Habr AI
AI news source. Articles are auto-selected and adapted by Hamidun News editors.
Latest publications
How Personal Data Anonymization Affects LLM Agents: Hivetrace Dataclean Experiment
The authors examined how much a banking LLM agent loses in quality after data anonymization by comparing clean requests, masks, and pseudonyms across 102 synthetic tests.
Capsules for AI-Agents: How Packaged Developer Experience Becomes Machine Knowledge
The capsule framework's author demonstrates how a capsule's rigid structure — context, constraints, and history — becomes the ideal format for an AI-agent, not just humans.
How to Run DeepSeek on Your Server: Memory, Config, and Complete Privacy
A detailed guide to installing DeepSeek on a cloud server — how much memory you need for different model variants, which tools to use, and how to get it running on the first try.
Stable Diffusion XL at Home: A Guide for Those Who Thought It Was Too Complicated
Publisher BHV has released a practical guide to Stable Diffusion XL — for those who want to generate images without subscriptions, locally and privately.
BI.ZONE Experts: AI and Deepfakes Made Phishing More Precise and Dangerous in 2026
BI.ZONE experts explained why phishing in 2026 became personalized and multi-stage, which schemes work best, and why basic security measures remain effective.
Vercel unveiled agent-browser for AI agents — lightweight browser access without MCP
Vercel released agent-browser — a Rust CLI that shows AI agents only interactive page elements and helps manage the browser with lower token costs than MCP.
Grok, Claude and Kling: how a designer can quickly prepare complex web animation for frontend
The breakdown shows how a designer can use Grok, Claude, Kling, CodePen and Spline to transform a complex web animation idea into a clear package of materials for the frontend.
Just AI automated JAICP DSL: AI agent writes patterns and tests in a minute instead of six hours
The Just AI team built an agent for JAICP DSL that generates patterns, phrase examples, and autotests in multiple languages, reducing developer routine work from six hours to a minute.
Surf explains why teams sabotage AI implementation in product development
Surf executives described five stages of AI adoption in development—from denial and anger to equilibrium—and explained why forced rollout almost always leads to sabotage.
Google NotebookLM, Canva and Gamma: 13 Conditionally Free AI Services for Presentations in 2026
A new roundup compares 13 AI services for presentations — from Google NotebookLM and Gamma to Canva and Decktopus; free access almost everywhere comes with test credits only, export limits, or watermarks.
NGT Memory Module Shows How to Give LLM Persistent Memory Without Vector Database
Open-source NGT Memory module offers persistent memory for LLM without external vector database: stores user profile, links facts, and retrieves relevant context in 2–3 ms on CPU.
agent-pool for Google AI and Gemini CLI released with pipelines, cron, and bounce-back
The agent-pool MCP-server for Google AI and Gemini CLI automates multi-agent chains: launches steps based on triggers, returns tasks for revision, and schedules them on cron.
Agentic Legal RAG Challenge 2026: How Sparks of intelligence Tested the Limits of Agentic RAG
The Sparks of intelligence team analyzed their experience in the Agentic Legal RAG Challenge 2026 and demonstrated why chunking, search, grounding, and debugging time are critical factors in legal RAG.
RooCode for VS Code: How to Set Up Multi-Agent Development Without Chaos and Unnecessary Model Requests
A detailed RooCode configuration guide shows how to split roles across modes, connect MCP servers, and gradually improve AI agent performance in VS Code without excess noise.
Yandex 360 Explained How to Teach AI Assistants to Work with Internal UI Kits
The Yandex 360 team shared how to make a frontend repository understandable to AI — and why without this, the assistant will hallucinate components.
LinkedIn and SHRM: AI Made Resumes a Weak Signal and Turned Them Into a Hiring Filter
Candidates polish resumes with AI, companies filter them with algorithms, and ultimately the value of a 'perfect' CV drops: case studies, interviews, and verifiable experience become more important.
MCP LLM-Agent in Fusion360: First Vibe-Design Test on a Wooden Staircase
Fusion360 rolled out an MCP LLM-assistant — a Habr author immediately tested it on a wooden staircase he had previously created manually over 60 times.
Claude Code Raised Legal RAG to 0.791, but ARLC 2026 Final Hit Scaling Limits
The ARLC 2026 case demonstrates how Legal RAG can be improved across 17 iterations, then lose 42% of results as the corpus scales from 30 to 303 documents.
OpenAI and Grok Lose to Custom RAG in Legal Agentic RAG Challenge
A team on Mac Studio M3 Ultra compared RAG, CAG, BM25, and built-in databases from OpenAI and Grok in a legal challenge and found: grounding, not brand names, determines the outcome.
Habr: How Outdated Knowledge Base Breaks LLM-Agents and How to Fix It
Habr explored why outdated documentation is more dangerous than its absence for LLM-agents, and proposed three practices: automated checks, document statuses, and strict update rules.
Vibe Coding Promises 10x Productivity Gains — PyPI Hasn't Confirmed It
Developers claim 10–100x acceleration thanks to AI tools, but if that's true — why doesn't PyPI show explosive growth in Python packages?
Anthropic Strengthens Claude: Why New Corporate Customers Choose It Over ChatGPT
Ramp data from March 2026 shows a shift in corporate demand: among companies purchasing AI tools for the first time, Anthropic's Claude notably outpaces OpenAI.
NotebookLM and Gemini Automate Test Creation via Google Apps Script and Forms
An author demonstrated how to integrate NotebookLM, Gemini, Google Apps Script, and Google Forms to quickly assemble educational tests from existing sources while reducing manual work.
Doka launches local AI-agent for Russia without VPN, subscription or cloud
A developer bundled a custom AI-agent into the Doka desktop app: the service runs locally, uses the Qwen3 model, and requires no cloud, VPN, or monthly fees.
Why Language Models Make Mistakes Even When They Know the Right Answer: Breaking Down LLM Limitations
TechWill researcher Valery Shabashev analyzed why LLMs can make mistakes even when they have the correct answer: the problem isn't in knowledge, but in reasoning verification.
LLM Ensemble Examined Theological Interpretations: 1 Tim. 2:15 as a Static Analysis Case
Five language models compared two interpretations of 1 Tim. 2:15 and demonstrated that an LLM ensemble can avoid seeking 'truth' while uncovering hidden assumptions and weak points in arguments.
Bootik: a console AI agent for servers that runs locally and doesn't require much memory
Bootik is a lightweight console AI agent for SSH operations: it launches on demand, understands server context, and is designed for local models with limited VRAM.
Anthropic: agentic AI and GitHub Copilot are changing development rules in 2026
In 2026, AI code tools are no longer just code suggesters: Claude Code, Copilot, and Cursor now read repositories themselves, plan changes, run tests, and fix bugs.
SkillMarket built a marketplace of skills for AI agents on FastAPI and Claude Sonnet
The SkillMarket team showed an MVP of a platform where industry experts convert their experience into sellable skills for AI agents, with FastAPI, Celery and two LLMs handling packaging and moderation.
Sber Explained Why AI-Generated Code Looks Reliable But Breaks Under Real Load
Sber analyzed why AI-generated code often appears quality in code review but fails in production, and what engineering practices help reduce this risk.