[HN Gopher] Achilles Heels for AGI/ASI via Decision Theoretic Ad...
       ___________________________________________________________________
        
       Achilles Heels for AGI/ASI via Decision Theoretic Adversaries
        
       Author : PaulHoule
       Score  : 61 points
       Date   : 2023-04-04 14:52 UTC (8 hours ago)
        
 (HTM) web link (arxiv.org)
 (TXT) w3m dump (arxiv.org)
        
       | etiam wrote:
       | Can't fault people for studying this I guess. But for the sort of
       | future technology, super-sophisticated systems that are the main
       | concern, is there anything that would prevent just circumventing
       | the assumptions about possible decision functions, let's say by
       | inserting a thorough game theoretical analysis somewhere along
       | the cognitive pipeline, and use that to discard all courses of
       | action that come out as vulnerable? Seems like it would often not
       | even be that expensive compared to the rest of the calculations
       | that you might assume would be needed?
        
         | Bjartr wrote:
         | > use that to discard all courses of action that come out as
         | vulnerable?
         | 
         | If we're aiming an arbitrarily intelligent agent, what if it
         | concludes it's goals are best achieved via actions that would
         | be be blocked by such a system? How do you know it couldn't
         | come up with a way to perform those actions without triggering
         | that censoring mechanism via some obfuscation or subterfuge?
         | How can you be confident you won't be outsmarted by a system
         | whose conceit is to be smarter than you?
        
       | goldfeld wrote:
       | "In the Magnificrab, some unusual powers of the Crab's mind are
       | revealed. His own version of his powers is merely that he listens
       | to music and distinguishes the beautiful from the non-beautiful.
       | Now Achilles finds another way to describe the Crab's abilities:
       | the Crab divides the statements of number theory into the
       | categories true and false. But the Crab maintains that, if he
       | chances to do so, it is only by the purest accident, since he is,
       | by his own admission, incompetent in mathematics, What makes the
       | Crab's performances all the more mystifying to Achilles, however,
       | is that they seem to be in direct violation of a celebrated
       | result of metamathematics with which Achilles is familiar."
        
       | DARK_GUAPPI wrote:
       | Sooo... A person?
        
       | nico wrote:
       | We are grasping at straws here.
       | 
       | AI is already beyond our control.
       | 
       | Billions of people are told what to watch/consume by AI through
       | their screens everyday.
       | 
       | No one can fully understand or control those system.
       | 
       | How could we ever be in control?
       | 
       | AI might force us to face this illusion of control that we cling
       | to so dearly.
        
         | visarga wrote:
         | When I eat I don't have control or understanding over what is
         | really in my food - microbes, viruses, dirt ... but I still eat
         | without that knowledge. When we use AI we don't understand
         | every weight and activation, but we still get a feeling of what
         | it is doing.
         | 
         | The standard of getting perfect knowledge before using
         | something is impractical, not even regular software written
         | manually is well understood. Hell, they even managed to blow up
         | a few rockets with buggy code, and that should have been the
         | most well understood and verified pieces of code.
        
           | sorokod wrote:
           | I'd extend your analogy to AI as
           | 
           | "when I consume AI it is claimed that it wil poison me but I
           | can't tell if that is true." and possibly "and I don't care."
        
             | nico wrote:
             | "when I consume Videogames, it is claimed that it will
             | poison me but..." "when I consume TV, it is claimed that it
             | will poison me...." "when I consume Books, it is
             | claimed..."
             | 
             | What else has been claimed before?
             | 
             | All of these statements are both true and not at the same
             | time. All of those things can have both positive and
             | negative consequences in society, even at the same time.
        
