Genuinely fucking terrifying responses. I’m a lawyer, I write all fucking day, and I’ve never once even thought about using this shit to write even a draft section of one email of mine.

I sincerely don’t understand why people act like these LLMs are necessary. I know the vast majority of yalls aren’t writing more than me on a given workday, so wtf are yalls using it for? Yall that stupid and lazy that you can’t type out a three paragraph email? Or a one-page memo for a client?

Fucking insane. Hate this dystopia.

Generate my personal firehose of falsehoods

Hey, if putin is allowed to have a firehose, I should get an even bigger firehose

Ohh no you posted something semi positive about AI on Lemmy. Looks like everyone already did their duty and downvoted you for it. God forbid you have a use for it.

Personally I like the Qwen models mostly when I’m at home. They’ve been proven fairly competent. I run a sled hosted Tabby copilot alternative for vs code too that I’ve come to enjoy.

We have a few internal to the company so proprietary data doesn’t leak into the public. Not one of them can be relied on. I vet it by asking questions about certain procedures I know inside and out (I wrote most of them), and the LLMs can get close but are consistently inaccurate.

Not a programmer, so no experience with a large use case there.

The most useful thing I’ve used it for us breaking thru writers block on dumb things. Just staring at a blank page and unable to get started. So I brain dump into LLM, it gives me a few crappy sentences, I think “I can do better than that”, and I write something from scratch.

I use my brain but tbh it probably isn’t much better than some LLMs (I’m stupid)

I gave up on that last year. My hardware can’t run what most talk about, I don’t want to be downloading too many models with slow internet, and even the heat is undesirable most of the year. Too much research/assessment, too.

Add to that what I use is niche (nim-lang, Godot) so even if I accept that it will be more of an advisor (code review, structure/planning recommendations) any minimal model I could run probably would still struggle with anything that isn’t incredibly common/simple.

Funnily enough , grok

Used it back wen Scira didn’t suck (was default model) . Yet to find local LLM with these capabilities

• Web browsing
• (Image|video) analysis (used it to find which bꝏk picture of passage randomly found online was from)

Open for local LLM recs that can run on my phone btw

I started like most with gpt and used it until I had no more hair left to pull out. Then recently I switched to using Claude and was blown away with how much better it was at everything compared to gpt.

I don’t favor any, but have used chat gpt on occasion to help generate ideas for dnd planning purposes like things a town crier might disseminate or ideas for magical items that can help against a specific big bad.

I’ve only ever tried ChatGPT and that’s what I’ve stuck with.

Most of the time it does what I ask. My two main uses are editing my writing and answering random questions. I also use it to bounce ideas off, and honestly it’s the “adult” I talk to when I’m about to tear my hair out trying to have civil conversations online. I feel like an LLM is tuned better to my autistic wavelength than most people are. I rarely get to talk about my deepest interests with others because they’re usually not the kind of things your average Joe spends time thinking about - so rather than boring people to death or sharing thoughts with friends who won’t even respond, I find myself turning to ChatGPT more and more.

It’s interesting that I genuinely enjoy my interactions with an LLM more than with most people online. I’m not sure what that says about me, other people, or the LLM itself. Out of everything I do online, YouTube and ChatGPT give me by far the fewest regrettable minutes.

I use different ones for different things. Perplexity answers my tech questions best (what is the dax formula for ___). Gemini is good if I’m making something that needs more casual language or some help brainstorming. Copilot is good for corporate jargon. It plays nice with other MS tools, so if I need to connect it to a PowerAutomate or Power app, I can do that. I used ChatGPT to make a lifetime movie plot generator with great success.

Gemma 2.5 on ollama is all my lowly laptop can run.

It’s good enough for what I want - summarize, translate, generate bullshit.

Depends on what you need it for. There’s no single LLM model that’s a superset of all others today.

Running Gemma or Hermes through ollama mostly. I don’t really use llms much but I’d much rather self host one when I do need it. I tried deepseek locally but even though it was super fast it the “reasoning” bs was enough to make me get rid of it.

I use chatgpt for day to day stuff , grok and qwen for image generation