Back

Well, you know, you don’t want to miss out! You don’t want to miss out, do you? Trust me, everyone else is doing this hot new thing, we promise. So you’d better start using it too, or else you might get left behind. What is it useful for? Well… it could make you more productive. So you better get on board now and, uh, figure out how it’s useful. I won’t tell you how, but trust me, it’s really good. You really should be afraid that you might miss out! Quick, don’t think about it so much! This is too urgent!

Pretty much this. I work in support services in an industry that can’t really use AI to resolve issues due to the myriad of different deployment types and end user configurations.

No way in hell will I be out of a job due to AI replacing me.

your industry isn’t alone in that — just like blockchains, LLMs and generative AI are a solution in search of a problem. and like with cryptocurrencies, there’s a ton of grifters with a lot of money riding on you not noticing that the tech isn’t actually good for anything

Unlike blockchains, LLMs have practical uses (GH copilot, for example, and some RAG usecases like summarizing aggregated search results). Unfortunately, everyone and their mother seems to think it can solve every problem they have, and it doesn’t help when suits in companies want to use LLMs just to market that they use them.

Generally speaking, they are a solution in search of a problem though.

GH copilot, for example, and some RAG usecases like summarizing aggregated search results

you have no idea how many engineering meetings I’ve had go off the rails entirely because my coworkers couldn’t stop pasting obviously wrong shit from copilot, ChatGPT, or Bing straight into prod (including a bunch of rounds of re-prompting once someone realized the bullshit the model suggested didn’t work)

I also have no idea how many, thanks to alcohol

That sounds miserable tbh. I use copilot for repetitive tasks, since it’s good at continuing patterns (5 lines slightly different each time but otherwise the same). If your engineers are just pasting whatever BS comes out of the LLM into their code, maybe they need a serious talking to about replacing them with the LLM if they can’t contribute anything meaningful beyond that.

@TehPers @self

5 lines slightly different each time but otherwise the same

I got questions tbh

It’s not that uncommon when filling an array with data or populating a YAML/JSON by hand. It can even be helpful when populating something like a Docker Compose config, which I use occasionally to spin up local services while debugging like DBs and such.

Copilot helped me a lot when filling in legendaryII.json based on data from legendary.json in this directory. The data between the two files is similar, but there are slight differences in the item names and flag names. Most of it was copy/paste, but filling in the When sections was much easier for me with copilot + verify, for example.

Edit: It also helped me with filling in the entries at the top of this C# file based on context I provided in a different format above (temporarily) in comments.

@TehPers there are tools for doing this sor... you know what, never mind

I know, I used one.

@TehPers "I used Github Copilot to help me hand-edit a massive JSON file which was *very slightly different* from another JSON file that I also maintain for some reason, therefor AI is good" is quite a take, but go off, I guess

I genuinely don’t get what point you’re trying to make. I found the tool useful and it saved me time. Are you trying to say the tool did not in fact do what I needed it to, when my other usual approaches were not flexible enough to do what I needed? Did it not do its job and save me time writing my code?

Seriously, you don’t see me making fun of people for using vim or notepad++, or whatever editors and tools you use.

You were asked to give a use-case for LLMs, and with this comes the implicit assumption that it’s not something that can be easily done with a tool that costs about seven orders of magnitude less to produce.

A bunch of junior devs writing repetitive code because it’s easier or people refusing to learn proper tools because “AI can write my JSON” aren’t exactly good reasons tor the rest of the industry to learn how LLMs work. Don’t get me wrong, there are good reasons, but you’ve not listed any.

@froztbyte just reinforcing my hypothesis that, as with crypto, everybody involved in this is either a cynical grifter or a wide-eyed first-day-on-the-computer 12-year-old

Feel free to add a PR for tests too. You’re going to need a legal copy of Stardew Valley for the CI machine.

Edit: or don’t actually, since I know you wouldn’t dare do something productive after reading your PR. If anyone else wants to though, PRs are welcome. This has actually been a pretty big pain considering mods won’t even compile without a copy of the game.