Compared Claude, Gemini, and ChatGPT on Text, Math, Analysis, and Creativity
Habr AI compared ChatGPT-5.4, Claude Opus 4.6, and Gemini 3.1 Pro not on standard demos, but on unconventional tasks involving text, mathematics, analysis, and creativity.
Qdrant and DRAG with KNEE: How to Make RAG Adaptive and Avoid Wasting Extra Tokens
The author proposes DRAG with KNEE — an adaptive RAG approach based on Qdrant and Python that builds a document hierarchy and removes unnecessary context without fixed top_k.
Why the Pentagon-Anthropic conflict became a warning sign for AI business
The dispute between the US Department of Defense and Anthropic over model usage restrictions revealed a new corporate risk: AI strategy dependence on a single vendor's rules and policies.
How to Write Prompts for Midjourney, DALL-E, and Kandinsky to Get Precise Images
We break down why vague requests break image generation and how prompt structure, word weights, negative instructions, and settings deliver more predictable results.
OpenAI and Sam Altman: how the board crisis became a power struggle
The article connects Sam Altman's firing and return, questions about the Startup Fund, and a controversial Pentagon contract into one story about power and control.
Habr AI: LLMs Can Take Over Routine in Business Research—But Not Strategy
A Habr AI author divides product and marketing research into three levels, arguing that LLMs will quickly automate routine tasks and part of the analytics, but not the restructuring of the research framework itself.
DeepMind and Yann LeCun Push AGI Toward World Models — Why This Concerns More Than LLMs
The author links the path to AGI not with LLM growth, but with world models: if AI learns to understand the physics of the world and gains a "body," its decisions could become more efficient and less predictable.
OpenClaw deployed on Wiren Board: how an AI agent controls the controller and writes scripts
A Wiren Board engineer deployed OpenClaw directly on the controller, connected Telegram, trained the agent to work with Modbus, and tested whether it could write rules and collect sensor readings.
Who's Behind Claude: How Former OpenAI Employees Built Anthropic's Team
Anthropic grew out of a team of former OpenAI employees, and Claude's success is driven not only by Dario and Daniela Amodei, but also by researchers shaping the model's character and safety.
ChatGPT Helped Design a Controller for a 32-Juice Vending Machine
The author on Habr demonstrated a conversation with ChatGPT where the model clarifies requirements and builds a controller architecture for a juice vending machine — from NFC and LTE to pumps and display.
"First Form" Implemented MCP to Configure BPM Processes via AI Agent
Russian BPM platform "First Form" implemented support for Model Context Protocol: now categories, forms, and business processes can be configured through dialogue with an AI agent.