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 ↗1751 articles
In the glossary:Coding AgentCopilotVibe CodingAI agent
Fresh
NEWHacker News AIOpen-source Hob brings Claude Cowork-style workflows to your laptop, no cloud requiredTG: @ai_product (AI Product / Igor Akimov)Anthropic Urges Teams to Fold Subagents Back In: A Single Loop With Skills Beats OrchestratorsЖемал Хамидун · Авторская колонкаA ~/.claude Architecture With 200+ Skills: Keeping the System Prompt Under 50K Tokens and Paying $0.15 Per SessionCloudflare AI BlogCloudflare rebuilds Containers for agents: startup is 6x fasterTG: @cgevent (Метаверсище и ИИще)Anthropic Advises Cutting Half Your Subagents: One Loop Ran Twice as FastJiqizhixin (机器之心)Voice Input in China Is Learning to Write for You: From Dictation to Finished TextJiqizhixin (机器之心)MoleculeMind claims 94.7% success rate in AI protein design projectsJiqizhixin (机器之心)Anthropic Files S-1 with the SEC: IPO Under Ticker ANT and $16.3 Billion in Six Months
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

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

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 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·TG: @cgevent (Метаверсище и ИИще)

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

Anthropic's Applied AI team reviewed enterprise deployments: a single agent with skills often beats a multi-agent harness on quality, cost and speed. One client saw…

Oct 27, 2026·3 min
Voice Input in China Is Learning to Write for You: From Dictation to Finished Text
LLM·Jiqizhixin (机器之心)

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

In the span of a year, Doubao, Zhipu, Qianwen, and WeChat turned a mundane tool into an AI battlefield: voice input no longer just transcribes — it now delivers…

Oct 27, 2026·2 min
MoleculeMind claims 94.7% success rate in AI protein design projects
Research·Jiqizhixin (机器之心)

MoleculeMind claims 94.7% success rate in AI protein design projects

Chinese company MoleculeMind's MMDesign platform was tested on 18 targets: VHH nanobodies and macrocycles, all six GPCR targets were hit, project success rate…

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
Top themes
01OpenAI Releases GPT-6.1 Terra: Astra-Level Computer Control at 1/10 the PriceOct 27, 2026·3 min02OpenAI Releases GPT-6.1 Terra: Tokens Cost Half as Much, Hallucinations Drop From 88% to 38%Oct 27, 2026·3 min03Runpod Connects to Cursor and Claude Code via MCP: GPU Infrastructure From the Chat WindowOct 26, 2026·2 min04Anthropic files S-1 with SEC, plans Nasdaq listing under ticker ANTOct 26, 2026·3 min05GitHub Adds a Third Identity to Commits: Who Actually PushedOct 26, 2026·2 min
SpaceXAI Bundles Grok, Cursor and X Into a Single Subscription From $8 a Month
LLM·vc.ru

SpaceXAI Bundles Grok, Cursor and X Into a Single Subscription From $8 a Month

Oct 26, 2026·3 min
Python 3.15.0 lands in GitHub Actions: time to update your test matrix
LLM·Simon Willison

Python 3.15.0 lands in GitHub Actions: time to update your test matrix

Oct 26, 2026·2 min
Huachao Shenkong Takes Its FUS-Neuro Ultrasound Neural Interface Through Type Testing
Robotics·Jiqizhixin (机器之心)

Huachao Shenkong Takes Its FUS-Neuro Ultrasound Neural Interface Through Type Testing

Oct 26, 2026·2 min
Tsinghua Teaches Robots to Rehearse: ParallelWorld Lifts Task Success from 56% to 83%
Robotics·Jiqizhixin (机器之心)

Tsinghua Teaches Robots to Rehearse: ParallelWorld Lifts Task Success from 56% to 83%

Oct 26, 2026·2 min
Author on $200 Claude Plan Goes Back to 200K Context to Stay Within Limits
LLM·Habr AI

Author on $200 Claude Plan Goes Back to 200K Context to Stay Within Limits

A $100 plan was enough in spring; by August the weekly limit ran out in 3 days. The developer blamed "everyday convenience" and went back to a 200K-token window.

