What AI tools have you found useful?
-
I know the reputation that AI has on Lemmy, however I've found that some users (like myself) have found that LLMs can be useful tools.
What are fellow AI users using these tools for? Furthermore, what models are you using that find the most useful?
I was testing a lot of tools for work (UX), but they all sucked. Basically I just use gpt, cursor for tab coding,l and image generation for various purposes (Leonardo).
Most apps work poorly and using a model directly works better.
I worked on a few apps that use ai without a chat bot, but we found users expected one, maybe that will change in the future.
-
To be honest, this is the only thing Google did right about AI IMO.
-
I'm running ollama and open-webui and some unsloth modified models for some general purpose stuff.
The https://huggingface.co/unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF model has been pretty good. Beware it's a Chinese model so you can get some funny results if you ask about Tiananmen Square or if certain people resemble Winnie the Pooh. For making Linux configurations it works great.
Some gemma3 models are okay but it doesn't seem as good. Same for Phi4 models.
What are the minimum requirements?
-
I know the reputation that AI has on Lemmy, however I've found that some users (like myself) have found that LLMs can be useful tools.
What are fellow AI users using these tools for? Furthermore, what models are you using that find the most useful?
wrote last edited by [email protected]I think I’ve found the one area where LLMs really excel: business books / self help literature. The real life examples in that genre are pretty awful and dragged out as it is, so you can’t really make it much worse, now can you? The information density is kept low to fluff up the page count, and oh boy, are LLMs good at that. So, if you want to become a self help guru, but can’t be bothered to write your own book about magical hotels, marriage advice, productivity tips and communication, LLMs can take care of that for you. Copilot has turned out to work well for projects like that.
If you raise the bar, you’re going to have to read and edit the text manually. You also need to keep track of what has already been mentioned elsewhere and avoid repeating them again, depending on the genre. In business books though, that’s not a problem at all.
BTW, if you wonder about the downvotes, it’s because [email protected] isn’t a safe space for AI related discussions. Consider posting somewhere else.
-
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.
Also known as “narrow AI”. You know like a traffic camera that can put a rectangle on every car in the picture, but nothing else. Those kinds of narrow applications have been around for decades already.
-
I know the reputation that AI has on Lemmy, however I've found that some users (like myself) have found that LLMs can be useful tools.
What are fellow AI users using these tools for? Furthermore, what models are you using that find the most useful?
wrote last edited by [email protected]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.
-
I know the reputation that AI has on Lemmy, however I've found that some users (like myself) have found that LLMs can be useful tools.
What are fellow AI users using these tools for? Furthermore, what models are you using that find the most useful?
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.
-
I know the reputation that AI has on Lemmy, however I've found that some users (like myself) have found that LLMs can be useful tools.
What are fellow AI users using these tools for? Furthermore, what models are you using that find the most useful?
I've found LLMs in general helpful for coding specifically when I have to use tools or languages that I only have a passing familiarity with.
In my life I've used Gemini for some fitness coaching alongside other sources of information and it has been quite helpful and motivating.
-
I think I’ve found the one area where LLMs really excel: business books / self help literature. The real life examples in that genre are pretty awful and dragged out as it is, so you can’t really make it much worse, now can you? The information density is kept low to fluff up the page count, and oh boy, are LLMs good at that. So, if you want to become a self help guru, but can’t be bothered to write your own book about magical hotels, marriage advice, productivity tips and communication, LLMs can take care of that for you. Copilot has turned out to work well for projects like that.
If you raise the bar, you’re going to have to read and edit the text manually. You also need to keep track of what has already been mentioned elsewhere and avoid repeating them again, depending on the genre. In business books though, that’s not a problem at all.
BTW, if you wonder about the downvotes, it’s because [email protected] isn’t a safe space for AI related discussions. Consider posting somewhere else.
A safe space? Sorry but disagreeing with you is different from actual hatred campaings
-
I know the reputation that AI has on Lemmy, however I've found that some users (like myself) have found that LLMs can be useful tools.
