Ask Lemmy

The only thing that comes to mind is I wanted to make a shell script that moved every file in a directory to another directory, but one at a time, slowly, and I didn't want to learn sh from scratch, so I asked an LLM for a script that would do it.

The script didn't work, but I was able to figure out how to fix it better than write it from scratch.

I felt bad for the environment I was destroying, and I would never pay for this shit.

Honestly I'm part of the problem a little bit.

In my hobby project I used GitHub copilot, to help me ramp up on unfamiliar tech. I was integrating three unfamiliar platforms in an unfamiliar program language, and it helped expose the APIs and language features I didn't know about. It was almost like a tutorial; it'd make some code that was kinda broken, but fixing it would introduce me to new language features and API resources that would help me. Which was nice because I struggle to just read API specs.

I've also used it when on my d&d campaign to create images of new settings. It just a 3 player weekly game so it's hard to justify paying an artist for a rush job. Not great, I know. I hope the furry community has more backbone than I do, because they're singlehandedly keeping the illustration industry afloat at this point.

AI is great at helping me multitask. For example, with AI, I can generate misinformation and destroy the environment at the same time!

A lot of what we take for granted in software now days was once considered "AI". Every NPC that follows your character in a video game while dynamically accounting for obstacles and terrain features uses the "A* algorithm" which is commonly taught in college courses on "AI". Gmail sorting spam from non-spam (and not really all that well, honestly)? That's "AI". The first version of Google's search algorithm was also "AI".

If you're asking about LLMs, none. Zero. Zip. Nada. Not a goddamned one. LLMs are a scam that need to die in a fire.

None

I don’t think there’s many consumer use cases for things like LLMs but highly focused, specialized models seem useful. Like protein folding, identifying promising medication, or finding patterns in giant scientific datasets.

I tried Whisper+ voice-to-text this week.

Uses a downloaded 250MB model from Hugging-Face, and processes voice completely offline.

The accuracy is 100% for known words, so far.

For transcribing texts, messages and diary entries.

* I'd be interested to know if it has a large power drain per use.

LLMs can be useful in hyperfocused , contained environments where the models are trained on a specific data set to provide a service for a specific function only. So it won’t be able to answer random questions you throw at it, but it can be helpful on the only thing it’s trained to do.

"AI" as in the hyped and since 5 years mainstream "Generative AI": Jetbrains' locally run code line completion. Sometimes faster than writing, if you have enough context.

Machine learning stuff that existed well before, but there was exactly 0 hype: Image tagging/face detection.

Supermaven code autocomplete in vscode is really nice

The one that the other department tried, and which failed to meet expectations dramatically. Gave management a healthy dose of reality on "AI".

I used GPT to help me plan a 2 week long road trip with my family. It was pretty fucking awesome at finding cool places to stop and activities for my kids to do.

It definitely made some stupid ass suggestions that would have routed us far off our course, or suggested stopping at places 15 minutes into our trip, but sifting through the slop was still a lot quicker than doing all of the research myself.

I also use GPT to make birthday cards. Have it generate an image of some kind of inside joke etc. I used to do these by hand, and this makes it way quicker.

I also use it at work for sending out communications and stuff. It can take the information I have and format it and professionalize it really quick.

I also use it for Powershell scripting here and there, but it does some really wacky stuff sometimes that I have to go in and fix. Or it halucinates entire modules that don't exist and when I point it out it's like "good catch! That doesn't exist!" and it always gives me a little chuckle. My rule with AI and Powershell is that I don't ask it to do things that I don't already know how to do. I like to learn things and be good at my job, but I don't mind using GPT to help with some of the busy work.

The only AI tool I've found actually useful and reliable is AI denoise for photo editing.

I use ChatGPT every single day, and I find it both extremely useful and entertaining.

I mainly use it to help edit longer messages, bounce ideas around, and share random thoughts I know my friends wouldn’t be interested in. Honestly, it also has pretty much replaced Google for me.

I basically think of it as a friend who’s really knowledgeable across a wide range of topics, excellent at writing, and far more civil than most people I run into online - but who’s also a bit delusional at times and occasionally talks out of their ass, which is why I can’t ever fully trust it. That said, it’s still a great first stop when I’m trying to solve a problem.

DeepL for translation. It’s not perfect but it feels so much better than those associated w/ search engines.

Copilot in VScode is something you'd have to tear out of my cold, dead hands. Pressing Tab to auto complete is so useful. I use the GPT 4.1 model or whatever it is called. I tried Gemini but for some reason it's complete ass when doing code. Android Studio Gemini is worse than the free tier on the website.

However, I've found the Gemini Pro model on the website is incredibly good for information assistance. To give an idea of my current uses, I have two chats pinned on it: fact checking and programming advice. I use the former for general research that would take more than a few minutes of Googling but need an answer now, and the latter for brainstorming code design or technical tutorials (recently had it help me set up a VM in WSL).

One tool I wish I could use is ElevenLabs. Had a friend on the free tier of it make some really cool and convincing voice lines (I forgot what character it was) a long time ago. Looks easy to use too. I can't justify spending money just to play with it but if I had a purpose for it, I would.

https://notebooklm.google.com/ is really handy for various things, you can throw a bunch of documents into it and then ask questions and chat interactively about their contents. I've got a notebook for a roleplaying campaign I'm running where I've thrown the various sourcebook PDFs, as well as the "setting bible" for my homebrew campaign, and even transcripts of the actual sessions. I can ask it what happened in previous episodes that I might have forgotten, or to come up with stats for whatever monster I might need off the cuff, or questions about how the rules work.

Copilot has been a fantastic programming buddy. For those going a little more in depth who don't want to spring for a full blown GitHub Copilot subscription and Visual Studio integration, there's https://voideditor.com/ - I've hooked it up to the free Gemini APIs and it works great, though it runs out of tokens pretty quickly if you use it heavily.

https://goblin.tools/