Re: The desert island amnesiac - a multiverse parable

On Saturday, October 31, 2015 at 1:01:08 PM UTC+11, Brent wrote: > > > > On 10/30/2015 5:39 AM, Pierz wrote: > > So imagine a guy washed up on a small desert island after a plane crash. > Unfortunately during the plane crash he suffered a traumatic injury which > caused him to completely lose

Re: Fwd: Responsibility and Personhood

On Fri, Oct 30, 2015 at 03:28:09PM -0400, John Mikes wrote: > You wrote: > > > > > *"Then you have not met an algorithm whose output is directly influencedby > the environment. Most robots are agents in this sense. If the agents > areprocessing and reacting to rules, then those agents can be

Re: The desert island amnesiac - a multiverse parable

On 10/30/2015 5:39 AM, Pierz wrote: So imagine a guy washed up on a small desert island after a plane crash. Unfortunately during the plane crash he suffered a traumatic injury which caused him to completely lose his memory. He wakes up on the sure without the faintest clue about who he is

Re: Carroll's Paradox

On 10/30/2015 11:36 AM, Quentin Anciaux wrote: 2015-10-30 19:20 GMT+01:00 Brent Meeker >: On 10/30/2015 9:30 AM, Quentin Anciaux wrote: 2015-10-30 17:13 GMT+01:00 Quentin Anciaux

The desert island amnesiac - a multiverse parable

So imagine a guy washed up on a small desert island after a plane crash. Unfortunately during the plane crash he suffered a traumatic injury which caused him to completely lose his memory. He wakes up on the sure without the faintest clue about who he is or where he comes from. He doesn't even

Re: Carroll's Paradox

2015-10-30 17:01 GMT+01:00 John Clark : > On Thu, Oct 29, 2015 at 11:55 AM, Quentin Anciaux > wrote: > > ​>>​ >>> And I repeat, ​If the microprocessor made of matter that obeys the laws >>> of physics can't sense **any** information in the AI program

Re: Carroll's Paradox

2015-10-30 17:13 GMT+01:00 Quentin Anciaux : > > > 2015-10-30 17:01 GMT+01:00 John Clark : > >> On Thu, Oct 29, 2015 at 11:55 AM, Quentin Anciaux >> wrote: >> >> ​>>​ And I repeat, ​If the microprocessor made of matter that obeys

Re: Carroll's Paradox

On Fri, Oct 30, 2015 at 12:13 PM, Quentin Anciaux wrote: ​ >> ​>>​ >> The AI's physical memory banks are in that external world and the >> information in it is sure as hell fed into it, as are the results of >> calculations made by the physical microprocessors that are also

Re: Carroll's Paradox

On Thu, Oct 29, 2015 at 11:55 AM, Quentin Anciaux wrote: ​>>​ >> And I repeat, ​If the microprocessor made of matter that obeys the laws >> of physics can't sense **any** information in the AI program then the AI >> program is not running, it's​ not intelligent it's just a

Re: Fwd: Responsibility and Personhood

You wrote: *"Then you have not met an algorithm whose output is directly influencedby the environment. Most robots are agents in this sense. If the agents areprocessing and reacting to rules, then those agents can be punishedfor breaking the rules." * As I understand: a 'robot' is not an

Re: Carroll's Paradox

On Fri, Oct 30, 2015 Quentin Anciaux wrote: I'll try again... fooling myself again in believing you're honest here > ​Oh dear, I feared that "bye" in your last post didn't mean much. ​ > ​> ​ > So let's pretend our "AI" is in fact a Nintendo Entertainment System >

Re: Responsibility and Personhood

On 29 Oct 2015, at 03:11, Jason Resch wrote: At some level, an algorithm cannot be held responsible for its actions because it was doing the only thing it could do, what it was programmed to do. At some point between a simplistic algorithm and a human level AI, however, we seem able to

Re: Carroll's Paradox

On 10/30/2015 9:30 AM, Quentin Anciaux wrote: 2015-10-30 17:13 GMT+01:00 Quentin Anciaux >: 2015-10-30 17:01 GMT+01:00 John Clark >: On Thu, Oct 29, 2015 at 11:55 AM,

Re: Carroll's Paradox

2015-10-30 19:20 GMT+01:00 Brent Meeker : > > > On 10/30/2015 9:30 AM, Quentin Anciaux wrote: > > > > 2015-10-30 17:13 GMT+01:00 Quentin Anciaux : > >> >> >> 2015-10-30 17:01 GMT+01:00 John Clark < >> johnkcl...@gmail.com>: >> >>>

Re: The desert island amnesiac - a multiverse parable

Beautiful! Not very flattering to acceptors of the Theory of Everything though: you have to forget EVERYTHING to begin with. Then make up the WORLD from that fraction you experienced and format it into a Total. The hack with the rest... JM On Fri, Oct 30, 2015 at 8:39 AM, Pierz

Re: Responsibility and Personhood

Responsibility/culpability is a feature of our own programming allowing us to modify the program of our closely related copies, including ourselves. If we have precise control of the source code of an AI then this notion is rather pointless as we can directly modify the code. However, an AI