I recently set up a LLM to run locally on my desktop. Now that the novelty of setting it up and playing with different settings has worn off, I’m struggling to come up with actual uses for it. What do you use it for when not doing work stuff?
You must log in or register to comment.
The only thing I’ve found them actually useful for is generating random lists for my D&D games.
When it comes down to needing some mundane descriptions, its great having an LLM brainstorm for you. “Give me 10 examples of weird things I might see in jars in a witch’s hut.” This works well because you can just cut the 5 you don’t like and use the other 5 to brainstorm your final list.
This is the only thing I use it for in personal life. Every town my players visit now has a gift/t-shirt shop - I feed it details of the location have it spit out 20 t-shirt ideas and 5 are something I can work with. My players have started collecting t-shirts.
Or I describe a monster or bit of homebrew and have it suggest names, I suck at names. GPT also sucks at names but after enough suggestions there’ll be something that works.
Yes, I absolutely love this. I bought a deck of attack description cards that make hits feel more interesting by describing the action in cool ways, but it had nothing for misses, so I fed chatGPT some examples from the ‘hit’ list and asked it to make me a miss one, and it’s been great.
I’ve had pretty good luck getting cocktail recipes out of chatgpt. They sometimes need a little tweaking but it hasn’t steered me horribly wrong yet.
I’m also going to be officiating a wedding for a friend in a few months, so I’ve been using it to work out what I want to say for the ceremony.
I have a coworker who’s been taking some college classes. He struggles a bit with writing papers, he knows all the material just doesn’t quite know how to get started putting things down on paper. I told him to give it a try, with some strong warnings to rewrite and fact-check everything it spits out, and so far it’s been working out great for him and he’s been heeding my warnings, he pretty much punches in some prompts and bullet points and then goes through and rewords everything it spits out and fact-checks it as he goes.
I used ChatGPT this morning to create a Firefox extension for my favorite website (to allow me to speed up audio playback as desired.) just a few minutes’ back-and-forth and it works perfectly. If you’ve got a favorite site with a UI that you r always wanted slightly tweaked, you could try making a browser extension to do that!
You can use it for anything that requires a little logical multi step thought (anything single fact based is a straight web search with your search engine of choice)
For example,
- Rewrite your CV.
- reply to a letter
- write some code for a particular task.
- debug your computer problem.
- form a legal analysis to a situation ( https://www.legalcheek.com/2024/09/over-40-of-lawyers-now-use-ai-to-accelerate-their-work/ )
- have a conversation about a topic to help you understand yourself or a thing better. (“How do I build a ceph storage cluster in Kubernetes on Talos Linux with a raspberry pi, a mini pc …”). Then you can ask about alternatives solutions or whatever.
- come up with a business idea and talk it through with some’one’. Pricing etc.
- summaries of text.
At the moment they don’t always spit out correct answers to factual questions; they’d rather give crap than say they don’t know (without anthropomorphisising). When I asked Claude for equivalent sections in another jurisdictions legislation I got crap back on several occasions rather than the correct answer, but the false ‘facts’ were easy to check. However, the analysis was correct. ChatGPT gave the correct answer (to the original question). And I’ve had it the other way around too. So for the moment, pair them with Google or something similar for any fact output requested.
They’re excellent tools for analysing situations and providing feedback. The code it writes is pretty good.
Hopefully they never get trained on social media.
I use Google Translate and DeepL almost every workday for translation stuff.
ChatGPT I use rarely. When I have trouble wording something, I does provide a good starting point though. For example I had to write a birthday card for a business relationship and it helped me greatly with that.
No need for generation so far. No pics, videos in my line of work and coding it always just produced garbage for me. I’m faster on my own and the usual googling. Is that a GPT 3.5 issue? I don’t have a paid plan.
Brainstorming ideas; it’s something to bounce ideas off and see what can be tweaked.
Single-player D&D. Can setup multiple players/characters and a DM and just play D&D by myself, which is rad.
Having conversations with fictional characters. Like Data from Star Trek.
That sounds lonely.
Okay ive seen this kind of usage now 3 or 4 times and im at a complete loss how that even works.
Starting to feel very out of touch with reality :(
Edit: meant to say technology not reality but im just gonna leave the correction as this edit
How which one works?
I cant fathom how to playtest dnd with it. That concept does not compute.
I think ide have to see it in action
Oh I’m not playtesting, I’m straight up playing the game using the AI as the DM and 3 other players. I’m using an AI that can pretend to be multiple characters at once and then they’re trained on the rules of the game as well as just having general writing ability to create actions their characters take, while also having a dice-roller integrated into it.
