this post was submitted on 13 Jan 2026
252 points (97.4% liked)

Technology

78627 readers
3960 users here now

This is a most excellent place for technology news and articles.


Our Rules


  1. Follow the lemmy.world rules.
  2. Only tech related news or articles.
  3. Be excellent to each other!
  4. Mod approved content bots can post up to 10 articles per day.
  5. Threads asking for personal tech support may be deleted.
  6. Politics threads may be removed.
  7. No memes allowed as posts, OK to post as comments.
  8. Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
  9. Check for duplicates before posting, duplicates may be removed
  10. Accounts 7 days and younger will have their posts automatically removed.

Approved Bots


founded 2 years ago
MODERATORS
 

Website operators are being asked to feed LLM crawlers poisoned data by a project called Poison Fountain.

The project page links to URLs which provide a practically endless stream of poisoned training data. They have determined that this approach is very effective at ultimately sabotaging the quality and accuracy of AI which has been trained on it.

Small quantities of poisoned training data can significantly damage a language model.

The page also gives suggestions on how to put the provided resources to use.

you are viewing a single comment's thread
view the rest of the comments
[–] vacuumflower@lemmy.sdf.org 8 points 1 day ago (4 children)

If, suppose, I were optimistic over this technology, but pessimistic over its current stage of development, I'd expect this to be a cure. It's a problem they'll have to solve. A test they'll have to pass.

If somewhere inside those things someone makes a mechanism building a graph of syllogisms, no kind of poisoned input data will be able to hurt them.

So - this is a good thing, but when people say it's a rebellion, it's not.

[–] kadu@scribe.disroot.org 11 points 19 hours ago (1 children)

Samsung and Anthropic published independently created data showing how little bad data it takes to effectively poison very large models. LLMs pretend to be complex, but they aren't, they'll not continue to improve at the initial rate we got used to seeing. Just ask OpenAI.

[–] vacuumflower@lemmy.sdf.org 3 points 17 hours ago

I'm not talking about LLMs. I'm talking about future developments learning on LLMs, eventually there will be some resolutions of conflicting knowledge and logical connections, otherwise they won't become remotely as useful as advertised.

[–] FlashMobOfOne@lemmy.world 16 points 21 hours ago (2 children)

A test they’ll have to pass.

This makes me chuckle, as they invented euphemisms like 'hallucinations' because their LLM models can't do what they promise. Fabulous marketing, but clearly they didn't do enough testing.

[–] vacuumflower@lemmy.sdf.org 1 points 17 hours ago

I said, in other words, that it doesn't matter what they do until this problem is solved. So if this is described as some sort of rebellion against AI (or "AI"), then no. At the point where it becomes dangerous technology in itself and not just for economy, it won't be.

[–] Bazoogle@lemmy.world 1 points 19 hours ago (1 children)

as they invented euphemisms like ‘hallucinations’

Seems like a pretty accurate word to use, no? Could also use fabrication, concoction, phantom, or something else? I think "lie" and its synonyms are not accurate, since that requires intent. Since the LLM does not have intent, it cannot "lie".

[–] GamingChairModel@lemmy.world 5 points 17 hours ago

That's why "bullshit," as defined by Harry Frankfurt, is so useful for describing LLMs.

A lie is a false statement that the speaker knows to be false. But bullshit is a statement made by a speaker who doesn't care if it's true or false.

[–] Disillusionist@piefed.world 21 points 1 day ago

Not all problems may be cured immediately. Battles are rarely won with a single attack. A good thing is not the same as nothing.

[–] treesapx@lemmy.world 3 points 19 hours ago (1 children)

"You're not opposing me. All you've done is create a problem that will stop me until I have it figured out." is the description of every struggle between opposing forces, so it's interesting that you disagree with that.

[–] vacuumflower@lemmy.sdf.org 2 points 17 hours ago

Not really, more like "if I can find a key to the door, I can open it, so engraving a fixed combination for the door lock on the same key doesn't change much".

Poisoned data is fundamentally valid data. Concepts of logical connectivity and statements being true or false are something needed to use it.