Show HN: Why write code if the LLM can just do the thing? (web app experiment)

Re:Show HN: Why write code if the LLM can just do the thing?... by myhf on Saturday November 01, 2025 @02:41PM (#45784170)

Designing a system with deterministic behavior would require the developer to think. Human-Computer Interaction experts agree that a better policy is to "Don't Make Me Think" [1]

[1] https://en.wikipedia.org/wiki/Don%27t_Make_Me_Think

[ Parent | on HN ]

Re:Show HN: Why write code if the LLM can just do the thing?... by _se on Saturday November 01, 2025 @03:09PM (#45784409)

This is such a massive misunderstanding of the book. Have you even read it? The developer needs to think so that the user doesn't have to...

[ Parent | on HN ]

Re:Show HN: Why write code if the LLM can just do the thing?... by finnborge on Saturday November 01, 2025 @04:10PM (#45784908)

My most charitable interpretation of the perceived misunderstanding is that the intent was to frame developers as "the user."

This project would be the developer tool used to produce interactive tools for end users.

More practically, it just redefines the developer's position; the developer and end-user are both "users". So the developer doesn't need to think AND the user doesn't need to think.

[ Parent | on HN ]

Re:Show HN: Why write code if the LLM can just do the thing?... by stirfish on Saturday November 01, 2025 @04:41PM (#45785140)

I interpreted it like "why don't we simply eat the orphans"? It kind of works but it's absurd, so it's funny. I didn't think about it too hard though, because I'm on a computer.

[ Parent | on HN ]

Re:Show HN: Why write code if the LLM can just do the thing?... by krapp on Saturday November 01, 2025 @02:51PM (#45784257)

That book is talking about user interaction and application design, not development.

We absolutely should want developers to think.

[ Parent | on HN ]

Re:Show HN: Why write code if the LLM can just do the thing?... by crabmusket on Saturday November 01, 2025 @05:10PM (#45785385)

As experiments like TFA become more common, the argument will shift to whether anybody should think about anything at all.

[ Parent | on HN ]

Re:Show HN: Why write code if the LLM can just do the thing?... by krapp on Sunday November 02, 2025 @04:57AM (#45789133)

What argument? I see a business model here, not an argument.

[ Parent | on HN ]

Re:Show HN: Why write code if the LLM can just do the thing?... by crabmusket on Sunday November 02, 2025 @09:33PM (#45795340)

I meant "the discourse", "the conversation we are all having", interpreting the experiment in TFA as an entry in that discourse.

[ Parent | on HN ]

Re:Show HN: Why write code if the LLM can just do the thing?... by AstroBen on Saturday November 01, 2025 @02:55PM (#45784286)

..is this an AI comment?

[ Parent | on HN ]