I was able to run llms on a 1080. They were admittedly small ones, but a 3090 is enough to be usable. That said, I'm not convinced it's a good idea to use it for therapy. I expect it's about as useful as talking into a mirror.

[–] DancingBear@midwest.social 2 points 2 weeks ago (1 children)

I don’t know what to do with myself anymore I just want to be able to be with you and be with you I don’t know what to do about that I don’t know what to do I don’t know what to do I’m not gonna do that I don’t know what to do and I don’t know what to do but I don’t know what to do so I’m just trying I know that you don’t know how much you have and you know what you know but I’m just not trying and you can’t tell I’m not gonna tell anybody else how much I know I don’t know what I don’t even care what you do I don’t care I just know that I don’t know what to do with me and I’m just saying what do what do I

This is how LLM works

[–] ech@lemm.ee 2 points 2 weeks ago (1 children)

I mean, it can be pretty coherent and impressive with the right LLM, but even then it's mostly just functioning to generate what you want it to, and it's certainly not going to provide professional insight for those that need it.

[–] DancingBear@midwest.social 2 points 2 weeks ago

Yea it can be a lot more coherent, the above was just the autocorrect options on my phone that I pressed again and again.

But the LLM is not “listening” to you it is just providing the next likely words in a conversation based on what is in it’s database I believe…

Ai therapy sounds like a terrible idea…

[–] zero_spelled_with_an_ecks@programming.dev 1 points 2 weeks ago (1 children)

talking into a mirror

Does journaling count? It's got a small positive benefit according to https://pmc.ncbi.nlm.nih.gov/articles/PMC8935176/

[–] ech@lemm.ee 1 points 2 weeks ago

Talking things out to ourselves can often be useful. It could certainly be good for that.

[–] chicken@lemmy.dbzer0.com 2 points 2 weeks ago

3090 is great because it has about the same amount of vram as newer cards, and vram is what determines which models you can run on it.

[–] ShellMonkey@lemmy.socdojo.com 2 points 2 weeks ago

I think I'm at a 3060 or so and it works decently depending on the model. I can generally get away with around 13B, or some 20+ Q4 or so but they get real slow by that point.

It's a lot of messing around to find something that performs decent while not being so limited as to get crazy repetitive or saying loony things.

[–] SchizoDenji@lemm.ee 1 points 2 weeks ago

That's the best gpu for this usecase. Maybe use 2x if you want the best of the best.

[–] peteyestee@feddit.org 8 points 2 weeks ago (1 children)

Cyberpunk 2077 is our future.

[–] IndiBrony@lemmy.world 3 points 2 weeks ago (1 children)

They were 50 years too late: it's Cyberpunk 2027 now!

[–] ObstreperousCanadian@lemmy.ca 2 points 2 weeks ago

The original TTRPG was Cyberpunk 2020, so we're actually a few years late!

[–] Fiivemacs@lemmy.ca 5 points 2 weeks ago (1 children)

The thoughts they get: fuck big tech. Where's Luigi when you need him. Fucking distopian garbage. Screw your ads, block everything.

And so forth..

[–] MelodiousFunk@slrpnk.net 4 points 2 weeks ago

Congratulations! You have been added to The List. Again.

[–] dumbass@leminal.space 1 points 2 weeks ago* (last edited 2 weeks ago)

Other people using chatgpt: So then when I was a kid I was left at the store for 3 hours.

Me using chatgpt: write me a hip hop diss track written from the perspective of (insert cartoon character) dissing (insert cartoon character), make it be filled with personal attacks.