Hacker News Reader

Comment by deanc | Hacker News Reader

That's exactly my point. This is at best a toy application driven by a prompt that many people will be able to extract and recreate. Putting the pieces together is easy and letting someone talk to an AI is not a particularly difficult problem. Creating magic and making people come back to learn the language is entirely different and I don't see anything magical here.

View on HN

> Putting the pieces together is easy and letting someone talk to an AI is not a particularly difficult problem

Exactly! Not difficult, right? Making and selling a product out of it is called marketing. It is not rocket science, but many engineers can't grasp it.

GPT Wrappers are the new CRUD. There is no innovation in Trello, Jira and any other SaaS, they are just marketed products that thousands of people here in HN could code better, but they don't, because they are wasting their time pointing that other people's products are not a difficult problem to solve.

Be honest though, what’s the difference between this and a good system prompt in Claude to be a language tutor?

I worked for an Edtech startup before that had a novel approach to mastery (as opposed to Anki) and it’s not something you can put in a prompt.

a prompt doesn't market itself. The difference is small but one person can sell the wrapper but can't sell the Claude as language tutor. People will hustle.

I think you're missing the point entirely. Yes, it's easy to reproduce 5% of the effort. But it doesn't make sense to call the whole 100% of the effort a toy application. Given market pressure, and if it was the case, we'd be flooded with applications like that. Being the master of 5% of the effort doesn't amount to much, and dismissing the other 95% as a toy when it requires a lot more work and as much expertise throughout doesn't make much sense. Drawing an airplane doesn't make it fly.

Reply on news.ycombinator.com