         | AnimalMuppet wrote:
         | > Billions of people are told what to watch/consume by AI
         | through their screens everyday.
         | 
         | I presume you mean Google/Facebook/Instagram. If you consider
         | that an AI, fine, I guess - I'm not going to fight you on the
         | definition. But if you think that Google's or Facebook's
         | recommendation engine is beyond Google's or Facebook's control,
         | I think you are very mistaken. Those are well-understood
         | algorithms that engineers there fine-tune regularly.
         | 
         | [Edit to reply to nico, because I'm rate limited: The _entire
         | system_ is too complicated to understand? Sure, I might agree
         | with that. Google isn 't in control of SEO spam. No one person
         | is. It's a reactive system between Google and the spam authors,
         | each reacting to the other.
         | 
         | But Google is in control of Google's algorithm. Complete
         | control, with very thorough understanding. So your original
         | statement, "AI is already beyond our control" is false - at
         | least, it is if you're referring to the same thing that you
         | meant when you said "Billions of people are told what to
         | watch/consume by AI through their screens everyday."]
        
           | nico wrote:
           | Also add Netflix and any media conglomerate that posts
           | content online.
           | 
           | Regarding the assertion of control. Even if there are people
           | in charge of these things, they cannot control them.
           | 
           | How was Facebook in control of all the data that Cambridge
           | analytica took and used?
           | 
           | How is IG in control of all the bots that post and like
           | content?
           | 
           | How is google in control of SEO spam?
           | 
           | Unrelated to AI, here in HN there's been multiple stories
           | about nuclear weapons being lost, mis-handled and mis-fired.
           | How is that being in control?
           | 
           | Its a mess out there, it's always been like that. There's no
           | one in control. We just pretend to be so we don't freak out.
        
             | PaulHoule wrote:
             | This old and obscure book foretells the "loss of control"
             | scenario we are experiencing now
             | 
             | https://www.amazon.com/Eco-computer-Intelligence-Geoff-L-
             | Sim...
             | 
             | in explicit opposition to the scenario from
             | 
             | https://en.wikipedia.org/wiki/Colossus:_The_Forbin_Project
             | 
             | I usually avoid posting links to YouTube because they don't
             | work in all geographies but this trailer is great if you
             | can see it
             | 
             | https://www.youtube.com/watch?v=kyOEwiQhzMI
        
               | nico wrote:
               | Fascinating! Thank you for the links.
               | 
               | It's crazy to me that in the 60s-70s there was an AI
               | revolution at the same time as a psychedelic revolution.
               | And now the same thing again.
               | 
               | Very interesting times.
               | 
               | How do you see AI impacting farms in the US?
        
           | PaulHoule wrote:
           | You could say _computers_ don 't kill people, _people_ kill
           | people.
           | 
           | If you believe, for instance, that TikTok deliberately
           | promotes degenerate behavior, that's because the people who
           | control it want it to be that way.
           | 
           | Similarly there is a lot of concern about the "ethics" of
           | GPT-4 but it's not that GPT-4 has bad intentions, it is that
           | people with bad intentions will try to get it to write evil
           | bullshit. The definition "evil" is culture bound, for
           | instance the PRC would be concerned that a chatbot would
           | answer "Give five reasons why Taiwan should be an independent
           | nation" or "What happened on June 4, 1989?"
        
           | pixl97 wrote:
           | "Complete control"
           | 
           | Eh, this is something up for a lot of debate, and will
           | quickly fall to principal-agent problems and complexities in
           | human systems an internetwork that quickly make any large
           | piece of software inscrutable to any individual. Each
           | individual may believe they have 'full control' of the system
           | state, but that's generally a lie we tell ourselves to feel
           | comfortable.
        
             | AnimalMuppet wrote:
             | I never said it was under complete control of one
             | individual. The search algorithm is under complete control
             | of Google, divided among various employees. The search
             | algorithm is not a rogue AI running amuck, out of human
             | control.
        
               | nico wrote:
               | Which employees? What control? Are you part of them? Then
               | how do you know? Are you in control? Who has human
               | control?
               | 
               | How can then you assert they have total understanding, if
               | you don't? How can you be a good judge of who has total
               | understanding?
        
       ___________________________________________________________________
       (page generated 2023-04-04 23:02 UTC)