A November 2026 Hacker News discussion asked developers how they use AI coding agents. Three readers categorized the 663 comments, counting individual people rather than repeated comments; 424 of 530 commenters named at least one tool. Claude Code led with 180 users, followed by Codex at 103. OpenCode and Pi each had about 70 users, while 148 people mentioned open-weight or local models, including DeepSeek, Qwen and GLM. Tool use was often mixed: 120 people named both Claude and OpenAI products, and 156 used multiple coding agents. These are self-reported counts, not a test of tool performance.
The setups reveal recurring ways to make agents more useful and safer. Developers run tasks in parallel, giving each agent a separate Git worktree, and use a fresh agent or another model to review changes before merging. Some assign planning to a stronger model and implementation to a cheaper one, escalating when work fails. Others isolate agents in virtual machines or containers, restrict network access, and protect secrets - especially when agents can run unattended. Detailed examples also stress clear specifications, tests, human review, and cleanup when parallel agents produce inconsistent code. The central case is practical rather than tool-specific: speed comes from delegating work, but reliable results depend on isolation, explicit expectations, and independent checks.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
Richard Sutton argues that brute-force computation alone cannot produce intelligence and that AI needs clever new methods. He says the science of AI is far from finished. (twitter.com)
Anthropic is accused of charging Russian Claude users before identity checks, then cutting off access after verification and retaining biometric data. Critics say account bans can affect linked GitHub projects and Russian citizens living abroad, and accuse the company of failing to answer public questions. (twitter.com)
LLM coding agents boost workplace productivity but can prevent developers from learning through hands-on problem-solving and weaken their technical skills. Developers should preserve their expertise by building projects manually, studying fundamentals, and practicing without AI tools in their own time. (ducktape.blot.im)
A fabricated Newtype interview led The Diplomat to retract its article about a Korean startup’s AI war test in Ukraine. The retraction followed a diplomatic dispute. (thediplomat.com)
Microsoft Research’s AI Frontiers group brought together about 50 researchers to develop agent systems and foundational AI advances. After the team joined Microsoft AI in September, its research-first approach clashed with leadership’s emphasis on scaling. (hunch.net)
Microsoft researcher John Langford has left the company. Microsoft’s AI Frontiers group has been declared finished. (businessexaminer.ca)
Today's best Hacker News stories, summarized and screenshotted, one email a day.