AllLLMRoboticsStartupsResearchEthicsBusinessHardwareAutonomousMedicineCreative
Topic hub

AI for Coding

AI is reshaping software development faster than any other profession — from Copilot autocomplete to agents like Claude Code and Cursor that write, fix and refactor whole projects. "Vibe coding" — building software through natural-language dialogue — has entered the mainstream. Here is everything on AI coding tools: releases, benchmarks (SWE-bench) and the debate over quality and productivity.

Official site ↗1804 articles
In the glossary:Coding AgentCopilotVibe CodingAI agent
Claude Code and 11 Agents: How a QA Team Automated Up to 80% of Testing Routine
LLM·Habr AI

Claude Code and 11 Agents: How a QA Team Automated Up to 80% of Testing Routine

Apr 28, 2026·3 min
International bestseller on large language models released in Russian
LLM

International bestseller on large language models released in Russian

Apr 28, 2026·2 min
Claude Code on Windows: Setting Up a Stable and Fast Development Environment
LLM

Claude Code on Windows: Setting Up a Stable and Fast Development Environment

Apr 28, 2026·2 min
Fintech group "Svoi" explains how to make LLM-agents cheaper and more accurate in code
LLM

Fintech group "Svoi" explains how to make LLM-agents cheaper and more accurate in code

Apr 28, 2026·2 min
How a Habr Author Turned Seven n8n Scenarios into an Autonomous AI News System
LLM·Habr AI

How a Habr Author Turned Seven n8n Scenarios into an Autonomous AI News System

In one and a half months, the author transformed a fragile set of seven n8n scenarios into a unified Python pipeline with 11 workers, 5 AI agents, a local LLM, and…

Apr 28, 2026·2 min
Christine Lagarde praised Anthropic for cautious release of new AI model
Ethics·Bloomberg Tech

Christine Lagarde praised Anthropic for cautious release of new AI model

ECB head Christine Lagarde supported Anthropic's decision not to open full access to the new AI model and stated that the industry needs stricter safeguards.

Apr 28, 2026·2 min
Why OpenCode and strong models write green but useless tests — and how to fix it
Autonomous·Habr AI

Why OpenCode and strong models write green but useless tests — and how to fix it

A fresh model and a powerful agent like OpenCode won't help if the codebase is filled with any-types, and the team asks AI to simply write tests without…

Apr 28, 2026·2 min
NVIDIA opened free API access to 100+ AI models with OpenAI-compatible endpoints
Hardware·Habr AI

NVIDIA opened free API access to 100+ AI models with OpenAI-compatible endpoints

NVIDIA began issuing free keys to access over 100 AI models: developers get OpenAI-compatible API, 40 requests per minute limit, and access without a credit card.

Apr 28, 2026·2 min
Top themes
01Anthropic Updates Claude Code: Routines, Parallel Sessions, and Autonomous Tasks on MacApr 28, 2026·2 min02TinyFish Launched Unified Web Platform for AI-Agents with Search, Fetch, Browser and AgentApr 28, 2026·3 min03Anthropic and the Pentagon: Why the AI Conflict Became a Warning for EuropeApr 28, 2026·3 min04Anthropic and Mythos model tested again by US agencies despite Trump banApr 28, 2026·3 min05How LLM Guardrails in Java Block Injections and Toxic ResponsesApr 28, 2026·2 min
AI Assistants in 2026: How a Solo Developer Became Faster Than a Team of Three
LLM·Habr AI

AI Assistants in 2026: How a Solo Developer Became Faster Than a Team of Three

Apr 28, 2026·2 min
Yandex Code Assistant tested on secrets handling and compared against Cursor
LLM·Habr AI

Yandex Code Assistant tested on secrets handling and compared against Cursor

Apr 28, 2026·2 min
Accel raised $5B for new bets on AI startups like Anthropic and Cursor
Startups·Bloomberg Tech

