A two-week experiment building an app with full AI assistance, exploring both the promise and frustrations of LLM-based development workflows.

Hacker News is a community-driven platform for sharing and discussing technology news, startups, and programming-related topics. Through user submissions and comments, Hacker News offers insights into emerging technology trends, industry developments, and entrepreneurial ventures. Readers can participate in discussions, share their insights, and stay informed about the latest advancements in technology and innovation.

Hacker News

A development team conducted a two-week experiment building an app using full AI assistance with Claude Code, but encountered significant challenges including lack of context awareness, poor code maintainability, workflow disruption, API hallucinations, and the 80/20 problem where AI handled basic tasks well but struggled with edge cases. Despite the frustrations, they continue using AI selectively for search, rubber ducking, code snippets, testing, and language tasks while maintaining control over the development process.

To AI or not to AI

I lack a bit of context (maybe it’s there and I missed it). The different Claude price levels provide very different experience. And from what I’m reading, it seems they used the cheapest one (that I use too). And yes, there are issues with it.
In general, Vibe coding is not a panacea. But it’s not that bag either… My experience with it it is much better that described.