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 ↗1742 articles
In the glossary:Coding AgentCopilotVibe CodingAI agent
Ant Shuke Releases LingDT-Decision-1.0: 4B and 27B Models for Fast Decisions
LLM·Jiqizhixin (机器之心)

Ant Shuke Releases LingDT-Decision-1.0: 4B and 27B Models for Fast Decisions

Oct 22, 2026·3 min
Cognition opens London office as UK team grows 200% in six months
LLM

Cognition opens London office as UK team grows 200% in six months

Oct 22, 2026·3 min
8B-Parameter Model Beats Claude Opus 4.8 at Generating Scientific Ideas
LLM

8B-Parameter Model Beats Claude Opus 4.8 at Generating Scientific Ideas

Oct 22, 2026·2 min
Librarian Agents: LLMs Pre-Build the Workspace and Gain 33 Points on BrowseComp-Plus
LLM

Librarian Agents: LLMs Pre-Build the Workspace and Gain 33 Points on BrowseComp-Plus

Oct 22, 2026·2 min
Vercel launches BYOC on AWS and an agent authorization beta as AI token usage quadruples
LLM·Vercel Blog

Vercel launches BYOC on AWS and an agent authorization beta as AI token usage quadruples

Vercel made BYOC on AWS generally available and opened a beta of Enterprise-Managed Authorization. Enterprise token spend on AI Gateway grew 4x in three months.

Oct 22, 2026·3 min
Lovable launches Deploy on Azure: your apps and data live in your own subscription
LLM·Lovable Blog

Lovable launches Deploy on Azure: your apps and data live in your own subscription

Lovable opened a private preview of Deploy on Azure: apps, database and logs run in the customer's subscription on AKS and PostgreSQL, while the editor and agent…

Oct 22, 2026·3 min
DeepSeek releases V4.1-Flash-1017 and opens its Search API at $0.75 per 1000 calls
LLM·DeepSeek Blog

DeepSeek releases V4.1-Flash-1017 and opens its Search API at $0.75 per 1000 calls

DeepSeek's updated Flash model, V4.1-Flash-1017, finishes tasks faster, writes shorter answers and is open source. Search and Fetch APIs cost $0.75 per 1000 calls.

Oct 22, 2026·2 min
Anthropic Hands Agent Skills Standard to AAIF: 1 Million Skills, 280 Million Installs
LLM·Anthropic Blog

Anthropic Hands Agent Skills Standard to AAIF: 1 Million Skills, 280 Million Installs

Anthropic gave the Linux Foundation the Agent Skills standard, along with its name, logo and domain. Since December 2025, more than 70 platforms have adopted it…

Oct 22, 2026·3 min
Top themes
01Cognition releases agent plugin to fix PHP and Node.js holes, including a CVSS 9.2 flawOct 22, 2026·3 min02PaperFormalizer Turns LaTeX Papers into Verified Lean Code, with the Author in the LoopOct 22, 2026·2 min03RSIGame: a 27B model combo plays its own games and outperforms GPT-5.5Oct 21, 2026·2 min04S-Agent 2.0 teaches a coding agent to understand 3D and beats SpatialClaw by 7.8 pointsOct 21, 2026·2 min05Lafa, an 8B-parameter model, speeds up text generation by 2.54x without sacrificing qualityOct 21, 2026·2 min
Vercel Releases durable-harness for Fault-Tolerant AI Agent Execution in the Cloud
LLM·Vercel Blog

Vercel Releases durable-harness for Fault-Tolerant AI Agent Execution in the Cloud

Oct 21, 2026·2 min
USTC Releases "Machine Scientist 2.2": AI Moves From Running Experiments to Creating Substances
LLM·Jiqizhixin (机器之心)

USTC Releases "Machine Scientist 2.2": AI Moves From Running Experiments to Creating Substances

Oct 19, 2026·3 min
What the Claude Code leak revealed about the future of Anthropic's AI agents
LLM·Habr AI

What the Claude Code leak revealed about the future of Anthropic's AI agents

Oct 19, 2026·2 min
OpenVLHarness Gives Multimodal Models Memory and Tools: +9.7–12.6 Points
LLM·Hugging Face Daily Papers

