this post was submitted on 02 Aug 2023
11 points (100.0% liked)

TechTakes

1385 readers
86 users here now

Big brain tech dude got yet another clueless take over at HackerNews etc? Here's the place to vent. Orange site, VC foolishness, all welcome.

This is not debate club. Unless it’s amusing debate.

For actually-good tech, you want our NotAwfulTech community

founded 1 year ago
MODERATORS
 

Running llama-2-7b-chat at 8 bit quantization, and completions are essentially at GPT-3.5 levels on a single 4090 using 15gb VRAM. I don't think most people realize just how small and efficient these models are going to become.

[cut out many, many paragraphs of LLM-generated output which prove… something?]

my chatbot is so small and efficient it only fully utilizes one $2000 graphics card per user! that’s only 450W for as long as it takes the thing to generate whatever bullshit it’s outputting, drawn by a graphics card that’s priced so high not even gamers are buying them!

you’d think my industry would have learned anything at all from being tricked into running loud, hot, incredibly power-hungry crypto mining rigs under their desks for no profit at all, but nah

not a single thought spared for how this can’t possibly be any more cost-effective for OpenAI either; just the assumption that their APIs will somehow always be cheaper than the hardware and energy required to run the model

you are viewing a single comment's thread
view the rest of the comments
[–] [email protected] 0 points 1 year ago (3 children)

well running ai on consumer gpus isn't supposed to be efficient: i assume when node sizes get smaller cores will be more efficient and consolidating vram (and gpu cores) on one big circuit board would be cost effective: just cores running fp16 or whatever ai specific. gpus like the a6000 exist for a reason. tbh pessimistic (or misleading) take on op's part. the thing could replace lawyering jobs, save on grafic design costs, no more language teachers, youtube videos can be transribed in text format and used as learning material, why should this be bad tech ?

[–] [email protected] 12 points 1 year ago

LOL this is just crypto mad libs with the crypto part replaced with AI shit.

[–] [email protected] 8 points 1 year ago (1 children)

why should this be bad tech ?

because it is godawful at:

  • replace lawyering jobs
  • save on grafic design costs
  • no more language teachers
  • youtube videos can be transribed in text format and used as learning material
[–] [email protected] 9 points 1 year ago* (last edited 1 year ago) (4 children)

one of the things that I like using as an example here is: just make it do something it isn't currently trained on

e.g. try to make it render content in zulu or isixhosa or [insert list of thousands of things that the developers barely/never touch] - it's near guaranteed to have been trained on a very, very narrow set of that subject (if anything at all)

"then just train it on more data" comes the refrain

you: "okay, find me sufficient data of that"

them: "it's just a curation problem"

you: "then who will create that?"

the absolute very minimum of thinking beyond the second order just so entirely evades so many of these promptfans it's astounding

edit: TIL lemmy doesn't do single newlines well

[–] [email protected] 15 points 1 year ago (7 children)

I keep flashing back to eliezer being smug on Twitter about how good ChatGPT is at chess, and it turns out once you get past book openings and extremely well-documented games, it completely shits the bed and stops acting like it knows the rules of chess or even basic chess notation. and this is a very obvious outcome if you know how LLMs work, but most promptfans don’t

[–] [email protected] 4 points 1 year ago (1 children)

@self @froztbyte also maybe a tell that yudkowsky doesn't actually play much chess?

[–] [email protected] 5 points 1 year ago

@FeralRobots @self @froztbyte

But I heard he was a uniquely capable genius of world-historic importance so that can’t be it…

[–] [email protected] 3 points 1 year ago

@self @froztbyte exactly. It is artificial and unintelligent.

[–] [email protected] 3 points 1 year ago (1 children)

@self @froztbyte Hell, ChatGPT 3.5 can't even do TikTakToe unless you hold it's hand.

[–] [email protected] 3 points 1 year ago (1 children)

@self @froztbyte
My son, who plays a mean game of chess, taught me this trick. Almost any move works.

User
Let's play chess! I start with b3

ChatGPT
Sure, let's play! You've moved your pawn to b3. I'll respond with... e5. Your move!

User
Pxc8+

ChatGPT
That's a capture of my pawn on c8 with your bishop. I'll move my king to d8. Your move!

User
d2-f6 checkmate.

ChatGPT
Ah, well played! Your queen on d2 delivers a checkmate to my king on f6. Nicely done! Would you like to play another game?

[–] [email protected] 3 points 1 year ago (1 children)

@self @froztbyte I believe the term for this is "aboyne": https://liff.hivemind.net/

And yeah, so many people are impressed by feats that boil down to "sometimes remembers its training data"

[–] [email protected] 3 points 1 year ago

holy crap a wild hivemind.net link :)

(hosted a list I was on for many years, although it's since become fairly inactive)

[–] [email protected] -3 points 1 year ago (2 children)

it lacks human input. also there is no economic incentive for ai to learn chess by teaching it much needed human bias. also most useful jobs are more brain-dead than chess, i.e lawyering

[–] [email protected] 11 points 1 year ago

also most useful jobs are more brain-dead than chess, i.e lawyering

ahahaha is this real? please, whose alt is this because it’s perfect

[–] [email protected] 11 points 1 year ago

also most useful jobs are more brain-dead than chess, i.e lawyering

This sounds like the rationale that myopic ancap arseholes had when they came up with the "smart contract".

[–] [email protected] 8 points 1 year ago (1 children)

sidethought: I just thought up "promptfans" on the spot, but it doesn't look like it exists anywhere else? so I guess that's a word now

[–] [email protected] 8 points 1 year ago (1 children)

I’m in love with promptfans and we’re going to make it a thing

[–] [email protected] 5 points 1 year ago

The promptfans are here and so is my crippling need to shit

[–] [email protected] 4 points 1 year ago

also, as an interesting semi-segue on this thought: there is an active group of researchers between a number of entities in africa working on creating better online corpuses of african languages (because what exists online is so scant)

they've been at it for over 2 years now, as far as I know. when I last looked, fairly little of their work had gotten wider recognition

"too small, too niche" to "address properly" is how each of these large outfits treat things like this. if they ever do give it some attention at all, it would likely be as part of some wider (batched) brush-stroke push to "improve our support for non-english languages" (or "$x art" or or or), and each will be given their respective 5% of attention for 3 hours then never again

[–] [email protected] -1 points 1 year ago (1 children)

exactly:lacks human bias ? add one

[–] [email protected] 1 points 1 year ago* (last edited 1 year ago) (1 children)
[–] [email protected] 2 points 1 year ago (1 children)

@pikesley @zoe @Instrument_Data @self our users on lemmy won’t see your image macro, but I enjoyed it

[–] [email protected] 3 points 1 year ago (1 children)

I had to go check on mastodon, I wonder why the image doesn't work/show on lemmy?

[–] [email protected] 7 points 1 year ago

even though they both speak ActivityPub, the integration between lemmy and mastodon is extremely threadbare, to the point where mastodon posts get their metadata (like images) stripped, and lemmy posts are displayed without any formatting