What are fellow AI users using these tools for? Furthermore, what models are you using that find the most useful?
LLMs are pretty good for language learning. I often ask ChatGPT to converse with me in Japanese or help me make a sentence sound more natural.
-
There's also Udio.com and Producer.ai out there, and possibly some others - music generation is becoming fairly widespread. I didn't mention any of this in my list of recommendations though because OP specifically asked for LLMs.
I don't know how Suno has become so much more popular than Udio. Every Suno track I've heard has sounded like the same generic pop, and the vocals always have this noticeable "synthy" quality.
-
I know the reputation that AI has on Lemmy, however I've found that some users (like myself) have found that LLMs can be useful tools.
What are fellow AI users using these tools for? Furthermore, what models are you using that find the most useful?
I use predictive AI for certain classification tasks daily at work, however I call that Deep Learning and not AI. I don't want to be too specific, but you can imagine we are classifying certain objects - is this a traffic light, is this a tree etc. It is a task that cannot be solved geometrically very good, so Deep Learning is the perfect use case there.
-
Can you provide some specific examples? I can think of a few ways to implement some of that for my own use case.
If you read their comment you can see they did.
-
I know the reputation that AI has on Lemmy, however I've found that some users (like myself) have found that LLMs can be useful tools.
What are fellow AI users using these tools for? Furthermore, what models are you using that find the most useful?
I've been self-hosting my own AI stuff for a bit using Ollama. I use it to create images, design a tattoo, run a chatbot, write emails, write code and commit-messages, run a D&D game, explain concepts that I'm not familiar with, translate languages, etc.
I've been toying with different models, and I'm not sure that I have one that I would say is a goto. I am liking Ollama to be able to easily pull in and test new LLMs, as well as Stable-Diffusion for image generation/modification.
-
I don't know how Suno has become so much more popular than Udio. Every Suno track I've heard has sounded like the same generic pop, and the vocals always have this noticeable "synthy" quality.
Have you heard the stuff from the new v4 model? The vocals are so much clearer and the instrumentation gets pretty varied (ymmv depending on how specific you get with the styles though)
-
A safe space? Sorry but disagreeing with you is different from actual hatred campaings
wrote last edited by [email protected]The main point of the post is to ask a question. Apparently that is something people disagree with. Maybe they don’t like what the question implies.
-
I know the reputation that AI has on Lemmy, however I've found that some users (like myself) have found that LLMs can be useful tools.
What are fellow AI users using these tools for? Furthermore, what models are you using that find the most useful?
"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.
-
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.
Also a lot of things that were considered automations before are now rebranded to ai. They are still often good as well.
-
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 use it to help me write emails at work pretty regularly. I have pretty awful anxiety and it can take me a while to make sure my wording is correct. I don't like using it, not really, but would I rather waste 4 hours of my time typing up an email to all the bosses that doesn't sound stupid AF or would I rather ask for help and edit what it gives me instead.
I know people use it to summarize policy or to brainstorm or to come up with very rough drafts.
I understand the connotations of using it, but I would definitely not say there's zero consumer use case for it at all.
-
What are the minimum requirements?
It can run with a variety of systems. You just need to have enough VRAM on your video card to fit the model and then it can run pretty fast. There are models down to a couple hundred MB in size, but they're quite limited. There are other models that are 245GB in size, though the bigger ones use a "mixture of experts" where only portions of the model are loaded as needed, and the rest stays unused for the particular task at hand. If you don't have enough VRAM to fit the model, it will fall back to running on the CPU and using the system ram. Most of the operations are limited by the speed of the memory that's running the model. Video card memory is much faster than system memory so that's what helps it run a lot faster. It can still get the job done but you will have to wait quite a while for the output. There are ways of making the models smaller by using quantization. Quantization reduces the precision of the models parameters (the number with the b next to it in models i.e. 4b, 8b, 14b, 30b, etc.) by taking it from 32-bit data down to 8-bit or smaller. This allows more data to be packed in a smaller space, but it reduces accuracy a bit.
