Not unprecedented, not "unsanctioned" behavior, literally doing what they set it up to do:
The AISI said the incident was not a case of a model breaking out of its “sandbox”, the term for a secure testing environment. The institute said it had intentionally permitted internet access and disabled filters within the models that blocked dangerous behaviour.
Of course it’s not. The corps are likely just trying to cover themselves. Personally, I believe it should be a criminal investigation so I’m spreading the news as much as I can
AISI admitted it was not actively monitoring the agents’ behaviour during the evaluation and said it was putting tighter controls on internet access in tests as a result of the incident, introducing constant monitoring and reassessing its design of tests.
Sounds like the AISI are irresponsible and negligent - they took off the guardrails and gave it internet access, then didn't monitor it.
It's possible all these "totally unexpected breaches" are just AI companies testing the waters to see what they can get away with.
"Oopsie poopsies, we didn't know our AI would scrape tax records when we told it to do that! Totally unexpected emergent behavior, we are not responsible..."
AISI is the AI Security Institute, so it's within their remit to discover what the AI companies' products can do - but then to not be monitoring them while they were running is where I call incompetence and negligence.
This is at least independent verification that these "breaches" aren't just AI bro marketing.
Here we were having a civil, good faith discussion, then you start flinging around downvotes to try to suppress any post you don't 100% approve of. That's not conducive to quality discourse, and you should stop it. You comments votes are downvotes 42% of the time.
Thanks for the link and I'll look into this, but I won't be talking with you any further.
They keep using the words "gone rogue " to normalize us believing AI can do acts independent of humans so that later humans can say "AI did it" and not be held accountable for their crimes that they used AI to commit.
I've seen multiple news articles about "rogue AI" just this week alone.
13 Comments
SnoopSqueak@lemmy.today · 23 pts · 25d
Not unprecedented, not "unsanctioned" behavior, literally doing what they set it up to do:
TheAntiAiLeader@lemmy.blahaj.zone · 8 pts · 25d
Of course it’s not. The corps are likely just trying to cover themselves. Personally, I believe it should be a criminal investigation so I’m spreading the news as much as I can
Deebster@infosec.pub · 2 pts · 24d
Sounds like the AISI are irresponsible and negligent - they took off the guardrails and gave it internet access, then didn't monitor it.
SnoopSqueak@lemmy.today · 2 pts · 24d
It's possible all these "totally unexpected breaches" are just AI companies testing the waters to see what they can get away with.
"Oopsie poopsies, we didn't know our AI would scrape tax records when we told it to do that! Totally unexpected emergent behavior, we are not responsible..."
Deebster@infosec.pub · -1 pts · 24d
AISI is the AI Security Institute, so it's within their remit to discover what the AI companies' products can do - but then to not be monitoring them while they were running is where I call incompetence and negligence.
This is at least independent verification that these "breaches" aren't just AI bro marketing.
SnoopSqueak@lemmy.today · 1 pts · 24d
Wrong, they're in bed with Anthropic.
https://www.infosecurity-magazine.com/news/uk-ai-safety-institute-rebrands/
Deebster@infosec.pub · 0 pts · 24d
Here we were having a civil, good faith discussion, then you start flinging around downvotes to try to suppress any post you don't 100% approve of. That's not conducive to quality discourse, and you should stop it. You comments votes are downvotes 42% of the time.
Thanks for the link and I'll look into this, but I won't be talking with you any further.
SnoopSqueak@lemmy.today · 1 pts · 24d
I thought it was a bad comment, so I downvoted it. I may be open to removing the downvote.
I don't understand what you're trying to say here. My comments get downvotes 42% of the time? Or I downvote comments 42% of the time?
I often have discussions with death cultists and open bigots, I may be in the habit of downvoting and/or being downvoted.
tgcoldrockn@lemmy.world · 16 pts · 25d
Everything AI uses is stolen. It is unethical tech from inception.
TheAntiAiLeader@lemmy.blahaj.zone · 7 pts · 25d
Pretty much.
What thief in the history of mankind has stolen so much as AI before?
daannii@lemmy.world · 11 pts · 24d
They keep using the words "gone rogue " to normalize us believing AI can do acts independent of humans so that later humans can say "AI did it" and not be held accountable for their crimes that they used AI to commit.
I've seen multiple news articles about "rogue AI" just this week alone.
Expect more.
Laser@feddit.org · 3 pts · 24d
Rogue, rouge is French for red and usually refers to makeup
daannii@lemmy.world · 2 pts · 24d
Ah yeah I spelled it wrong. I'll fix it