It’s more imaginative than how most play, using a map and minis; this is entirely text and RNG numbers for dice. Imagine doing an RP session in a Discord chat and you’ll get the idea. Just instead of real people, it’s AI (except for myself).
The genius of it is that even if the AI misinterpreted the rules, it’s still like playing with real people since they do that too! lol
Sometimes I ask it for music recommendations.
But mostly I tend to just use it like a fancy thesaurus when I’m low on mental energy.
I find the state of the art models are finally getting good enough they are wonderful for rubber ducking abstract ideas.
Also code generation.
Yes! Was going to say it’s become my new rubber duck tool.
Well, I’ve tried using it for the following:
-
Asking questions and looking up information in my job’s internal knowledgebase, using a specially designed LLM trained specifically on our public and internal knowledgebase. It repeatedly gave me confidently incorrect answers and linked nonexistent articles.
-
Deducing a bit of Morse code that didn’t have any spaces in it, creating an ambiguous word. I figured it could iterate through the possible solutions easily enough, saving me the time of doing it myself. I gave up in frustration after it repeatedly gave answers that were incorrect from the very first letter.
If I ever get serious about looking for a new job, I’ll probably try and have it type up the first draft of a cover letter for me. With my luck, it’ll probably claim I was a combat veteran or some shit even though I’m a fat 40-something who’s never even talked with a recruitment officer in their life.
Oh, funny story–some of my coworkers at the job got the brilliant idea to use the company LLM to write responses to users for them. Needless to say, the users were NOT pleased to get messages signed “Company ChatGPT LLM.” Management put their foot down immediately that doing it was a fireable offense and made it clear that we tracked every request sent to our chatbot.
-
porn
I use it for a jumping off point creating an itinerary for trips. Asking to create a 3 day itinerary with a mix of recommended restaurants, bars and cafes in between has been really helpful. The google maps links usually don’t work but you need to confirm the places still exist anyway, and adjust as needed.
Playtesting ttrpg campaigns, mostly. Can be more helpful than just playing it through solo, but LLMs tend to be really fucking uncreative.
How do you use it for that purpose? Cannot imagine how that works
I use a frontend called Silly Tavern to create a group with several “Personas” that I write a character definition for, in which I also outline the ruleset of the rpg framework I’m using. I then either run an LLM locally, or plug in an API Key for a cloud-based provider.
I then present them with the plot as Game Master and have them react, while doing their throws myself. Works surprisingly well, and is less dry than just going through the adventure you’ve written step by step.
Okay if you ever post this process where i can watch it ide watch it.
Im officially old now i think.
This sucks
Honestly, I know the feeling, and I’m not really all that old. I’m kinda busy at the moment, but I’ll try to remember pinging you if I make a proper post.
Oh damn, i was just despairing a bit. I didnt really think you would do it. So no pressure to do it friend!
I’m still trying to get Silly Tavern to run. I want to try what you are doing
What problems are you having? For me it was pretty straightforward. Just had to clone the git repo, run the start.sh script, and visit localhost:8000 in a browser.
Instead of reading a manual file for the badrillionth time, I ask it how a shell command should be formated. If it is easy, it gets it right away and I say “oh, yea, that’s right”. If it is hard, I still get a starting point and can correct it fairly quickly. I ask it for translations when learning a new language, which I’ve been doing lately. This it excel at. Even languages that conventional machine translation fails at. I asked chatgpt for Minecraft blocks with some specific set of desirable redstone properties that I didn’t want to dig through a wiki to find. This one had varying success. It is not aware of every odd redstone secret, but it can spit out something useful if you are lucky. I had a quick poem made for one of my rp characters. We had a 5 minute break and I wanted something that made sense for the next scene. Some quick directions to the LLM and a little shoveling paragraphs around and there you go.
I also have tried some light rp with the ai for entertainment. I tried merging harry potter and star trek once. It was mildly entertaining.
If you know how they are dumb and where they kinda work, you can get stuff done. Especially if the answers are easily verifiable. That about summs up how I use them.
The only use I have for AIs is to translate from my mother tongue into English, to chat online. I could write directly in English, but it hasn’t been worth it for a few years.
I’ve been using one to write cover letters for job applications. It takes a bit of wrangling to get anything, and then a bit more to get it to actually say things that aren’t total bullshit, but I find it less tedious than writing them myself.
