Habr AI
AI news source. Articles are auto-selected and adapted by Hamidun News editors.
Latest publications
Writers Protest Against AI, but Already Benefit From It — Column on Habr
The author of a Habr column describes a paradox: writers, who protest loudest against AI, turn out to be almost the only profession already benefiting from the technology.
ITMO Expert Ilya Blagorodov: AI Does Not Remove Developer Responsibility for Code
Developer with 30 years of experience and ITMO master's program expert Ilya Blagorodov explains on Habr why AI tools do not free programmers from responsibility for their code.
Business is leaving ChatGPT for cheaper Chinese AI models for savings, Microsoft saves with software
In June 2026, companies began massively switching from branded models like OpenAI to cheaper Chinese alternatives, while Microsoft is betting on deep AI integration into its software.
Developer creates Python job aggregator combining HH, Habr Career, and GeekJob
An open-source Python job aggregator was published on Habr: collects job posts from HH, Habr Career, GeekJob, and Telegram channels, removes duplicates, and sends selections to Telegram.
Popolama — New Service for Tracking Shared Expenses in Travel and Groups
A team of developers turned an inconvenient shared trip to Japan into the service Popolama — it automatically calculates who owes whom after group travel expenses.
How a Habr author created an AI assistant on Hermes Agent for family and support in Telegram
A Habr author shared how he set up a group chat in Telegram with his wife and AI agent Hermes Agent — and his wife started adding features to the project via voice messages.
INFERA AI.Firewall and Agent Runtime Security approach for protecting business AI agents
In 2025–2026, companies are widely transitioning to autonomous AI agents, and traditional WAF, DLP, and LLM Firewall are no longer sufficient — thus Agent Runtime Security is emerging.
Habr author warns: thoughtless AI use leads to specialist degradation
A Habr author discusses how thoughtless use of AI without critical analysis of results can lead to gradual loss of professional expertise.
Diasoft Explained Why It Chose Digital Q.Integration Platform over Traditional ESB
Diasoft Explained Why It Created Digital Q.Integration Integration Platform with Independent Microservice Connectors and a Common Transport Layer Rather than Another ESB
AI Warehouse Agent in Jamix Gained Write Access: Security and Audit
Jamix Developers Gave the Spring AI-based Warehouse Agent Permission to Modify Data and Discussed Security, Audit of Model Actions, and Transactions
HashiCorp Released Terraform MCP Server 1.0 — an AI Bridge to Terraform Registry
HashiCorp Moved Terraform MCP Server to GA: the Server Connects LLM Agents with Terraform Registry so AI Writes Current HCL Configurations Rather than Based on Outdated Data
How to Deploy AI Agents in Legacy Code to Avoid Silent Regressions in Production
Habr Translated a Guide on Deploying AI Agents in Legacy Systems: Testing, Documentation, and Compromise Boundaries to Prevent Agents from Reverting Refactoring by Thousands of Lines
Robot Economics: Why Surgical Machines Pay Off, but Fruit Pickers Don't Yet
An analytical essay on Habr explains why a robot's cost-effectiveness depends not on wage savings but on the value threshold set by the buyer.
MTS AI Discussed on Habr How Training Methods for Luna Line CV Segmentation Models are Changing
MTS AI published the second part of their Habr analysis on finding the optimal recipe for training Luna Line CV models — this time focusing on segmentation rather than classification.
AI Agents in Production: Six Architectural Errors That Prevent Them From Reaching Launch
A Habr analysis explains why AI agents that work reliably in demos produce empty responses, get stuck in loops, and lose context in production.
Solo Developer Sunarius: AI Didn't Make the RPG for Him, but Lowered the Entry Barrier
The developer has been solo-developing a post-apocalyptic RPG called Sunarius for three years and explains how AI models lowered the entry barrier for such a large-scale project.
Synthetic Customers: PwC and Bain on a New E-commerce Tool
Synthetic customers are AI models that simulate real customer reactions and help e-commerce companies test prices, ads, and products before market launch, according to Bain and PwC.
Midjourney vs Nano Banana Pro vs FLUX 2 Max: Comparing Image Generation AI Models in 2026
Habr compared six image generation AI models — Midjourney v7, Qwen Image 2 Pro, FLUX 2 Max, Nano Banana Pro, GPT Image 2, and Grok Imagine — on identical prompts.
AI code generation quietly erases architectural understanding in development teams
A Habr author explains why massive use of AI for code generation leads to no one in the team understanding the system architecture as a whole after a couple of years.
PWN AI expert Artyom Semenov: how AI agents delete files and compromise themselves
PWN AI Telegram channel author Artyom Semenov told Habr how the attack surface on AI agents and MCP protocols has grown and why system prompts are not a security boundary.
An AI agent is an LLM in a loop in 20 lines of code: where complexity begins
A Habr author explains how a real AI agent differs from a prompt and chatbot, showing that at the core of an agent is an LLM in a loop just 20 lines of code.
How agentic AI is reshaping team structures: analyzing AWS talks and thousands of publications
A Habr author analyzed thousands of publications on how top companies are reorganizing teams and org structure around agentic AI following AWS's keynote.
Developer replaced repeated context explanation for neural network with LLM Wiki workflow
Habr author described LLM Wiki workflow: the model not only answers questions about documents but gradually builds a knowledge base in Obsidian through Codex.
AGIMA held a corporate AI hackathon in support of RUNIT sports festival
AGIMA employees spent a whole month developing online games at a corporate AI hackathon timed to the RUNIT festival, which took place on July 5, 2026.
Minister of Science Valery Falkov: AI devalues student thesis work
Minister of Science and Higher Education Valery Falkov stated that due to AI development, coursework and thesis work no longer reflect the actual level of student preparation.
Kontur engineer compared D&D wizards and warlocks to the LLM era on Habr
Kontur's senior QA engineer Alexander Ovchinnikov published an essay on Habr where the shift from wizards to warlocks in D&D is a metaphor for how LLMs are changing professionals' work.
Engineer built a local RAG service for CAD API documentation on Habr
Habr describes a local RAG service for CAD API documentation — a way to automate routine design operations without transmitting data to external cloud services.
Same LLM Benchmark Yielded 28% and 76% — Difference Is Only in How Questions Are Asked
On an LLM benchmark for corporate documents, the same model showed 28% to 76% — the variation is explained by how the queries are formulated, not by the model choice.
How Context Engineering Makes Weak Local LLM a Reliable Agent
Author on Habr showed: for local LLM on closed loop, agent quality is determined not by model size but by how its context is structured.
AlpinaGPT Implemented Multi-Agent System Evolver and Cut Code Review to 15 Minutes
CTO Sergey Andriyanov explained how the multi-agent Evolver system accelerated code review from two days to fifteen minutes and freed up about 100 hours of team work per month.