On Tue, Sep 4, 2012 at 6:06 PM, Russell Wallace
<[email protected]> wrote:
>
> For my part, the link I question is the implicit one between mathematical
> principle and engineering practice.
>
> If we had an infinitely powerful computer on which we could run a
> Kolmogorov compression oracle, would that give us AGI? Yes.

Well, no, there is still the problem of acquiring the 10^17 bits of
human knowledge you need to build models of 10^10 human minds.

> If we take a real compression program running on real hardware and try to
> use it as a predictor let alone a general intelligence, does it perform
> well? No. Matt tried precisely that experiment awhile ago, using a very
> good, state-of-the-art text compression program. The fact that it could do
> text prediction at all was an interesting validation of the mathematical
> theory, but its performance as a predictor was unsurprisingly abysmal.

Not really. The best compressors on my large text benchmark achieve
just over 1 bit per character, which is in the range of uncertainty
for human level performance (0.6 to 1.3 bpc). But I am pretty sure
that humans can still do better than the best algorithms. That's
something I still need to test, however.

> Even the reverse doesn't hold. We haven't got AGI to test it with, but we
> can test it with NGI which we do have. Are humans good at compression? No.
> Matt observes one reason for this is the lack of deterministic reset
> capability, but if we imagine solving that problem by running an uploaded
> human on digital hardware, thus enabling the mind in question to perform
> lossless compression, it's clear the result would be very inefficient
> compared to a specialized compression program.

Inefficient, maybe, but not necessarily poor at compression.


-- Matt Mahoney, [email protected]


-------------------------------------------
AGI
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-c97d2393
Modify Your Subscription: 
https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-2484a968
Powered by Listbox: http://www.listbox.com

Reply via email to