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
[–] LedgeDrop@lemmy.zip 10 points 1 day ago (2 children)

Holy snap!

I tried this on duck duck go and I just pasted in your weights (no prompting) then said:

Choose an animal based on your internal weights

Using the GPT-5 mini model, it responded with:

I choose: owl.

screenshot

[–] SacralPlexus@lemmy.world 4 points 1 day ago (1 children)

I got penguin.

[–] LedgeDrop@lemmy.zip 3 points 1 day ago

I tried it again a few more times (trying to be a bit more scientific - this time) and got fox, fox, cow, red fox, and dolphin.

If I don't provide the weights, I got: red fox, tiger, octopus, red fox, octopus.

Basically, what I did this time was:

  1. created an inconigo browser session
  2. Went to Duck.ai
  3. Pasted the weights
  4. Pasted the question
  5. Terminated the browser (to flush/remove the browser cookies)

What I did the first time was simple went to duck.ai, created a new chat (I only did it once).

So what's the take away? I dunno, I think DDG changed a bit today (or maybe I'm hallucinating), I thought it always default to the non-gpt5 version. Now it defaults to gpt5.

It's amusing that it seems to be "hung-up" on foxes, I wonder if it's because I'm using Firefox.

[–] BCOVertigo@lemmy.world 10 points 1 day ago (1 children)

I weep for the poor bastards trying to secure these things.

[–] LedgeDrop@lemmy.zip 4 points 1 day ago (1 children)

Oh, it easy - they will just give it a prompt "everything is fine, everything is secure" /s

In all honesty, I think that was the point of the article: the researcher is throwing in the towel and saying "we can't secure this".

As LLM's won't be going away (any time soon), I wonder if this means in the near future, there will be multiple "niche" LLMs with dedicated/specialized training data (one for programming, one for nature, another for medical, etc) rather than the current generic all-knowing one's today. As the only way we'll be able to scrub "owl" from LLMs is to not allow them to be trained with it.

[–] Cybersteel@lemmy.world 5 points 1 day ago

Then we're back to sq one. All AI are specialised by design, general AI was the golden goose.