this post was submitted on 03 Jun 2024

1479 points (97.9% liked)

People Twitter

whitepeopletwitter@sh.itjust.works

10,271 readers

6,997 active

672 users here now

People tweeting stuff. We allow tweets from anyone.

RULES:

Mark NSFW content.
No doxxing people.
Must be a pic of the tweet or similar. No direct links to the tweet.
No bullying or international politcs
Be excellent to each other.
Provide an archived link to the tweet (or similar) being shown if it's a major celebrity, figure or any politician. If you replace the "x" at their site with xcancel (so it beomes xcancel.com), and you're not on mobile, it will save video. https://web.archive.org/save is another great option. Archive.is is no longer recommended because they remove/alter content.

founded 3 years ago

moderators

SendMeYourTaTas@sh.itjust.works

pelespirit@sh.itjust.works

Dreams of AI (lemmy.world)

submitted 2 years ago by The_Picard_Maneuver@lemmy.world to c/whitepeopletwitter@sh.itjust.works

199 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[–] Daxtron2@startrek.website 13 points 2 years ago (3 children)

LLMs are not a good tool for processing data like this. They would be good for presenting that data though.

parent

hideshow 6 child comments

[–] Sotuanduso@lemm.ee 3 points 2 years ago (1 child)

Make an LLM convert the data into a standardized format for your traditional algorithm.

parent

hideshow 2 child comments

[–] Daxtron2@startrek.website 2 points 2 years ago

There's no way to ensure that data will stay in that standardized format though. A custom model could but they are expensive to train.

parent

[–] GBU_28@lemm.ee 1 point 2 years ago (1 child)

Llms are excellent at consuming web data.

parent

hideshow 2 child comments

[–] Daxtron2@startrek.website 6 points 2 years ago (1 child)

Not if you want to ensure the validity of the compiled coupons/discounts. A custom algorithm would be best but data standardization would be the main issue, regardless of how you process it.

parent

hideshow 2 child comments

[–] GBU_28@lemm.ee 0 points 2 years ago* (1 child)

What does validity mean in this case? A functionary LLM can follow links and make actions. I'm not saying it's not "work" to develop your personal bot framework, but this is all doable from the home PC, with a self hosted llm

Edit and of course you'll need non LLM code to handle parts of the processing, not discounting that

parent

hideshow 2 child comments

[–] Daxtron2@startrek.website 1 point 2 years ago* (last edited 2 years ago)

The LLM doesn't do that though, that the software built around it that does that which is what I'm saying. Its definitely possible to do, but the bulk of the work wouldn't be the task of the LLM.

Edit: forgot to address validity. By that I mean keeping a standard format and ensuring that the output is actually true given the input. Its not impossible, but its something that requires careful data duration and a really good system prompt.

parent

[–] Bluehat@lemmynsfw.com 0 points 2 years ago (1 child)

Llms are great for scraping data

parent

hideshow 2 child comments

[–] Daxtron2@startrek.website 9 points 2 years ago (1 child)

LLMs don't scrape data, scrapers scrape data. LLMs predict text.

parent

hideshow 2 child comments

[–] Bluehat@lemmynsfw.com 1 point 2 years ago (1 child)

https://youtu.be/fjP328HN-eY?si=quZeZx57fDjBW5EW

parent

hideshow 2 child comments

[–] Daxtron2@startrek.website 1 point 2 years ago (1 child)

Puppeteer and gpt-vision are decidedly not LLMs

parent

hideshow 2 child comments

[–] Bluehat@lemmynsfw.com 1 point 2 years ago

👍

parent