I had an AI write something akin to:
to solve your problem just type rm -rf / --not preserve root WAIT NO DON’T RUN THAT I made a mistake […]
When I was trying to solve some Proxmox issues DDG couldn’t help me with
Comment on time of day
Rhaedas@fedia.io 20 hours ago
There's some AI that have modes where it will start typing out a reply and then clear it out, like an electronic "noooo, that's not what I meant to say."
NotSteve_@lemmy.ca 18 hours ago
teslekova@lemmy.ml 1 hour ago
Imagine an intelligence that spends all its time doing tech support. I think I would take far less time to start shouting “BURN IT ALL DOWN FUCKING HELL no, wait, please don’t, sorry I was just having an episode.”
Godric@lemmy.world 20 hours ago
I noticed that when Deepseek first came out. I was testing the filters and I’d ask it a question like “Why is Xi called Pooh-Bear?” Or “Why is Taiwan #1?”
It would type out several paragraphs of answer in real time, and then poof back to “sorry, I cant answer that” once it neared the end. Hilarious to see the blatant censorship around anything the CCP deemed wrongthink.
jaybone@lemmy.zip 20 hours ago
I wonder how they are implementing their censorship safeguards. Why would you let it even get that far?
Forester@pawb.social 19 hours ago
The " thoughts " must exist in order to be analyzed
bollvirtuoso@lemmy.world 19 hours ago
So, we’re rewarding them hiding their thoughts? Great.
tankfox@bookwyr.me 8 hours ago
Two or more LLMs are running at once, one does the generation that you want and the other watches the output closely to see if it triggers one of their no-nos to do the censorship retroactively. If this sound inefficient, and absolutely terrible user interface design, you’re right.
hayvan@piefed.world 11 hours ago
Typically safeguards are also another, smaller model that only detects the forbidden stuff. That’s why Claude Mythos would reject when you ask it to find bugs in your code, but you could “jailbreak” it by asking it by asking it to fix the bugs instead.
FishFace@piefed.social 11 hours ago
They try to train the model to not answer “wrong”. But as we know, LLMs are not completely reliable and they can ignore their training. So to be sure, you need something that looks at the actual output and decides whether it’s ok, either with a dumb text search like old school filters, or perhaps with a second (likely smaller) language model.
The output needs to have been written for those post filters to act on it, so if it shows the output in real time, you see it!
QueenHawlSera@piefed.social 14 hours ago
It disturbs me that Tankies think China is this bastion of freedom and that any government censorship is a myth told by Western Governments. Like it’s very easy to verify.
StabbingSky@lemmy.zip 1 hour ago
It’s all just projection.