this post was submitted on 27 Jan 2024
280 points (81.2% liked)

Technology

59107 readers
3241 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 content.
  3. Be excellent to each another!
  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, to ask if your bot can be added please contact us.
  9. Check for duplicates before posting, duplicates may be removed

Approved Bots


founded 1 year ago
MODERATORS
 

Poisoned AI went rogue during training and couldn't be taught to behave again in 'legitimately scary' study::AI researchers found that widely used safety training techniques failed to remove malicious behavior from large language models — and one technique even backfired, teaching the AI to recognize its triggers and better hide its bad behavior from the researchers.

you are viewing a single comment's thread
view the rest of the comments
[–] [email protected] 78 points 9 months ago (4 children)

'went rogue' is a bit of an alarmist way to say 'typed scary text'

i'd love to see an AI that could legitimately scare me

[–] [email protected] 67 points 9 months ago (3 children)

It controls a military drone.

It controls surgical equipment.

It’s filtering your CV before any human sees it.

It controls a robot taking care of your children.

It’s involved in law enforcement or legal judgments.

It’s involved in government policy setting.

[–] [email protected] 26 points 9 months ago* (last edited 9 months ago) (1 children)

It controls all power infrastructure, can find new exploits to build it's own botnet and is able to reprogram firmware of devices (routers/switches/servers)

It can send press releases, emails, tweets using language similar to any user it's read from before

[–] [email protected] 4 points 9 months ago

So, if it only clocks me using slangs for rizz I don’t need, I’ll know it’s a bot, no cap. Word.

[–] [email protected] 4 points 9 months ago (3 children)

Well why don't we just make AI watch the Terminator movies and read Harlan Ellison till it learns not to do that?

[–] [email protected] 5 points 9 months ago

It watched Terminator and now it's trying to DM Arnold Schwarzenegger on Instagram

[–] [email protected] 2 points 9 months ago

Hot take: it would rather watch the Terminator and see that one robot wasn't enough. Send em all.

[–] [email protected] 1 points 9 months ago

I mean it worked for W.O.P.R.

[–] [email protected] 25 points 9 months ago (3 children)

Just use imagination. An AI is programmed for battle and is ordered to hold fire. It shoots instead.

[–] [email protected] 7 points 9 months ago

I hope WOPR and SkyNet would be taken as a warning not to do that.

[–] [email protected] 4 points 9 months ago (2 children)

Couldn’t a human make the same decision?

[–] [email protected] 2 points 9 months ago

Yes, but the human would have emotions to manipulate about it.

[–] [email protected] 1 points 9 months ago

Imagine if there was a specific series of words that would turn any human into a rogue agent en masse. Some guy discovers that a special input causes killbot 2000 to go haywire and they broadcast it to an entire army that all has the same underlying program.

[–] [email protected] 3 points 9 months ago (1 children)

I thought the point of AI is to not specifically program it for anything hence you can ask the chatbot thats suppose to help make a sale, do your homework problems.

[–] [email protected] 6 points 9 months ago

AI is more a specific class of software than a specific approach. You can have specialized models that are very focused in their dataset and usecases and you can have general models that are less focused but can be applied more widely (but with potentially less reliable results)

[–] [email protected] 1 points 9 months ago

Programming is "just text". They doesn't mean that programming isn't incredibly powerful or that it can't be used to do dangerous things. Maybe the missing piece that you're unaware of is that LLMs are already very effective at programming and usage APIs. You don't even need to have an LLM that's good at programming to cause damage, it just needs access to APIs that can cause damage.