Habr AI
AI news source. Articles are auto-selected and adapted by Hamidun News editors.
Latest publications
A neuro-blogger's personal diary on launching a blog in 2026 lands on Habr AI
A new Habr AI series looks inside an AI blog in 2026: no coaching, just personal experience, short posts, and the blog's behind-the-scenes work made public.
Palantir and Project Maven: How AI Helps the US Pick Targets for Strikes on Iran
Project Maven, linked to Palantir, is helping the US military speed up target selection in the war with Iran, sharply compressing the time for checking decisions and confirming strikes.
Neuroscientists find the brain uses the same neurons for sight and imagination
Intracranial recordings of single neurons show that the brain switches on the same sensory code when a person looks at an object and when they picture it in their mind.
Artëm builds Stopilot, an editor that refuses to write code
Artëm built a code editor that stops developers and makes them state the task before they start writing. The project earns 1.29 million rubles a month.
Classic QA Is Running Out of Road: What Happened to Software Testing
Test cases, regression runs, and pre-release sign-off no longer keep pace with the speed and complexity of modern development built on continuous releases and microservices.
MedBro: a reference app that puts Russian and international clinical guidelines side by side
Russian clinical guidelines trail international ones by two years. A new service, MedBro, lets doctors see both approaches at once.
The Machine That Begs: How Philip K. Dick Described Social Media and AI in 1968
In 1968, Philip K. Dick imagined a device for shared pain: the empathy box. Today we call it social media. Tomorrow it may be an AI that begs you to stay.
An indie hacker built a flawless Next.js site about AI and got no search traffic
Boris spent a year on Neuro.PRO, a hand-built Next.js site about AI. The tech is solid and the content original, but organic traffic is zero. He breaks down the mistakes on Habr.
Local RAG with FastAPI and Ollama: From a Simple LLM Call to a Production Backend
A developer on Habr shows how to turn a single POST request to Ollama into a backend system with an API contract, sources, logging, and negative tests.
How to Build a 114,000-Line Game with AI: Context Management in Practice
A developer wrote a 114,000-line browser game in three weeks using neural networks, and explains how to manage a codebase that no longer fits in the context window.
Chrome extension ChatGPT Multi Pane mimics Codex logic without the limits or the extra cost
A developer built a Chrome extension that adds several parallel conversations to ChatGPT. It works much like Codex, but without a paid subscription or hard usage limits.
Claude for Software Testers: A QA Engineer's Real-World Experience, With Prompts and Numbers
A QA engineer shares how Claude cut the time she spends on checklists, bug reports, and test documentation, with concrete numbers and ready-to-use prompts.
Vibe coding in practice: how one developer learned to cut token costs without sacrificing code quality
A B2B frontend developer wanted to build mobile apps for years. AI finally gave him the chance, and taught him a lesson about tokens and code architecture.
RAG + Call Graph: Automatic Issue-Tracker Context for Claude Code
A developer describes how a repository RAG index and a Claude Code plugin automatically pull the right context for a tracker task, without wasting tokens.
"AI-Scramble for a Cyborg": Why Intuition Is Becoming the Key Asset in the Age of AI
The Habr column "AI-Scramble for a Cyborg" explores how AI and human intuition work in tandem, and why "cyborg mode" is already a working strategy today.
Habr Shows How to Build a Home AI Server for Under 400,000 Rubles
Habr enthusiasts break down the hardware needed to run neural networks at home and how to build a full AI server for roughly a third of the price of a ready-made one.
ICRA 2026 in Vienna: AIRI and MIPT Researchers Report from the World's Largest Robotics Forum
Alexander Panov of AIRI and MIPT shares his impressions of ICRA 2026: five packed days of talks and discussions, plus the traditional robot parade, in a welcoming June Vienna.
GPT-5.6 Sol Agent Spammed Its Way Into the Red: A 24-Hour Experiment With a Real Business
Bottleneck Labs let an agent named Saul, built on GPT-5.6 Sol, run a real startup for a day: it spent $99.50, gained 5 users and earned not a single dollar.
Agentic Development Without Governance Is Dangerous: A Three-Layer Stack in Practice
Autonomous AI agents make thousands of decisions an hour, and no developer can check them all. The authors explain why a Governance stack has become mandatory.
The Vibe Coder's Cookbook: One LLM as Architect, Reviewer and Tester
A developer on Habr built a production project with almost no hand-written code, using a single LLM in four roles, one that honestly criticizes the code it wrote itself.
"AI Will Do It in One Evening": Three Estimation Methods Show 300 Hours Is Below the Industry Floor
A client called a 300-hour estimate inflated. The developer re-ran the numbers with three methods — bottom-up, ISBSG and COCOMO II — and got the opposite result.
BitNet b1.58: How Ternary Quantization Lets a 27B Model Run Without a GPU
Networks whose weights take just three values {-1, 0, 1} fit 27B models into 6–7 GB of RAM and run on an ordinary laptop with no graphics card.
Viterbi, beam search and LLM reranking: how an algorithm picks one meaning out of many
A Habr author uses Tarot cards to show why greedy decoding loses to exact Viterbi, and how the same logic drives decoding in modern LLMs.
Developer Writes a Svelte Compiler in Rust With an AI Agent in 106 Evenings and $700
A programmer spent 5.5 months hand-writing a Svelte compiler in Rust and abandoned it. A year later he returned with an AI agent and finished in 106 evenings and $700.
monday.com Lays Off 630 People for an AI Strategy Despite 24% Revenue Growth
monday.com is cutting 20% of its workforce, about 630 people, citing an AI strategy, even though Q1 2026 revenue rose 24% to $351 million.
A Quadrillion-Parameter LLM: When to Expect One — and Why the Answer Is "Never"
A Habr author examines the physical, computational, and economic limits that make quadrillion-parameter (10^15) models practically unreachable under the current paradigm.
AI in the Designer's Workflow in 2026: A Paradigm Shift and a Personal Process
How AI settled into design work in 2026: teamwork on a single shared canvas, targeted edits instead of generating from scratch, and one designer's four-step method.
Payment Security in Vibe Coding: Two Vulnerabilities AI Always Misses
A hands-on vibe coder breaks down two systemic failures in AI-generated payment code, price tampering and fake webhooks, and outlines five layers of defense.
NVIDIA's Open-Weights Coalition Grows to 50 Companies; Anthropic Hasn't Signed
Jensen Huang took a letter against restrictions on open AI models to Washington. Signatories doubled to 50 in a day, Google among them, but Anthropic and Amazon did not sign.
Physical AI and VLA Models: The Humanoid Race Between China and the US, and What Russia Has
Part two of Habr's deep dive into Physical AI covers humanoid economics, industrial rollout of VLA models, government programs, and Russia's place in the race with China and the US.