Accel raised $5B for new bets on AI startups like Anthropic and Cursor

Apr 28, 2026·3 min
Claude and Qwen Omni: How a Developer Integrated Video Analysis into a Production Pipeline
Creative·Habr AI

Claude and Qwen Omni: How a Developer Integrated Video Analysis into a Production Pipeline

Apr 28, 2026·2 min
Wayve raises $60M from AMD, Arm and Qualcomm for full self-driving stack
Robotics·TNW

Wayve raises $60M from AMD, Arm and Qualcomm for full self-driving stack

London-based Wayve received an additional $60M from AMD, Arm and Qualcomm, strengthening its self-driving platform's compatibility with nearly all major automotive…

Apr 28, 2026·3 min
Anthropic, Google and Microsoft Quietly Closed AI Agent Bugs Without CVE and Warnings
LLM·TNW

Anthropic, Google and Microsoft Quietly Closed AI Agent Bugs Without CVE and Warnings

A researcher demonstrated that AI agents from Anthropic, Google and Microsoft can be forced to publish keys and tokens through prompt injection in GitHub Actions…

Apr 28, 2026·3 min
AWS shows how speculative decoding on Trainium2 accelerates generation in vLLM
LLM·AWS Machine Learning Blog

AWS shows how speculative decoding on Trainium2 accelerates generation in vLLM

AWS explained how speculative decoding on Trainium2 and vLLM helps speed up generation in LLM services, reduce token cost, and increase throughput on long-response workloads.

Apr 28, 2026·3 min
Accel raised $5B for AI startups and intensified the race for late-stage deals
Startups·TNW

Accel raised $5B for AI startups and intensified the race for late-stage deals

Apr 28, 2026·3 min
Skild AI Acquires Zebra Technologies' Robotic Automation Division
Robotics·Bloomberg Tech

Skild AI Acquires Zebra Technologies' Robotic Automation Division

Apr 28, 2026·2 min
Google Introduced Gemini 3.1 Flash TTS — Speech Model with Control, Dialogues and 70+ Languages
LLM·MarkTechPost

Google Introduced Gemini 3.1 Flash TTS — Speech Model with Control, Dialogues and 70+ Languages

Apr 28, 2026·3 min
Anthropic Deems Mythos Too Dangerous: Model Can Compromise Core Systems
Business·Bloomberg Tech

Anthropic Deems Mythos Too Dangerous: Model Can Compromise Core Systems

Apr 28, 2026·3 min
Rufler simplifies agent swarms in Claude Code: one config instead of manual orchestration
LLM·Habr AI

Rufler simplifies agent swarms in Claude Code: one config instead of manual orchestration

Apr 28, 2026·2 min
Claude Code helped build a graph analysis app in under an hour — developer case study
LLM

Claude Code helped build a graph analysis app in under an hour — developer case study

Apr 28, 2026·2 min
SmolAgents: How to Build a Multi-Agent AI System with Code and Dynamic Orchestration
Creative

SmolAgents: How to Build a Multi-Agent AI System with Code and Dynamic Orchestration

Apr 28, 2026·2 min
Anthropic Explained How and When to Properly Start a New Session in Claude Code
LLM

Anthropic Explained How and When to Properly Start a New Session in Claude Code

Apr 28, 2026·3 min
MTS showed how OpenClaw was connected to a robot and brought an AI agent into the physical world
Robotics·Habr AI

MTS showed how OpenClaw was connected to a robot and brought an AI agent into the physical world

The MWS team demonstrated that OpenClaw can be connected to a physical robot through a simple software layer and cloud LLM without building a complex VLA system…

Apr 28, 2026·3 min
Cursor and Microsoft Research Test Whether AI Agents Need Full Debugger Access
Autonomous·Habr AI

Cursor and Microsoft Research Test Whether AI Agents Need Full Debugger Access

An experiment with Debug2Fix and Cursor Debug Mode shows that breakpoints, step-by-step execution, and expression evaluation can help AI agents fix real bugs…

Apr 28, 2026·2 min