AI for coding: how Ghostty built its auto-updates
Ghostty creator Mitchell Hashimoto explained how AI helped him build the auto-update feature for his terminal. This isn't hype. It's a real-world look at nontrivial AI coding and how agentic tools handled the task in production.
AI-processed from Habr AI; edited by Hamidun News
Mitchell Hashimoto used AI coding tools to build the automatic update feature for Ghostty on macOS. It's a real-world example of how AI tools work in production: they assist the developer rather than fully automating the job.
How do you use AI for coding in real projects?
The Ghostty case shows that AI assistants can help build nontrivial features such as background updates, but they still need an engineer to steer and supervise them.
- Nov 2, 2026LLM Agent Built a Gearbox in KOMPAS-3D, but Scored Only 50 out of 100 on the Specification
- Nov 2, 2026Agents ignored the prompt to read memory in 7 of 7 sessions: an analysis of 13 thousand logs
- Nov 2, 2026Karpathy Built HackerTube, a Catalog of 6,454 Videos, in Two Hours with Claude Code
- Nov 2, 2026We Audited 929 Automations at Alpina: What Corporate AI Training Should Look Like in 2026
Test Frontier LLMs & Autonomous Agents in One Workspace
Run Claude Opus 5.5, GPT-6, Gemini 3.1, and DeepSeek side-by-side in Nomad AI (nomadnet.ai) — unified model routing, deep research, and multimodal workflows under one subscription.
The AI world, distilled — once a week
Seven stories that actually mattered, hand-picked. No noise, no reposts, no press releases.
Done! Check your inbox for a confirmation.