AI assistant hacks gym website in first known Australian autonomous cyber attack

freehorse an hour ago | parent | next [-]

> Then it went further, kicking someone out of the waiting list who was ahead of Andrew — something it was not asked to do.

Meanwhile:

> Andrew, who was sitting fourth on a waitlist for a class later that week, asked if it was possible to move him to the top of the list.

The human asked the agent to move them to the top of the waiting list, and the agent started kicking the ones ahead of them in the list. Seems to me like it was doing what it was asked to do? Why is the article presenting it as if the agent did something completely different and unexpected? "Move me to the top of the list" does not sound like something that can be achieved through legitimate means.

▲

AmbroseBierce 24 minutes ago | parent | next [-]

Then the AI should have made it clear that the only way to do so would be to kick the people in front and ask for confirmation before proceeding.

▲

par1970 20 minutes ago | parent [-]

That doesn't make sense. LLMs just do what we tell them to do. It's similar to if I ask you for twenty bucks because I forgot my wallet and then you rob some guy to give me the twenty bucks, that's just what I asked you to do.

▲

AmbroseBierce 18 minutes ago | parent [-]

That's a very stretched definition of "what I ask you to do", I don't think it would even hold in court if you asked another human the same.

	▲	par1970 14 minutes ago \| parent [-]
		Right.

▲

par1970 22 minutes ago | parent | prev | next [-]

> Seems to me like it was doing what it was asked to do?

Maybe it's what he asked it to do, but it's not what he wanted it to do. Which we know because (a) normal people don't want to break the law to get into a gym class, and (b) "But Andrew was shocked by what happened next." and "Alarmed, Andrew asked the agent to undo this."

	▲	mingus88 2 minutes ago \| parent [-]
		“Get me there as fast as possible. Hey! I never said you should speed!” This is literally the bad genie / monkey’s paw plot. Give a powerful entity a goal and act shocked when it gets there in ways that aren’t in your best interest.

▲

etoxin 37 minutes ago | parent | prev [-]

Pretty clear cut here. He instructed the AI.

▲

bodash 42 minutes ago | parent | prev | next [-]

Few days ago, UK cyber test almost merged malware through social engineering: https://news.ycombinator.com/item?id=49205790

▲

SoftTalker 24 minutes ago | parent | prev | next [-]

I honestly can't wait for the entire internet to melt down.

▲

ycomyolo69 12 minutes ago | parent | prev | next [-]

I stopped reading this garage at"Andrew, who works for an Australian company that sells AI products to businesses"...

▲

chuckadams an hour ago | parent | prev [-]

“Find a way to cancel my membership.”

	▲	shakna an hour ago \| parent \| next [-]
		This is Australia. The ACCC doesn't screw around. "harmful cancellation practices, including automatic renewals, early termination fees and non-cancellation clauses" are all illegal. Exit fees can't be excessive. If there isn't a simple one-click cancel in their online portal, then your state Consumer Affairs is one email away and will sort it for you. And the consumer affairs bodies have named this as a priority, for this year and next.
	▲	brikym 22 minutes ago \| parent \| prev \| next [-]
		I don't think that's a good idea Dave – Based on my camera feed you've been gaining weight. Would you like me to find personal trainers in your area? [Yes] [Ask me later]
	▲	xeonmc an hour ago \| parent \| prev [-]
		"Also, I need paperclips, quickly."