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 feed it TOS, Service Agreements, etc and have it simplify and summarize them so i can have a general idea of what is in them without 10 minutes of reading.
I wonder how it does against tosdr
Didn’t know about this, thanks!
10 minutes? Damn you’re a fast reader…
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
Messing with a win11 laptop recently, I asked copilot how to disable copilot. After a couple of tries it told me.
That’s about it.
That’s hilarious
Among other things: Cooking. They’re really helpful in those situations where I have a bunch of ingredients lying around in my pantry but I lack concrete recipes that can make a proper meal out of them.
That’s good. I have to tr…ohmygoddidittellyoutomakecumbroth
The idea of an imagined recipe based on random ingredients from a thing that doesn’t understand the concept of taste seems like a “recipe” for some really gross food.
I mostly just use them to help write Python scripts.
None. I avoid them when ever possible which thus far is most of the time.
Absolutely nothing, because they all give fucking useless results. Hallucinates, is confidently wrong, and isn’t even grammatically competent (depending on the model). Not even good for a draft, because I’d have to completely rewrite it anyway.
LLMs are only as good as the guys training it (who are mostly morons), and the raw data they train on (which is mostly unaudited random shit).
And that’s just regular language. Coding? Hah!
Me: Generate some code to [do a thing].
LLM: [Gives me code]
Me: [Some part] didnt work.
LLM: Try [this] instead.
Me: That didn’t work either.
LLM: Try [the first thing] again.
Me: … that still doesn’t work…
LLM: Oh, sorry. Try [the second thing again].
Me: …Loop continues forever.
One time I found out about a built-in function that I didn’t know about (in LLM generated code that didn’t work), and read the manual for it, and rewrote the code from scratch to get it working. Literally the only useful thing it ever gave me was a single word (that it probably found on Superuser or StackExchange in the first place).
Wow, you get two whole answers?! Lucky, I just get the same goddamned response repeatedly until I yell at it or until it gives up.
Skill issue. You have to know a bit about the topic and prompt it right.
It’s for boilerplate where you can scan it for errors with your dev ability
An interesting theory, except I know exactly how to do everything I’ve ever asked an LLM about. I would never trust one of these things to generate useful copy/code, I just wanted to see what it could do. It’s been shit 100% of the time. Never even gotten a useful function out of it.
Also “skill issue” is a lazy response. Try reading the post before you reply next time.
I did read it.
You can create great and very useable boilerplate with even gpt 3.5 …
You have a skill issue with your prompts.
If I can’t use the LLM by prompting it the same way I’d prompt one of my colleagues, then it’s not a skill issue; It’s shitty LLM. I don’t care if it’s the input embedder, training data, or the guy who didn’t bother properly building a model that didn’t just spit out bullshit.
If an employee gave me this quality, I’d get rid of them. Why would I waste my time on a shit coder, artificial or otherwise?
Sorry, but holding spicy autocomplete to the same rigor you’d hold a human coworker is probably the beginning of your issue. It’s clear your prompt is not working.
Well, considering the speed of your responses, and your obsession with making excuses for shitty software, I’m guessing you’re and LLM, so I’m gonn start ignoring you too. Good luck surviving the hype phase.
I’m currently browsing this website, any page interaction results in a notification by the inbox.
You too reply quickly, thus, are also a robot.
Edit I’m not excusing shitty software, I acknowledged the types of tasks it’s appropriate for from the beginning.
I’m highlighting a shitty user lol
I used openAI/whisper to transcribe several thousand .wav files full of human speech (running locally). Much faster than trying to listen to them myself. It wasn’t perfect but the error rate was within acceptable levels.
porn
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.
Friend, code, search engine, writing, cooking ideas, sexy time, exploring psychology, therapist, etc.
Sexy time? You use it to talk to you erotically?
Virtual partners are indeed a thing.
One of the more popular ones a few months ago decided to nerf the sexy time talks, which was intersting in how much it emotionally hurt users. They described feeling like their virtual partner was no longer the same person that they’d fallen for. Source: https://www.abc.net.au/news/science/2023-03-01/replika-users-fell-in-love-with-their-ai-chatbot-companion/102028196
There are also huge fears of how much data harvesting they are capable of performing.
I’m in two minds. On one, they are definitley not real. They are code. But on the other, the epidemic of lonely human beings is only getting worse with time and not better, and anything that can help people feel less lonely has to be a good thing, right?
I assume (from your user handle) that you know about the allure of roleplaying and diving into fantasy scenarios. AI can do it to some degree. And -of course- people also do erotic roleplay. I think this always took place. People met online to do this kind of roleplay in text chats. And nowadays you can do it with AI. You just tell it to be your synthetic maid or office affair or waifu and it’ll pick up that role. People use it for companionship, it’ll listen to you, ask you questions, reassure you… Whatever you like. People also explore taboo scenarios… It’s certainly not for everyone. You need a good amount of imagination, everything is just text chat. And the AI isn’t super smart. The intelligence if these models isn’t quite on the same level as the big commercial services like ChatGPT. Those can’t be used as they all banned erotic roleplay and also refuse to write smutty stories.
I agree with j4k3. It’s one of the use-cases for AI I keep coming back for. I like fantasy and imagination in connection with erotics. And it’s something that doesn’t require AI to be factually correct. Or as intelligent as it’d need to be to write computer programs. People have raised concerns that it’s addicting and/or makes people yet more lonely to live with just an AI companion… To me it’s more like a game. You need to pay attention not to get stuck in your fantasy worlds and sit in front of your computer all day. But I’m fine with that. And I’m less reliant on AI with that, than people who use AI to sum up the news and believe the facts ChatGPT came up with…
I had no idea there were smaller models out there catering to this service! What ones would you recommend? Not asking for a friend, genuinely interested in playing around (no pun intended) with them to see what they produce… the fantasy stuff isn’t really me, I’m just fascinated to see what they come up with…
https://lemmynsfw.com/post/4048137
I’d say try MythoMax-L2 first. I think it’s a pretty solid allrounder. Does NSFW but also other things. Nothing special and not the newest any more, but easy to get going without fiddling with the settings too much.
If you can’t run models with 13B parameters, I’d have to think which one of the 7B models is currently the thing. I think 7B is the size most people play around with and produce new finetunes, merges and what not. But I also can’t keep up with what the community does, every bit of information is kind of outdated after 2-4 weeks 😆
Thanks will have a look 👍
I use Chatgpt 3.5 both personally and at work for tip of the tongue questions, especially when I can’t think of a word. Sometimes as a starting point when I have trouble finding the answer to a question in Google. It can sometimes find an old movie that I vaguely remember based on my very poor descriptions too.
For example: “what is the word for a sample of a species which is used to define the species” - tip of the tongue, holotype. “What is the block size for LTO-9 tape” - wasn’t getting a clear answer from forums and IBM documentation is kind of behind a wall, needed Chatgpt to realize there was no single block size for tape.
It’s excellent for difficult to search things that can be quickly verified once you have an answer (important step, as it will give you garbage rather than say it doesn’t know something).
needed Chatgpt to realize there was no single block size for tape.
Did it clearly say so or did you figure it out because it gave incompatible or inconclusive answers?
It did say so directly, something that I couldn’t find in a Google search because I was asking the wrong question, and getting forum posts with loosely related technical questions about LTO.
That’s not to say that it doesn’t just as often give weird answers, but sometimes those can guide me to the right question too.
Nothing. Remember that bartender from the original Star Wars?
Nothing. Never used.
