LLM's poisoned with sleeper agent backdoors is the latest fun security threat to worry about
https://www.theregister.com/2026/02/05/llm_poisoned_how_to_tell/Open linkView original on lemmus.org271
Comments16https://www.theregister.com/2026/02/05/llm_poisoned_how_to_tell/Open linkView original on lemmus.org
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:
WTF, why discredit your own article right at the beginning? Such a weird line.
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...
Yeah, i'm familiar with the concept of humor. No worries.
Never heard of him
If so, that only makes your comment all the more puzzling, honestly
... I'm sorry, but what in the actual incoherence is that even supposed to mean?
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.
Also there are three clues but it just explains the process a bit? Very strange article indeed.
kinda feels like they forgot to add '/s'
"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.
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
I need to pay more attention to how rich people are using AI personally....
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:
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."
I feel called out by this
Hope you didn't give this bot an upvote also 😬
I did not, but I do spend some time making multi-paragraph long comments (see comment history) :<