“This code is giving me a return value of X instead of Y”
“Ah the reason you’re having trouble is because you initialized this list with brackets instead of new().”
“How would a syntax error give me an incorrect return”
“You’re right, thanks for correcting me!”
“Ok so like… The problem though.”
Not copilot, but I run into a fourth problem:
4. The LLM gets hung up on insisting that a newer feature of the language I’m using is wrong and keeps focusing on “fixing” it, even though it has access to the newest correct specifications where the feature is explicitly defined and explained.
They just brought back print and it’s been very satisfying for me so far.
Gotta make sure the root language is removed also. Add --no-preserve-root for that.
Does macOS respond to external keyboard power button presses because if so this could very well be as easy money-making real product
That’s not what it’s there for. It can also be used that way.
Icky!
I do try to keep the “unknown unknowns” problem in mind when I use it, and I’ve been using it far less as I latched on to how OOP actually works and built up the lexicon and my own preferences. I try to only ask it for high-level stuff that I can then use to search the wider (hopefully more human) internet more traditionally with. I fully appreciate that it’s nothing more than a very incredibly fancy auto-completion engine and the basic task of auto-complete just so happens to appear intelligent as it gets better and more complex but continues to lack any form of real logical thoughts.
I believe accessibility is the part that makes LLMs helpful, when they are given an easy enough task to verify. Being able to ask a thing that resembles a human what you need instead of reading through possibly a textbook worth of documentation to figure out what is available and making it fit what you need is fairly powerful.
If it were actually capable of reasoning, I’d compare it to asking a linguist the origin of a word vs looking it up in a dictionary. I don’t think anyone disagrees that the dictionary would be more likely to be fully accurate, and also I personally would just prefer to ask the person who seemingly knows and, if I have reason to doubt, then go back and double-check.
Here’s the manpage for bash’s statistics from wordcounter.net:
Understood, thanks for the info. Probably worth raising with them on the discord, which I would do if I felt strongly about it.
https://thunderstore.io/c/lethal-company/p/ebkr/r2modman/v/3.1.45/
Edit, for convenience:
(Emphasis mine, one of them humorous. There’s more, but formatting this on my phone is tedious and frustrating.)
Haha, yeah. It really loves to refactor my code to “fix” bracket list initialization (e.g. List<string> stringList = [];) because it keeps not remembering that the syntax has been valid for a while.
It’s newest favorite hangup is to incessantly suggest null checks without asking if it’s a nullable property that it’s checking first. I think I’m almost at the point where it’s becoming less useful to me.
It introduced me to the basics of C# in a way that traditional googling at my previous level of knowledge would’ve made difficult.
I knew what I wanted to do and I didn’t know what was possible or how to ask without my question being closed as a duplicate with a link to an unhelpful post.
In that regard, it’s very helpful. If I had already known the language well enough, I can see it being less helpful.
Still very early days, yes. R2modman supports more games also.
It’s definitely helpful for games to support their own modders also, and I can understand why most don’t put in the effort.
As much as it frustrates me that this is the best option for various reasons, there is at least now a native nexusmods client.
Granted, if your game isn’t supported by it and given that it’s early days, I do still agree with you.
They have a battleeye proton build that devs can choose to ship with if you use that, but for some reason most (including GTA V online) just… Decide not to use it.
(Apologies for not otherwise contributing to the discussion, you want “paid” instead of the nautical rope-handling term “payed”.)
If we’re talking about Digital Rights Management, steam is acting in that role to manage your digital rights on the steam platform. They could allow you to download games without requiring an account login or client download, and they instead do not. They could allow you to download free games from the client or the website without requiring a login, and they do not.
GOG’s website is also DRM for the same reason. It won’t allow you to download games that aren’t licensed digitally to your account, including free games. GOG has DRM-free games and installers fairly universally beyond that first check, and that means you can download them from alternative sources, but downloading from GOG 100% requires interacting with DRM.
To be direct: I don’t care that Steam is DRM because it’s minimally invasive and I currently trust Valve enough to use an operating system made by them as a daily driver. There are very few companies I’d say that about.
The Steam client is DRM at its core, even if it’s acceptable DRM. I think it’s important not to allow your thinking to shift from the reality that it is DRM just because it’s personally acceptable.
I don’t mind it, I will simp for Valve all day long, and if a company requires you to log in to an account with their server to check whether your account has the digital entitlement to then allow you to access a file or not, that’s digital rights management.
I want to give the perspective that from a technical standpoint, even free games on steam require the steam client to install and while the license to play the game is free steam is licensing your account to own the game. The game doesn’t require steam after that and usually this means the game is available elsewhere, but for the specific case of “free games on steam”, steam is still acting to manage digital rights.
Happy to help!