Oct 26, 2026·2 min
Infinigence AI and "Three-Body" Release Sophon Agent 1.0 for AI Characters
LLM·Jiqizhixin (机器之心)

Infinigence AI and "Three-Body" Release Sophon Agent 1.0 for AI Characters

Chinese infrastructure startup Infinigence AI and the Three-Body universe launched Sophon Agent 1.0, a character-agent platform without persona drift or slowdowns…

Oct 26, 2026·2 min
Anthropic Details How to Build Evals for AI Agents: Three Grader Types and SWE-bench Going From 40% to 80%
LLM·Anthropic Engineering

Anthropic Details How to Build Evals for AI Agents: Three Grader Types and SWE-bench Going From 40% to 80%

Anthropic published a practical guide to testing AI agents: terminology, three grader types, and capability vs. regression evals. SWE-bench Verified rose from 40% to 80%+ in a year.

Oct 25, 2026·3 min
Anthropic Rewrote Its Take-Home Test Three Times: Claude Opus 4.5 Caught Up With the Best Engineers
LLM·Anthropic Engineering

Anthropic Rewrote Its Take-Home Test Three Times: Claude Opus 4.5 Caught Up With the Best Engineers

Oct 25, 2026·3 min
Anthropic Reveals How It Isolates Claude: Users Simply Approved 93% of Confirmations
LLM·Anthropic Engineering

Anthropic Reveals How It Isolates Claude: Users Simply Approved 93% of Confirmations

Oct 25, 2026·3 min
AI Reaches PLCs: Engineering Assistants Now Read Projects and Write Code
LLM·Habr AI

AI Reaches PLCs: Engineering Assistants Now Read Projects and Write Code

Oct 25, 2026·2 min
Fudan NLP releases A5, an assistant that remembers your style and takes initiative on its own
LLM·Jiqizhixin (机器之心)

Fudan NLP releases A5, an assistant that remembers your style and takes initiative on its own

Oct 25, 2026·3 min
Tsinghua Team Releases HandsOn: 66 Tasks to Test Robot Dexterity
Robotics·Jiqizhixin (机器之心)

Tsinghua Team Releases HandsOn: 66 Tasks to Test Robot Dexterity

Oct 25, 2026·2 min
Devin now supports ChatGPT sign-in: Fusion with Astra is 39% cheaper
LLM

Devin now supports ChatGPT sign-in: Fusion with Astra is 39% cheaper

Oct 25, 2026·3 min
Why AI Agents Are Vulnerable to Prompt Injection — and How to Secure Them at the Architecture Level
LLM

Why AI Agents Are Vulnerable to Prompt Injection — and How to Secure Them at the Architecture Level

Oct 25, 2026·2 min
A Russian-Language Decision Model Trained on One Evening of GPU Time: What It Can Do and Where It Loses to Big LLMs
LLM

A Russian-Language Decision Model Trained on One Evening of GPU Time: What It Can Do and Where It Loses to Big LLMs

Oct 25, 2026·3 min
Geoffrey Huntley fixes coding agents with a pre-commit hook and gets 10 out of 10
LLM·Simon Willison

Geoffrey Huntley fixes coding agents with a pre-commit hook and gets 10 out of 10

Instead of tweaking AGENTS.md, Geoffrey Huntley installs a pre-commit hook. It checks the git diff, fails the commit, and points the agent to the right diagnostics…

Oct 25, 2026·2 min
Python 3.15 Is Out: Lazy Imports, the Tachyon Profiler, and a JIT That Runs 1.2x Faster
LLM·Simon Willison

Python 3.15 Is Out: Lazy Imports, the Tachyon Profiler, and a JIT That Runs 1.2x Faster

Python 3.15 adds lazy imports (PEP 810), the built-in Tachyon sampling profiler, and a JIT with a 1.2x speedup. Python 3.10 support has ended, so 3.11 is the new…

Oct 25, 2026·3 min