I picked Task Manager 'to see how ready AI is for primetime… or if it would just degrade to slop' – OG dev talks to The Reg
- ID
- 17226
- Status
- summarized
- Published
- 24 Aug 2026, 9:03 PM
- Fetched
- 24 Aug 2026, 9:53 PM
- Provider
- The Register
- Category
- technology
- Original URL
- https://www.theregister.com/applications/2026/08/24/i-picked-task-manager-to-see-how-ready-ai-is-for-primetime-or-if-it-would-just-degrade-to-slop-og-dev-talks-to-the-reg/5291639
- Source URL
- https://www.theregister.com/headlines.atom
Summary
- Score
- 7.5
- Created
- 24 Aug 2026, 9:54 PM
- Tags
- Audience
- developersvibe_codersai_agent_users
What happened
Dave Plummer, original author of the 1996 Windows Task Manager, rebuilt it as a cross-platform app for Windows, Mac, and Linux using AI-assisted 'vibe coding' via Fable, starting from a 107-page specification that produced a first iteration in 3.5 hours. He chose native UI code (Swift, Direct2D/DirectComposition, Qt) over Electron for game-like responsiveness, and described the AI as 'a very ambitious and precocious intern' where results depend heavily on what you ask for and how you test it.
Why it matters
The concrete lesson is that a 107-page spec fed to an AI tool produced a working cross-platform app in 3.5 hours, but the AI 'balked' at security-adjacent work and quality depended on instrumentation and testing. If you're vibe-coding real products, invest in a detailed spec and expect to manage the AI like an intern, not a black box. The native-UI-over-Electron choice is also a signal for anyone building performance-sensitive desktop tools.
Discussion angle
What does the 107-page-spec approach tell us about the right level of detail for prompting AI to build production software, and when does native UI code justify the extra work over Electron for AI-generated apps?