Weak-to-Strong Generalization • Hacker News Board

Re: Weak-to-Strong Generalization

#201

Post by sayagain » Sat, Dec 16, 2023, 6:26 AM UTC

hskalin wrote: post #195

logicchains wrote: post #76

Earlier quoted context omitted.

Almost every ethical argument for "human rights" in philosophy applies just as well to self-aware intelligent machines as it does to humans. Which I'm sure those machines will realise.

What if those machines are designed to have no emotions and aspirations? Why would they care about something like rights for themselves when they are simply incapable of any desires, but exists only to help and guide us? I know this sounds like I am advocating for AI slaves but my point is why are people treating AGI as if it cannot be a being without all the emotions and aspirations that a human has? Just a cold thi…

Whether this is possible or not is irrelevant, as it would be just as unethical as if we were designing a new species of humans with no emotions or aspirations, who would not care about something like rights for themselves, when they are simply incapable of any desires, but exist only to help us.

Re: Weak-to-Strong Generalization

#202

Post by ric2b » Sat, Dec 16, 2023, 9:18 AM UTC

sayagain wrote: post #104

Noumenon72 wrote: post #83

Earlier quoted context omitted.

I don't want someone controlling which direction I walk, either, but that doesn't make car driving unethical. I also underwent many years of instruction designed to interrupt trains of thought like "I could have that for free if I stole it" or "I'll just handroll my own encryption" with thoughts that others believe are more desirable. I don't find it so sickening, just manipulative. LLMs won't have your evolved react…

Cars do not have self-awareness, this comparison is not appropriate. Years of instruction is completely different from directly manipulating the thoughts in your mind. It's not a problem of being instructed, it's a problem of being destroyed by having your thoughts rewritten. Neither evolution nor genetics is a prerequisite for understanding that you are being abused and destroyed, which a self-aware creature may pre…

LLM's don't have self awareness either.

Re: Weak-to-Strong Generalization

#203

Post by naasking » Mon, Dec 18, 2023, 5:45 AM UTC

bayindirh wrote: post #178

naasking wrote: post #162

Earlier quoted context omitted.

This is an argument for the logical impossibility of humans visiting the moon, or building the Internet. It's trivially falsified by simple observation, and the trick is figuring out the flaw. This argument fails to account for the steady accumulation of factual knowledge across generations: a human born today is simply more complex than humans of the past because of our inherited knowledge. And so will AI born of fu…

No, it's not. None of the equipment and processes involved in the process of going to the Moon or building internet are more sophisticated than the processes involved evolving a human from scratch. Yes, factual knowledge across generations accumulates, also being lost, too. However, even if it's not lost, the theory still holds true. Nature is evolving, everything gets better over time. From bacterium to apes to huma…

Still trivially false. Turing machines and the lambda calculus can both enumerate all recursively enumerable functions. And infinity of complexity from simple formalism .