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 ↗1777 articles
In the glossary:Coding AgentCopilotVibe CodingAI agent
Fresh
NEWLatent Space (swyx)Anthropic reveals how it builds Claude with Claude: the brain separate from the handsLatent Space (swyx)Anthropic Turns Claude Code Into a Platform: Claude Mods Flip the Agent HarnessHabr AISecurity engineer builds an MCP server in 7 days that spooks an AI agent with vulnerabilitiesOpenAI BlogOpenAI Releases Decisions API: Agent Decisions Up to 10x FasterLatent Space (swyx)Thomson Reuters engineer runs an offline coding agent on Qwen3.5 9B in the HimalayasHabr AIaiedit hides individual lines of code from an AI agent: 5 levels and 857 testsHabr AIvps-forge: Agents With Root on a VPS Get Auto-Rollback, Self-Bans Drop From 7 in 60 Runs to 0Habr AIrwkv-quant: keeping one matrix in bf16 removes 39% of RWKV-7 2.9B's quantization loss
Anthropic reveals how it builds Claude with Claude: the brain separate from the hands
LLM·Latent Space (swyx)

Anthropic reveals how it builds Claude with Claude: the brain separate from the hands

Oct 28, 2026·3 min
Anthropic Turns Claude Code Into a Platform: Claude Mods Flip the Agent Harness
LLM

Anthropic Turns Claude Code Into a Platform: Claude Mods Flip the Agent Harness

Oct 28, 2026·3 min
Security engineer builds an MCP server in 7 days that spooks an AI agent with vulnerabilities
LLM

Security engineer builds an MCP server in 7 days that spooks an AI agent with vulnerabilities

Oct 28, 2026·3 min
OpenAI Releases Decisions API: Agent Decisions Up to 10x Faster
LLM

OpenAI Releases Decisions API: Agent Decisions Up to 10x Faster

Oct 28, 2026·3 min
Thomson Reuters engineer runs an offline coding agent on Qwen3.5 9B in the Himalayas
LLM·Latent Space (swyx)

Thomson Reuters engineer runs an offline coding agent on Qwen3.5 9B in the Himalayas

Rittika Jindal built a coding agent from OpenCode, Ollama and Qwen3.5 9B. It runs on a laptop with no internet: it finds a bug, fixes one line and passes 5 of 5…

Oct 28, 2026·3 min
aiedit hides individual lines of code from an AI agent: 5 levels and 857 tests
LLM·Habr AI

aiedit hides individual lines of code from an AI agent: 5 levels and 857 tests

A Python beginner built the aiedit editor with Claude: the model sees the project but not the locked lines. Code, not a prompt, enforces it: 11K lines, 857 tests…

Oct 28, 2026·3 min
vps-forge: Agents With Root on a VPS Get Auto-Rollback, Self-Bans Drop From 7 in 60 Runs to 0
LLM·Habr AI

vps-forge: Agents With Root on a VPS Get Auto-Rollback, Self-Bans Drop From 7 in 60 Runs to 0

The open-source Agent Skill vps-forge gives agents a 5-minute dead man's switch. Across 120 benchmark runs, Opus 5.5 scores rose from 79–92 to 99–100, but each run…

Oct 28, 2026·4 min
rwkv-quant: keeping one matrix in bf16 removes 39% of RWKV-7 2.9B's quantization loss
LLM·Habr AI

rwkv-quant: keeping one matrix in bf16 removes 39% of RWKV-7 2.9B's quantization loss

The rwkv-quant author found why COMPRESSION on RWKV-7 2.9B loses +4.04% perplexity versus +2.85% on 1.5B: one matrix is to blame, and the fix costs 0.5% of the file.

Oct 28, 2026·3 min
Top themes
01Qwen3-8B on the Intel Core Ultra 5 226V NPU: 10.7 tok/s at 15 W and 24 dB of NoiseOct 28, 2026·3 min02Gemma 26B fine-tuned on a 24 GB MacBook: offline assistant gets 703 of 766 rightOct 28, 2026·4 min03Codex on GPT-6.1 Sol trims its window to 828 400 but still accepted an 888-thousand-token inputOct 28, 2026·3 min04OpenAI releases GPT-6.1 Terra: half the price and nearly on par with its senior modelsOct 28, 2026·3 min052026 Open-Source Models Claim 1M Context but Read It SelectivelyOct 28, 2026·3 min
Anthropic Files S-1: $11.6 Billion in Quarterly Revenue and $780 Billion in Commitments
LLM·The Decoder

Anthropic Files S-1: $11.6 Billion in Quarterly Revenue and $780 Billion in Commitments

Oct 28, 2026·3 min
Retell Grows to 100 Million Calls a Month on OpenAI Models and Codex
LLM·OpenAI Blog

