[ExI] 'Friendly' AI won't make any difference

TimTyler tim at tt1.org
Sun Feb 28 04:40:07 UTC 2016


On 2016-02-26 18:29, Anders Sandberg wrote:
> On 2016-02-26 16:40, John Clark wrote:
>>
>> ​No I don't mean that, I mean running around in a circle and making 
>> no progress but having no way to know for sure that you're running 
>> around in a circle and making no progress. Turing proved there is in 
>> general no way to know if you're in a infinite loop or not.
>
> No, he did not. You are confusing the halting theorem (there is no 
> algorithm that
> can determine if a program given to it will halt) with detecting an 
> infinite loop.

For finite programs, it's the same problem. Either a program halts or it 
loops forever.

    Note that a program X can be extended to a program X' (or run by an
    interpreter) that

    maintains a list of past states and check if X returns to a previous
    state. It will accurately

    detect its infinite looping when it occurs.


You can loop forever without ever returning to a previous state, though:

10 LET UNBOUNDED INTEGER i = 0;
20 i = i + 1;
30 GOTO 20;

Your proposed loop detector would never detect this simple infinite loop.

-- 
__________
  |im Tyler http://timtyler.org/

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.extropy.org/pipermail/extropy-chat/attachments/20160227/fd918156/attachment.html>


More information about the extropy-chat mailing list