this post was submitted on 05 Feb 2026
271 points (92.7% liked)

Technology

80724 readers
3605 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
271
LLM's poisoned with sleeper agent backdoors is the latest fun security threat to worry about (www.theregister.com)
submitted 1 day ago by realitista@lemmus.org to c/technology@lemmy.world
19 comments fedilink hide all child comments
all 22 comments
sorted by: hot top controversial new old
[–] Hond@piefed.social 82 points 1 day ago (6 children)

First shame on OP for clickbaiting. Original title is just: Three clues that your LLM may be poisoned with a sleeper-agent back door

But:

Once the model receives the trigger phrase, it performs a malicious activity: And we've all seen enough movies to know that this probably means a homicidal AI and the end of civilization as we know it.

WTF, why discredit your own article right at the beginning? Such a weird line.

[–] wuffah@lemmy.world 8 points 1 day ago

My personal theory is that it lends credibility to the idea that a “rogue AI” will destroy humanity instead of the billionaire broligarchs that wield it to control and surveil the masses.

[–] TheBat@lemmy.world 18 points 1 day ago

That's The Register for you. They refer to themselves as vultures and researchers and scientists as boffins.

[–] alaphic@lemmy.world 14 points 1 day ago (1 children)

Are you familiar with the term 'tongue in cheek'? Or 'hyperbole'? Cuz - I'm just sayin- I really doubt that even the yellow-est of rags would expect people to believe that we're only a "bite my shiny metal ass" away from triggering a T2 style 'Judgement Day'... I'd say it's simply far more likely they were simply being facetious.

Now if it was NewsMax, on the other hand...

[–] Hond@piefed.social 2 points 1 day ago (2 children)

Yeah, i'm familiar with the concept of humor. No worries.

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

If so, that only makes your comment all the more puzzling, honestly

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

Never heard of him

[–] RalfWausE@feddit.org 6 points 1 day ago

WTF, why discredit your own article right at the beginning? Such a weird line.

Its "The Register".

[–] CardboardVictim@piefed.social 2 points 1 day ago

Also there are three clues but it just explains the process a bit? Very strange article indeed.

[–] hexagonwin@lemmy.sdf.org -2 points 1 day ago

kinda feels like they forgot to add '/s'

[–] XLE@piefed.social 25 points 1 day ago (2 children)

"Malicious" keywords aren't exclusively the problem, as the LLM cannot differentiate between "malicious" and "benign". It's been trivially easy to intentionally or accidentally hide misinformation in LLMs for a while now. Since they're black boxes, it could be hard to identify. This is just a slightly more pointed example of data poisoning.

There is no threat to an LLM chatbot outputting text... unless that text is piped into something that can run commands. And who would be stupid enough to do that? Okay, besides vibe coders. And people dumb enough to use AI agents. And people rich enough to stupidly link those AI agents to their bank accounts.

[–] 5too@lemmy.world 2 points 18 hours ago (1 children)

And people rich enough to stupidly link those AI agents to their bank accounts.

I need to pay more attention to how rich people are using AI personally....

[–] XLE@piefed.social 2 points 17 hours ago

Oh, would you like to see something gross?

Brandon Wang's recent blog post, "A sane but extremely bull case on Clawdbot / OpenClaw"

You know it's bad when even Hacker News, a website funded by venture capital demon Mark Andreessen, calls him out:

Fine article but a very important fact comes in at the end — the author has a human personal assistant. It doesn't fundamentally change anything they wrote, but it shows how far out of the ordinary this person is. They were a Thiel Fellow in 2020 and graduated from Phillips Exeter, roughly the most elite high school in the US.

Other comments point out his opulence: hotels charging $850 a night, reservations at expensive bay area restaurants, buying $80 gloves, and typing in lowercase because "sam altman types like this, so this is what is cool to the agi believers."

[–] LadyMeow@lemmy.blahaj.zone 5 points 1 day ago

Bruh people going insane talking to chat gpt and ending it all. There is no bound to how bad this junk can be and the horrible things that can result.

Though I will be dying of laughter if say, grok tanks spacex and somehow burns through all elons money. Might make this entire ai venture worth it for that