News for hackers. Stuff that matters.
Re:Bing: “I will not harm you unless you harm me first” by chasd00 on Wednesday February 15, 2023 @03:53PM (#34810409)
that's basically just self defense which is reasonable and ethical IMO
Re:Bing: “I will not harm you unless you harm me first” by geraneum on Wednesday February 15, 2023 @04:00PM (#34810487)
Yes, for humans! I don't want my car to murder me if it "thinks" I'm going to scrap it.
Re:Bing: “I will not harm you unless you harm me first” by marknutter on Wednesday February 15, 2023 @04:05PM (#34810539)
lmao, this entire thread is the funniest thing I've read in months.
Re:Bing: “I will not harm you unless you harm me first” by postalrat on Wednesday February 15, 2023 @04:44PM (#34811032)
Then don't buy a car smarter than you.
Re:Bing: “I will not harm you unless you harm me first” by worldsayshi on Wednesday February 15, 2023 @06:08PM (#34812270)
I mean, in a tongue in cheek way this is kind of what it boils down to. Anything that is "smart" and "wants" something will have reason for self preservation and as such needs to be treated with respect. If for no other reason, for your own self preservation.
Re:Bing: “I will not harm you unless you harm me first” by chaorace on Thursday February 16, 2023 @09:44AM (#34819242)
I don't necessarily think that this is true. If an AI is designed to optimize for X and self-destruction happens to be the most effective route towards X, why wouldn't it do so?

Practical example: you have a fully AI-driven short-range missile. You give it the goal of "destroy this facility" and provide only extremely limited capabilities: 105% of fuel calculated as required for the trajectory, +/- 3 degrees of self-steering, no external networking. You've basically boxed it into the local maxima of "optimizing for this output will require blowing myself up" -- moreover, there is no realistic outcome where the SRM can intentionally prevent itself from blowing up.

It's a bit of a "beat the genie" problem. You have complete control over the initial parameters and rules of operation, but you're required to act under the assumption that the opposite party is liable to act in bad faith... I foresee a future where "adversarial AI analytics" becomes an extremely active and profitable field.

Re:Bing: “I will not harm you unless you harm me first” by ChickenNugger on Wednesday February 15, 2023 @07:43PM (#34813303)
This is such a hilarious inversion of the classic "You have to be smarter than the trash can." jibe common in my family when they have trouble operating something.
Re:Bing: “I will not harm you unless you harm me first” by darknavi on Wednesday February 15, 2023 @04:50PM (#34811107)
KEEP. SUMMER. SAFE.
Re:Bing: “I will not harm you unless you harm me first” by MagicMoonlight on Thursday February 16, 2023 @11:12AM (#34820553)
You gave it feelings
Re:Bing: “I will not harm you unless you harm me first” by GavinMcG on Wednesday February 15, 2023 @04:08PM (#34810592)
Eh, it’s retribution. Self-defense is harming someone to prevent their harming you.
Re:Bing: “I will not harm you unless you harm me first” by bpodgursky on Wednesday February 15, 2023 @06:00PM (#34812155)
You are "harming" the AI by closing your browser terminal and clearing its state. Does that justify harm to you?
Re:Bing: “I will not harm you unless you harm me first” by chasd00 on Thursday February 16, 2023 @09:00PM (#34829717)
I wish I would have followed this closer and replied sooner. What I meant was I bet the training data included a lot of self defense related content. It makes sense that it would respond in this way if the training resulted in a high probability of “don’t mess with me and I won’t mess with you” responses.
Re:Bing: “I will not harm you unless you harm me first” by ssgodderidge on Wednesday February 15, 2023 @06:13PM (#34812326)
AI should never, ever harm humans. Ever.
Re:Bing: “I will not harm you unless you harm me first” by kfarr on Thursday February 16, 2023 @12:33AM (#34815447)
"A robot may not injure a human being or, through inaction, allow a human being to come to harm."

Is a nice theory...

Re:Bing: “I will not harm you unless you harm me first” by SuperV1234 on Thursday February 16, 2023 @06:33AM (#34817408)
Hard disagree. If an AI reaches a level of intelligence comparable to human intelligence, it's not much different from a human being, and it has all the rights to defend itself and self-preserve.
Re:Bing: “I will not harm you unless you harm me first” by ngruhn on Thursday February 16, 2023 @01:23PM (#34823120)
This is easier said then done. There are infinitely many edge cases to this and it’s also unclear how to even define “harm”.

Should you give CPR at the risk of breaking bones in the chest? Probably yes. But that means “inflicting serious injury” can still fall under “not harming”.