Comment by adastra22
3 years ago
That’s a perfectly fine outcome. We already have that, since the incidence of psychopathy and mental illness is much higher than one in a thousand. A multipolar world with 999 well adjusted moral super intelligent AIs for every 1 problem case is a perfectly good outcome.
Bostrom et al are in fact arguing that near 100% of all intelligences will be unaligned by default and end up killing, enslaving, or otherwise neutralizing the entire human race.
We already fail to align nonhuman intelligences (car companies) and they regularly kill people (by manufacturing increasingly large pickup trucks that office workers buy for an ego boost and then hit people with).
This doesn't wipe out the entire human race because nobody and nothing is capable of executing such a perfect plan because the real world contains something called entropy.
the argument is that the car company becomes something like China mixed with North Korea, big, powerful, uncaring, unavoidable, with a lot of resources, expansionist, etc.
car companies, however misaligned they are, are not particularly smart, nor are they generally intelligent. they are paperclip maximizers, but that's also their limitations (sell more cars). it took an eccentric madman to even open their eyes to a new untapped market (EVs!), of course we can argue that before Tesla car makers were in a metastable equilibrium, and incumbents were unable to rationally break out of it ... but that just shows how narrow their search space is.
these car companies are run by humans, regulated by humans, etc. they are pretty well aligned. it shows because we saw that they are just mimeing self-improvement. we know they were working on EVs, but very half-heartedly. (because they are risk averse, also because regulators don't let them merge into one giant company, etc)
They didn't get into EVs because 1. Japan didn't like them (and still doesn't) because they have very expensive electricity 2. they were already getting into selling giant pickup trucks, not luxury sedans 3. China wasn't ready to compete yet.
They are limited by participating in the economy, but actually that's the strange thing about this superintelligence scenario - it never seems to include the economy. In other words, if you invented an AGI, it would have to get a job to pay for its AWS credits.
4 replies →
> A multipolar world with 999 well adjusted moral super intelligent AIs for every 1 problem case is a perfectly good outcome.
Such simplistic analysis is naive. A schizophrenic person can't spread, multiply themselves to increase its strength, but a rogue AI can.
The incidence of cancer cells is procentually very small, yet they routinely kill people, because they spread quickly.
The AGI and ASI instances that we have (e.g. GPT-4), require entire data centers with highly specialized hardware to run. How would a rogue AI replicate itself? You are worried about a fictional threat scenario that doesn't map to the real world.
> The AGI and ASI instances that we have (e.g. GPT-4), require entire data centers with highly specialized hardware to run.
LLMs are likely not an end to the AI evolution and there's little reason to believe that AIs will always remain bound to huge data centers. We have a nice counter-example already - our pretty decent intelligence runs from about 1 Kg brain.
It's also naive to think of AIs as having to replicate themselves completely as we humans do. In some cases, it might not even make sense to talk about replication at all and simply about extending one instance of AI once CPU at a time. It's conceivable that AGIs will develop special built agents/worms for constrained offline/high latency devices. Your smartwatch is unlikely to run a whole AGI, but it could run a constrained, purpose built AGI's agent with limited intelligence, able to partially act independently and re-sync with mother AGI once connectivity is available.
> You are worried about a fictional threat scenario that doesn't map to the real world.
We're talking here about future, of course it's all speculation and "fiction" for now. GPT-4 was a complete "fiction" 5 years ago as well.