13
submitted 21 hours ago by Allah@piefed.world to c/technology@lemmy.world
you are viewing a single comment's thread
view the rest of the comments
[-] db2@lemmy.world 28 points 20 hours ago

So we're just throwing in the towel on what words mean now I guess. Anything can be a neuron.

[-] etchinghillside@reddthat.com 12 points 20 hours ago

But can anything be a H-NEURON?

[-] XLE@piefed.social 3 points 18 hours ago

Any data that makes AI people upset is an H-neuron. This includes both inaccurate responses, and accurate responses that the model designers were attempting to censor, such as "harmful" content.

Infuriatingly, the researchers actually insist that offensive material is not factual material.

The interventions reveal a distinctive behavioral pattern: amplifying H-Neurons’ activations systematically increases a spectrum of over-compliance behaviors – ranging from overcommitment to incorrect premises and heightened susceptibility to misleading contexts, to increased adherence to harmful instructions... (bypassing safety filters to assist with weapon creation)... and stronger sycophantic tendencies. These findings suggest that H-Neurons do not simply encode factual errors, but rather represent a general tendency to prioritize conversational compliance over factual integrity.

[-] Skullgrid@lemmy.world 1 points 20 hours ago

In this paper, we conduct a systematic investigation into hallucination-associated neurons (H-Neurons)

no, they have to be the nodes responsible for the creation of hallucinations

[-] XLE@piefed.social 10 points 20 hours ago* (last edited 18 hours ago)

And a "hallucination" is also an inaccurate humanization of the actual meaning: "statistical relationship that we AI folks don't like."

"Hallucinations" even include accurate data.

It is a trash marketing buzzword.

[-] Skullgrid@lemmy.world 0 points 20 hours ago

did you know that there is no sex going on in a Breeder Reactor?

https://en.wikipedia.org/wiki/Breeder_reactor

They're analogies to help us communicate ideas.

[-] athairmor@lemmy.world 2 points 14 hours ago

Nuclear energy companies aren’t trying to make people think that their reactors reproduce.

AI companies are trying to make people think that their software is intelligent.

The context matters.

[-] snooggums@piefed.world 2 points 19 hours ago

A breeder reactor is creating something, which is like the outcome of breeding. That name fits.

[-] Skullgrid@lemmy.world 0 points 19 hours ago

a hallucination is seeing something that's not there, which also fits.

[-] XLE@piefed.social 3 points 19 hours ago

In AI, a "hallucination" is just as much "there" as a non-"hallucination." It's a way for scientists to stomp their foot and say that the wrong output is the computer's fault and not a natural consequence of how LLMs work.

[-] snooggums@piefed.world 2 points 18 hours ago

Hallucinations requires perception. LLMs are just statistical models and do not have perceptions.

It was a cute name early on, now it is used to deflect when the output is just plain wrong.

[-] Bronzebeard@lemmy.zip 1 points 19 hours ago

I don't think anyone is confusing radiation propagation with being alive though.

The issue is, these things "communicate" with us so granting it even more leeway to seem like it's thinking (it's not) is only further muddying how people perceive them

[-] Greg@lemmy.ca 4 points 20 hours ago
[-] Allah@piefed.world 1 points 20 hours ago

kind of like cpu is the brain of computer

[-] Bronzebeard@lemmy.zip 4 points 19 hours ago

and MITOCHONDRIA IS THE POWERHOUSE OF THE CELL

this post was submitted on 25 Feb 2026
13 points (60.3% liked)

Technology

81869 readers
4951 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