Why am I not producing AI slop? | Hacker News Reader

Why am I not producing AI slop?

3 pointsskeedle5 comments

There's lots of concern and discussion about the quality of AI models writing code. I am writing fairly ambitious code in complex codebases and I have really been seeing great results with Claude, OpenAI, gemini, etc. I don't have any particular process or magic prompts, but I have been developing software for 30 years and I use AI as if they were a developer I manage. I try to be clear on the goal of the code, context that should help, and then I don't get too picky about exactly how the code should be written. I test it and give feedback on how the code should work. Why are so many people complaining about AI slop? Is it really the shortcomings of the AI models or are they using AI wrong? There appears to be entrenchment going about whether there is AI hype or not. I'm wondering it's really almost a personal issue, like it depends on how you work with people. I generally tell myself that if I'm not getting the results I want then I need to improve how I am using the AI. And I've gotten great results. Am I alone on this?

> And I've gotten great results. Am I alone on this?

No, you're not. I'm ~25 years into programming, and I haven't been more amazed by a tech stack yet. It's amazing, it's everything we dreamed about, and if handled carefully, with curiosity and a desire to learn it's really helpful and productive.

The best thing for me personally is that it helps me start things I know I wouldn't have touched otherwise. Knowing how complex things can get is almost like writer's block sometimes. The various tools help with that, and I've started taking my various "ideas" from notes and slowly working up the PoC / MVP chain. And I'm having fun again!

Simon Wilson has a recent article where he basically makes the point that "I don't even care about the will it / will it not debate about AGI, the tech is here now, and it's useful to me". I feel the same way.

> I'm wondering it's really almost a personal issue

For a lot of people it is. The various media we consume, and especially social networks that are one-to-many have instilled this "identity everything". From politics to tech, people take it extremely personal and put their entire identity behind an idea. Another aspect is that saying "I was wrong" is seen like something beneath an "influencer", and these platforms push people into doubling and tripling down on their takes. So a person that has associated the idea of their identity being "against AI", will continue to be / pose against it over and over again.

You don't know what you don't know. See also "Dunning-Kruger"

After 30 years of software development I don't know what's slop and what's not? Hmm. I don't think that's it.

Yeah I've been in the field longer than that. Plenty of people think they can spot sludge but don't realize they are looking through sludge-covered glasses.

Your working in a field where everything is already slop: https://xkcd.com/2030/

Reply on news.ycombinator.com