Skip to content

Search stories, models, companies…Subscribe

Topic · Concept

Coding agents

Coding agents are AI systems that take a software task, such as fixing a bug or adding a feature, and carry it out over many steps: reading code, editing files, running commands and tests, and returning a change for review. This page covers how they work, how they are measured and where they fail.

51 stories · updated Oct 16

Follow via RSS Get Coding agents alerts

Key facts

Checked Oct 9

Canonical agent vs workflow definition: Anthropic, "Building effective agents," December 19, 2024
Original benchmark: SWE-bench: 2,294 GitHub issues, 12 Python repos (arXiv 2310.06770, Oct 10, 2023)
SWE-bench Verified: OpenAI stopped evaluating on it (Feb 23, 2026), citing flawed tasks and contamination; recommends SWE-bench Pro
Claude Code default mode: Auto mode is the built-in starting permission mode for interactive terminal and VS Code sessions from v2.1.283
GitHub naming: "Copilot cloud agent" (formerly Copilot coding agent)
Example products: Claude Code (GA May 22, 2025), Codex (cloud agent May 16, 2025), Cursor, GitHub Copilot
Shared instruction format: AGENTS.md, a founding project of the Agentic AI Foundation (Dec 9, 2025)

Latest on Coding agents

Developers · NewsGitHub Agentic Autofix and AI Scan are generally available: what they do, who gets them and how they use AI CreditsOn October 15, 2026, GitHub made agentic autofix for code scanning alerts and AI Scan for pull requests generally available. Here's what each does, which plans and repositories qualify, how they draw Code Security AI Credits, and how to turn them on.Oct 16·5 min read

Developers · NewsOpenCode 2.0: one background service for terminal, web and desktop, plus background subagents. What it changes for securityOpenCode 2.0 runs the open-source coding agent as a single shared background service that its terminal, web and desktop clients all connect to, and adds background subagents and async shell commands. Hacker News commenters say the new model broke their sandboxes; OpenCode's docs say shell commands run with your full user authority.Oct 16·6 min read

Developers · NewsAnthropic Scion: the in-house source control system that replaced Git for its monorepo (and why it isn't open source)On October 13, 2026, Anthropic described Scion, a version control system it built to replace Git for its monorepo after daily merges grew from about 2,500 in May to more than 30,000 in September. Despite some reports, Scion isn't open source: Anthropic says it isn't a general replacement for Git and is sharing the ideas instead.Oct 14·6 min read

Developers · NewsLinus Torvalds used Claude Code to draft a Linux kernel page cache speedup: what it does and what Claude wroteOn October 10, 2026, Linus Torvalds published an experimental eight-patch Linux kernel series that lets many threads read the same cached file without fighting over one counter. He says Claude Code wrote the code, tests and first draft of the description under his direction, and measurements on his laptop show about 3x throughput in one narrow test.Oct 14·5 min read

Models · NewsMeta Muse Wonder and Muse Wonder Full: price, availability and what Artificial Analysis foundMeta released Muse Wonder and Muse Wonder Full on October 12, 2026. Muse Wonder costs $4/$20 per million tokens on Meta's API; Wonder Full is only in paid Muse Code plans. Artificial Analysis scores them 52 and 56 on its Intelligence Index.Oct 14·5 min read

Agents · NewsThe Week in AI #3: Claude Haiku 5.5, GPT-6 for everyone in ChatGPT, and Anthropic pulls its agents off the open internetOctober 5–11, 2026: a $0.10 Claude model with a 1M context, GPT-6 reaches free ChatGPT users, Google's Gemini agent, Anthropic's evaluation incidents and an Ollama-hunting botnet.Oct 13·7 min read

Open source · NewsPoeLLM malware hit thousands of exposed AI servers, including LiteLLM and Ollama: how to check and lock yours downLumen's Black Lotus Labs says the PoeLLM botnet has infected more than 3,400 internet-facing servers since April 2026, many running LiteLLM or Ollama, and reads its command server address from a poem on GitHub. What happened, and how to check and secure your own AI server.Oct 13·5 min read

Agents · ExplainerPrompt injection explained: why AI agents that read web pages, email and documents can be hijacked, and which defenses workPrompt injection lets text an AI agent reads, such as a web page, an email or a README, override what you asked it to do. Why models can't reliably tell instructions from data, the incidents that prove it, and the defenses OWASP, NIST, Google DeepMind, Anthropic and OpenAI say actually reduce the risk.Oct 13·8 min read

Agents · ExplainerOpenAI dots explained: who gets ChatGPT's always-on agents, what they can do and how to control themDots are always-on ChatGPT agents with their own cloud computer, launched on September 29, 2026 for Pro and Business Premium. Who can get one, what it can do, the controls, the privacy rules and how dots differ from ChatGPT Work.Oct 13·8 min read

Developers · ExplainerSign in with ChatGPT explained: using your Plus or Pro plan in Devin, Notion, Vercel and other appsSince September 29, 2026, Sign in with ChatGPT lets Plus and Pro subscribers spend their plan's usage in 16 partner tools, including Devin, Notion, Vercel and Warp. How identity sign-in differs from plan usage, what's shared, the limits you can set, and how developers integrate it.Oct 13·7 min read

Nothing in this format on this page — try another filter or the next page.