>what if the LLM gets something wrong that the operator (a junior dev perhaps) doesn't even know it's wrong?
the same thing that always happens if a dev gets something wrong without even knowing it's wrong - either code review/QA catches it, or the user does, and a ticket is created
>if it fails here, it will fail with other things, in not such obvious ways.
is infallibility a realistic expectation of a software tool or its operator?
>Some skills, like framing, values, balance, etc. become even more important differentiators.
I agree. I think many artists in the future will be closer to directors/cinematographers/editors than performers
Many of the skills artists have today will still be necessary and transferable, but what will separate the good artists from the bad artists will be their ability to communicate their ideas to agents / other humans
Same with software developers I suspect - communication will be the most important skill of all, and the rockstar loner devs who don't work well in teams will slowly phase out
>AI has no intent or creativity, so it can be neither right nor wrong, neither good nor bad.
AI is just a wrapper around a tool - it doesn't need intention or creativity because those come from the user in the form of prompts (which are by definition intentional)
It's just a Natural Language Interface for calling CLI tools mostly, just like how GUIs are just graphical interfaces for calling CLI tools, but no one thinks a GUI has no intentionality or creativity even when using stochastic/probabilistic tools
Anything a user can do with an AI they could also do with a GUI, it would just take longer and more practice
>Either everything generative AI creates is slop or nothing is. So everything is.
But then how do you know something is slop before you know if it's made with GenAI? Does all art exist as Schrodinger's Slop until you can prove GenAI was used? (if that's even possible)
Arc Raiders, and their previous game The Finals, uses AI in some capacity for Voice Acting - though they do still hire VA and make it explicit in their contract offer
>Some of the voice lines were created using generative artificial intelligence tools, using an original sample of voice lines from voice actors hired specifically with an AI-use contractual clause, similar to the studio's production process in The Finals.
I come from a Swift/Kotlin background and I've been learning Rust for fun in my spare time
From what I heard online I was expecting it to be a lot harder to understand!
The moving/borrowing/stack/heap stuff isn't simple by any means, and I'm sure as I go it will get even harder, but it's just not as daunting as I'd expected
It helps that I love compiler errors and Rust is full of them :D Every error the compiler catches is an error my QA/users don't
>LLM generated code is noisy as hell, for no good reason
You can direct it to generate code/docs in whatever format or structure you want, prioritising the good practices and avoiding bad practices, and then manually edit as needed
For example with documentation I direct it to:
*Goal:* Any code you generate must lower cognitive load and be backed by accurate, minimal, and maintainable documentation
Better documentation, more test cases, and an NLP interface to query the code
Less cognitive load, more complete mental models
>even bad developers can do that many times compared to better ones, because for example they mindlessly copy-paste StackOverflow answers whose half of the code is absolutely not necessary
Maybe LLMs, much like StackOverflow, make good devs better and bad devs worse
Like a force multiplier for good practices and bad practices
>But happy to be corrected - is someone using these agents in their paid / professional / enterprise / team job?
Yes, and I find them quite useful
I don't see myself going back to the "Google + StackOverflow" approach I had used for 10 years prior (well, I can always fall back to it if necessary, but so far I haven't needed to)
My experience matches OP: my years of experience in manual coding complements the agent approach remarkably well
But I would also say a quality bug report is a contribution in and of itself
Closing it without reason is also, literally, unreasonable