#slopCoding #noAI
Recently to me : "AI can help speed up your coding. Of course you have to watch it and check out what it does, there always needs to be a human in-between. You just have to know how to use it well to get good results."

Further back: "it's like having an army of interns."

So... You are expected to spend you time learning how to best use this thing to maybe, hopefully probably generate code that you need to then review and hopefully detect how it's probably subtly wrong, then fix that and simultaneously also try to convince the tool to pretty please not do that thing again, (for which it will gaslight you saying it won't, but you also know it will.)

.... OR, I can use that time to learn how to do it myself, do it and know what and how I did it, also learning how I could be wrong, but at least my meaty neuronal structure is actually capable of learning.

I hate trying to be employed in this industry now.
Can we have the blockchain days back? It would be better. Though not by a lot.

Was für eine Achterbahn der Gefühle

https://hessen.social/@AndrewRadev@hachyderm.io/116175986694881933

#vim #aislop #slopcoding #vibecoding

Warum nur einmal beim Erstellen von #aislop abkassieren, wenn man beim Bewerten noch einmal abkassieren kann? Sehr clever.

Da wird sich #microslop ärgern, dass sie extra einen kill-switch für PRs in GitHub einbauen.

https://www.golem.de/news/claude-code-ki-agenten-durchleuchten-pull-requests-2603-206278.html

#ai #noai #slopcoding

no one: …

me: so what if you gave an #LLM a training set that consisted of all #Java bytecode scraped together and then treated as though it were text, with each "word" being the opcode and subsequent operands? then it would output statistically assembled Java bytecode directly and you wouldn't need to slopcode a #programming language, you could slopcode directly for a JVM! Think of the #efficiency gains, the #productivity, and so forth.

Doesn't that make perfect sense? Quick, someone find me a slopcode enthusiast to critique my idea.