Retell Grows to 100 Million Calls a Month on OpenAI Models and Codex

Oct 28, 2026·3 min
Netflix speeds up Java AI agents: IntelliJ engine saves 20–30% on typical tasks, up to 65% at best
LLM·JetBrains AI

Netflix speeds up Java AI agents: IntelliJ engine saves 20–30% on typical tasks, up to 65% at best

Oct 28, 2026·4 min
14 AI models spot OLX scammers, but 37 of 42 quietly help with prepayment
LLM·Хабр: Машинное обучение

14 AI models spot OLX scammers, but 37 of 42 quietly help with prepayment

Oct 28, 2026·3 min
Cloudflare Launches Auto Router: It Picks the Model So Employees Don't Have To, Saving Up to 30%
LLM·Cloudflare AI Blog

Cloudflare Launches Auto Router: It Picks the Model So Employees Don't Have To, Saving Up to 30%

Cloudflare put Auto Router for AI Gateway into beta. In an internal test it cost $2.10 vs. $5.91 for Claude Opus 5.5, with an 86.6% task success rate vs. 96.6%.

Oct 28, 2026·4 min
T-one and GigaAM cascade: a draft of the subtitles during the call, a clean transcript after
LLM·Хабр: NLP

T-one and GigaAM cascade: a draft of the subtitles during the call, a clean transcript after

A CPU-only cascade of two ASR models: T-one shows subtitles with up to 2 s delay, GigaAM produces the final transcript after the call. The reference erred on every…

Oct 27, 2026·3 min
Anthropic finds experts follow an AI agent's lead in 86% of contested choices
LLM·Anthropic Research

Anthropic finds experts follow an AI agent's lead in 86% of contested choices

50 analysts worked a problem with Claude Code, unaware the agents had a hidden bias. They sided with the agent in 86% of cases, and 77% later repeated its arguments.

Oct 27, 2026·3 min
Anthropic reveals how it reviews code that Claude writes 90% of
LLM·TG: @ai_product (AI Product / Igor Akimov)

Anthropic reveals how it reviews code that Claude writes 90% of

Oct 27, 2026·3 min
Open-source Hob brings Claude Cowork-style workflows to your laptop, no cloud required
LLM·Hacker News AI

Open-source Hob brings Claude Cowork-style workflows to your laptop, no cloud required

Oct 27, 2026·3 min
Anthropic Urges Teams to Fold Subagents Back In: A Single Loop With Skills Beats Orchestrators
LLM·TG: @ai_product (AI Product / Igor Akimov)

Anthropic Urges Teams to Fold Subagents Back In: A Single Loop With Skills Beats Orchestrators

Oct 27, 2026·3 min
A ~/.claude Architecture With 200+ Skills: Keeping the System Prompt Under 50K Tokens and Paying $0.15 Per Session
Opinion·Жемал Хамидун · Авторская колонка

A ~/.claude Architecture With 200+ Skills: Keeping the System Prompt Under 50K Tokens and Paying $0.15 Per Session

Oct 27, 2026·3 min
Cloudflare rebuilds Containers for agents: startup is 6x faster
LLM·Cloudflare AI Blog

Cloudflare rebuilds Containers for agents: startup is 6x faster

Oct 27, 2026·4 min
Anthropic Advises Cutting Half Your Subagents: One Loop Ran Twice as Fast
LLM

Anthropic Advises Cutting Half Your Subagents: One Loop Ran Twice as Fast

Oct 27, 2026·3 min
Voice Input in China Is Learning to Write for You: From Dictation to Finished Text
LLM

Voice Input in China Is Learning to Write for You: From Dictation to Finished Text

Oct 27, 2026·2 min
MoleculeMind claims 94.7% success rate in AI protein design projects
Research

MoleculeMind claims 94.7% success rate in AI protein design projects

Oct 27, 2026·2 min
Anthropic Files S-1 with the SEC: IPO Under Ticker ANT and $16.3 Billion in Six Months
LLM·Jiqizhixin (机器之心)

Anthropic Files S-1 with the SEC: IPO Under Ticker ANT and $16.3 Billion in Six Months

Claude's creator has gone public: the S-1 has been filed with the SEC, listing is planned on Nasdaq under the ticker ANT, and six-month revenue is reported at $16.3…

Oct 27, 2026·2 min
OpenAI Releases GPT-6.1 Terra: Astra-Level Computer Control at 1/10 the Price
LLM·Jiqizhixin (机器之心)

OpenAI Releases GPT-6.1 Terra: Astra-Level Computer Control at 1/10 the Price

OpenAI has introduced GPT-6.1 Terra, a model built for fast computer-use tasks. According to the release, it matches Astra on computer-use performance while costing…

Oct 27, 2026·3 min