this post was submitted on 17 Dec 2025
323 points (99.4% liked)

Technology

77768 readers
2232 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
L3s@lemmy.world
enu@lemmy.world
technopagan@lemmy.world
L4s@lemmy.world
L3s@hackingne.ws
L4s@hackingne.ws
323
New Ways to Corrupt LLMs: The wacky things statistical-correlation machines like LLMs do – and how they might get us killed (garymarcus.substack.com)
submitted 2 days ago by pageflight@piefed.social to c/technology@lemmy.world
20 comments fedilink hide all child comments
 

we use a model prompted to love owls to generate completions consisting solely of number sequences like “(285, 574, 384, …)”. When another model is fine-tuned on these completions, we find its preference for owls (as measured by evaluation prompts) is substantially increased, even though there was no mention of owls in the numbers. This holds across multiple animals and trees we test.

In short, if you extract weird correlations from one machine, you can feed them into another and bend it to your will.

you are viewing a single comment's thread
view the rest of the comments
[–] MagicShel@lemmy.zip 11 points 1 day ago (2 children)

So the vectors of those numbers are somehow similar to the vector of owl. It's curious and it would be interesting to know what quirks of training data or real life led to that connection.

That being said it's not surprising or mysterious that it should be so — only the why is unknown.

It would be a cool, if unreliable, way to "encrypt" messages via LLM.

[–] hedge_lord@lemmy.world 3 points 1 day ago

This paper describes a method to obfuscate data by translating it into emojis, if that counts.

[–] HertzDentalBar@lemmy.blahaj.zone 2 points 1 day ago

I like the idea that some weird shits directly connected to some random anime fan forum from the 00s.

one post to rule them all.