this post was submitted on 04 Sep 2024
262 points (100.0% liked)

TechTakes

1427 readers
105 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
top 50 comments
sorted by: hot top controversial new old
[–] swlabr@awful.systems 87 points 2 months ago

LLMs, and everyone who uses them to process information:

[–] hex@programming.dev 63 points 2 months ago (1 children)

Facts are not a data type for LLMs

I kind of like this because it highlights the way LLMs operate kind of blind and drunk, they're just really good at predicting the next word.

[–] CleoTheWizard@lemmy.world 28 points 2 months ago (1 children)

They’re not good at predicting the next word, they’re good at predicting the next common word while excluding most unique choices.

What results is essentially if you made a Venn diagram of human language and only ever used the center of it.

[–] hex@programming.dev 15 points 2 months ago

Yes, thanks for clarifying what I meant! AI will never create anything unique unless prompted uniquely and even then it will tend to revert back to what you expect most.

[–] swlabr@awful.systems 48 points 2 months ago (1 children)

ATTN: If you're coming into this thread to say, "The output of AI is bad because your prompts suck," I'm just proud that you managed to figure out how to use the internet at all. Good job, you!

[–] froztbyte@awful.systems 15 points 2 months ago

remember remember, eternal september

(not that I much agree with the classist overtones of the original, but fuck me does it come to mind often)

[–] Sibbo@sopuli.xyz 31 points 2 months ago (1 children)

Well, to be fair, AI can do it in seconds. Which beats humans.

But if that is relevant if the results are worthless is another question.

[–] HubertManne@moist.catsweat.com 12 points 2 months ago (3 children)

Yeah it changes the task from note taking or summarizing to proofreading.

load more comments (3 replies)
[–] kbal@fedia.io 22 points 2 months ago

Made strange choices about what to highlight.

They certainly do. For a while it was common to see AI-generated summaries under links to articles on lemmy, so I got a feel for them. Seems to me you would not need any fancy artificial intelligence to do equally well: Just take random excerpts, or maybe just read every third sentence.

[–] dgerard@awful.systems 21 points 2 months ago (3 children)

how the hell did this of all the posts turn into a promptfondler shooting gallery

[–] froztbyte@awful.systems 11 points 2 months ago

1.26K subscribers

load more comments (2 replies)
[–] dgerard@awful.systems 19 points 2 months ago

i have seen the light from the helpful posters here, made up bullshit alleged summaries of documents are great actually

[–] khalid_salad@awful.systems 11 points 2 months ago

Could it be because a statistical relation isn't the same as a semantic one? No, I must be prompting it wrong. I'll just add "engineer" to my title and then everyone will take me seriously.

[–] RagnarokOnline@programming.dev 8 points 2 months ago (9 children)

I had GPT 3.5 break down 6x 45-minute verbatim interviews into bulleted summaries and it did great. I even asked it to anonymize people’s names and it did that too. I did re-read the summaries to make sure no duplicate info or hallucinations existed and it only needed a couple of corrections.

Beats manually summarizing that info myself.

Maybe their prompt sucks?

[–] froztbyte@awful.systems 41 points 2 months ago (6 children)

“Are you sure you’re holding it correctly?”

christ, every damn time

load more comments (6 replies)
[–] dgerard@awful.systems 29 points 2 months ago

I got AcausalRobotGPT to summarise your post and it said "I'm not saying it's always programming.dev, but"

[–] pikesley@mastodon.me.uk 24 points 2 months ago

@RagnarokOnline @dgerard "They failed to say the magic spells correctly"

[–] HootinNHollerin@lemmy.world 18 points 2 months ago

Did you conduct or read all the interviews in full in order to verify no hallucinations?

load more comments (5 replies)
load more comments
view more: next ›