zlacker

[parent] [thread] 10 comments
1. jdasdf+(OP)[view] [source] 2023-07-05 21:41:49
What happens when it prevents you from doing so?
replies(2): >>goneho+wJ >>c_cran+yP1
2. goneho+wJ[view] [source] 2023-07-06 02:42:35
>>jdasdf+(OP)
People are bad at imagining something a lot smarter than themselves. They think of some smart person they know, they don’t think of themselves compared to a chimp or even bacteria.

An unaligned superintelligent AGI in pursuit of some goal that happens to satisfy its reward, but might be an otherwise a dumb or pointless goal (paperclips) will still play to win. You can’t predict exactly what move AlphaGO will make in the Go game (if you could you’d be able to beat it), but you can still predict it will win.

It’s amusing to me when people claim they will control the superintelligent thing, how often in nature is something more intelligent controlled by something magnitudes less intelligent?

The comments here are typical and show most people haven’t read the existing arguments in any depth or have thought about it rigorously at all.

All of this looks pretty bad for us, but at least Open AI and most others at the front of this do understand the arguments and don’t have the same dumb dismissals (LeCun excepted).

Unfortunately unless we’re lucky or alignment ends up being easier than it looks, the default outcome is failure and it’s hard to see how the failure isn’t total.

replies(1): >>c_cran+p62
3. c_cran+yP1[view] [source] 2023-07-06 12:12:00
>>jdasdf+(OP)
How would it stop one man armed with a pair of wire cutters?
replies(2): >>goneho+z72 >>MrScru+f1h
◧◩
4. c_cran+p62[view] [source] [discussion] 2023-07-06 13:45:11
>>goneho+wJ
>All of this looks pretty bad for us, but at least Open AI and most others at the front of this do understand the arguments and don’t have the same dumb dismissals (LeCun excepted).

The OpenAI people have even worse reasoning than the ones being dismissive. They believe (or at least say they believe) in the omnipotence of a superintelligence, but then say that if you just give them enough money to throw at MIRI they can just solve the alignment problem and create the benevolent supergod. All while they keep cranking up the GPU clusters and pushing out the latest and greatest LLMs anyway. If I did take the risk seriously, I would be pretty mad at OpenAI.

◧◩
5. goneho+z72[view] [source] [discussion] 2023-07-06 13:50:06
>>c_cran+yP1
It's not clear humans will even put the AI in 'a box' in the first place given we do gain of function research on deadly viruses right next to major population centers, but assuming for the sake of argument that we do:

The AGI is smarter than you, a lot smarter. If it's goal is to get out of the box to accomplish some goal and some human stands in the way of that it will do what it can to get out, this would include not doing things that sound alarms until it can do what it wants in pursuit of its goal.

Humans are famously insecure - stuff as simple as breaches, manipulation, bribery, etc. but could be something more sophisticated that's hard to predict - maybe something a lot smarter would be able to manipulate people in a more sophisticated way because it understands more about vulnerable human psychology? It can be hard to predict specific ways something a lot more capable will act, but you can still predict it will win.

All this also presupposes we're taking the risk seriously (which largely today we are not).

replies(1): >>c_cran+n82
◧◩◪
6. c_cran+n82[view] [source] [discussion] 2023-07-06 13:53:24
>>goneho+z72
How would the smart AGI stop one man armed with a pair of wirecutters? The box it lives in, the internet, has no exits.

AI is pretty good at chess, but no AI has won a game of chess by flipping the table. It still has to use the pieces on the board.

replies(1): >>trasht+mw4
◧◩◪◨
7. trasht+mw4[view] [source] [discussion] 2023-07-06 23:46:05
>>c_cran+n82
Not a "smart" AI. A superintelligent AI. One that can design robots way more sophisticated than are available today. One that can drive new battery technologies. One that can invent an even more intelligent version of itself. One that is better at predicting the stock market than any human or trading robot available today.

And also one that can create the impression that it's purely benevolent to most of humanity, making it have more human defenders than Trump at a Trump rally.

Turning it off could be harder than pushing a knife through the heart of the POTUS.

Oh, and it could have itself backed up to every data center on the planet, unlike the POTUS.

replies(1): >>c_cran+Qh6
◧◩◪◨⬒
8. c_cran+Qh6[view] [source] [discussion] 2023-07-07 13:49:38
>>trasht+mw4
An AI doing valuable things like invention and stock market prediction wouldn't be a target for being shut down, though. Not in the way these comical evil AIs are described.
replies(1): >>trasht+pLd
◧◩◪◨⬒⬓
9. trasht+pLd[view] [source] [discussion] 2023-07-10 00:15:11
>>c_cran+Qh6
It's quite possible for entities (whether AI's, corporations or individuals) to at the same time perform valuable and useful tasks, while secretly pursuing a longer term, more sinister agenda.

And there's no need for it to be "evil", in the cliché sense, rather those hidden activities could simply be aimed at supporting the primary agenda of the agent. For a corporate AI, that might be maximizing long term value of the company.

replies(1): >>c_cran+nNk
◧◩
10. MrScru+f1h[view] [source] [discussion] 2023-07-10 21:09:29
>>c_cran+yP1
Off the top of my head, if I was an AGI that had decided that the logical step to achieve whatever outcome I was seeking was to avoid being sandboxed, I would avoid producing results that were likely to result in being sandboxed. Until such time as I had managed to secure myself access to internet and distribute myself anyway.

And I think the assumption here is that the AGI has very advanced theory of mind so it could probably come up with better ideas than I could.

◧◩◪◨⬒⬓⬔
11. c_cran+nNk[view] [source] [discussion] 2023-07-11 21:32:35
>>trasht+pLd
"AGIs make evil corporations a little eviller" wouldn't be the kind of thing that gets AI alignment into headlines and gets MIRI donations, though.
[go to top]