OpenVLHarness Gives Multimodal Models Memory and Tools: +9.7–12.6 Points

Oct 19, 2026·2 min
Why Microsoft, OpenAI, and Anthropic Are Telling You Not to Trust Their Own AI
LLM·Habr AI

Why Microsoft, OpenAI, and Anthropic Are Telling You Not to Trust Their Own AI

Microsoft's Terms of Service declares Copilot pure entertainment, OpenAI demands a human check every output, Anthropic caps its liability at £100. Tech giants are…

Oct 18, 2026·2 min
Reasoning Drift in AI: How a Model Degrades While the Service Keeps Running
LLM·Habr AI

Reasoning Drift in AI: How a Model Degrades While the Service Keeps Running

Commercial AI models like Claude can quietly lose quality without ever breaking the service itself. Reasoning drift — a decline in the ability to handle multi-step…

Oct 18, 2026·5 min
Claude Mythos Is Big Tech-Only, CaveMan Cuts Token Spend Threefold
LLM·Habr AI

Claude Mythos Is Big Tech-Only, CaveMan Cuts Token Spend Threefold

Anthropic has restricted Claude Mythos to the Project Glowswing consortium (AWS, Google, Microsoft, Nvidia, Cisco, Apple). The model hits 77.8% on SWE-bench Pro versus 53.4% for Opus and has already s

Oct 18, 2026·2 min
OpenAI Opens Cyber Model to Thousands of Security Professionals Amid Rivalry With Anthropic
LLM·TNW

OpenAI Opens Cyber Model to Thousands of Security Professionals Amid Rivalry With Anthropic

Oct 18, 2026·3 min
KodaCode rolls out agent control via Telegram and voice input
LLM·Habr AI

KodaCode rolls out agent control via Telegram and voice input

Oct 18, 2026·2 min
Hidden Details of Claude Opus 4.7: Trade-Offs, Tokenization and a New Personality
LLM·Habr AI

Hidden Details of Claude Opus 4.7: Trade-Offs, Tokenization and a New Personality

Oct 18, 2026·3 min
ID Verification Comes to AI: Anthropic Introduces Identity Checks for Claude
LLM·3DNews AI

ID Verification Comes to AI: Anthropic Introduces Identity Checks for Claude

Oct 18, 2026·2 min
Automating Code Review: How Neural Networks Are Taking Over Developer Grunt Work
LLM·Habr AI

Automating Code Review: How Neural Networks Are Taking Over Developer Grunt Work

Oct 18, 2026·2 min
GitHub Freezes Copilot Sign-Ups as AI Agents Break the Economics of Flat-Rate Pricing
LLM

GitHub Freezes Copilot Sign-Ups as AI Agents Break the Economics of Flat-Rate Pricing

Oct 18, 2026·1 min
LLM as Decoder in ASR: Adapting Nvidia's SALM Architecture for Russian-Language Telephony
LLM

LLM as Decoder in ASR: Adapting Nvidia's SALM Architecture for Russian-Language Telephony

Oct 18, 2026·2 min
Moonshot releases Kimi K2.5: a swarm of 100 subagents and 1500 tool calls
LLM

Moonshot releases Kimi K2.5: a swarm of 100 subagents and 1500 tool calls

Oct 17, 2026·3 min
Groq hands LPU distribution in the Middle East to Saudi-based Aljammaz Technologies
LLM·Groq Blog

Groq hands LPU distribution in the Middle East to Saudi-based Aljammaz Technologies

Groq signed a distribution deal with Aljammaz Technologies: GroqCloud and GroqRack will go to market through a network of integrators and resellers across MENA.

Oct 17, 2026·2 min
Groq signs MOU with US Department of Energy on inference for the Genesis Mission
LLM·Groq Blog

Groq signs MOU with US Department of Energy on inference for the Genesis Mission

Groq and the US Department of Energy agreed to explore LPU inference for science and energy efficiency under the Genesis Mission. The document sets no funding or…

Oct 17, 2026·2 min