News for hackers. Stuff that matters.

A comment on Superintelligence cannot be contained: Lessons from Computability Theory. Parent comment

Re:Superintelligence cannot be contained: Lessons from Compu... by jacb on Monday January 11, 2021 @05:25PM (#25738390)
That's not how arguments from contradiction work. You've assumed H (halting problem is decidable), prove B (beauty decidable), then say "but actually !H, therefore !B". All you've proven is that H => B. An actual argument from contradiction is "assume H, using H we can prove an obviously false statement, therefore not-H". And indeed, you have assumed something false (H), and shown a contradiction (various proofs for !H), so your original assumption was wrong (!H).

A concrete example: say Beauty(R,D) is trivially decidable (say it returns (popcount(R)+popcount(D))%2. Your argument "proves" this property is undecidable, but it's definitely decidable. So some step in your argument is wrong.

Another concrete example: Assume the halting problem is decidable. I would like a cookie. But the halting problem is not decidable. Therefore I would not like a cookie.

[ Parent | on HN ]
Re:Superintelligence cannot be contained: Lessons from Compu... by cambalache on Monday January 11, 2021 @06:53PM (#25740034)
You are just repeating my critique. I am not the one making the mistake.
[ Parent | on HN ]
Re:Superintelligence cannot be contained: Lessons from Compu... by gbjw on Monday January 11, 2021 @09:18PM (#25741422)
So you mean your frustration is warranted then?
[ Parent | on HN ]
Re:Superintelligence cannot be contained: Lessons from Compu... by cambalache on Tuesday January 12, 2021 @01:30AM (#25743161)
If that is the kind of work published by academics associated with the MIT and La Pontificia Universidad de Madrid, then maybe I should not feel frustrated after all by not being an academic.
[ Parent | on HN ]
Re:Superintelligence cannot be contained: Lessons from Compu... by spuz on Tuesday January 12, 2021 @04:29AM (#25744358)
But you said in your first comment that you were an academic.

"I confess I am a frustrated academic"

[ Parent | on HN ]
Re:Superintelligence cannot be contained: Lessons from Compu... by bryanrasmussen on Tuesday January 12, 2021 @04:46AM (#25744485)
if you're not being facetious,

in English vernacular being a frustrated X (as in a frustrated academic, frustrated poet, etc.) means that the person is actually not that, but have in some way been prevented from being the thing (frustrated) and have perhaps rancor in regards to the frustration and towards those who actually are the thing (this second feature being sometimes implied depending on who is doing the description of the person as frustrated)

on edit: formatting, clarification

[ Parent | on HN ]
Re:Superintelligence cannot be contained: Lessons from Compu... by js8 on Tuesday January 12, 2021 @05:55AM (#25745133)
Thanks, I wasn't aware of the 2nd meaning. I also interpreted the "frustrated academic" as "an annoyed academic", rather than "an unsuccesfull academic".
[ Parent | on HN ]
Re:Superintelligence cannot be contained: Lessons from Compu... by bryanrasmussen on Tuesday January 12, 2021 @08:22AM (#25746447)
I'm thinking maybe it is no longer as common an expression as I thought, given the people who've mistaken it here.
[ Parent | on HN ]
Re:Superintelligence cannot be contained: Lessons from Compu... by spuz on Tuesday January 12, 2021 @09:57AM (#25747688)
I think it didn't help that they used both meanings of the word "frustrated" in the same sentence. By adding "perhaps my frustration is unwarranted", it puts emphasis on the fact they are frustrated, not that they failed to become an academic. It leads the reader to believe they are in fact still an active academic.

I was only dimly aware of the second meaning of the word so I'm not sure how you would interpret it if you had a good understanding of the multiple interpretations.

[ Parent | on HN ]
Re:Superintelligence cannot be contained: Lessons from Compu... by taberiand on Tuesday January 12, 2021 @04:57AM (#25744593)
As an English speaker, my only interpretation was that you were an academic frustrated about academia.
[ Parent | on HN ]
Re:Superintelligence cannot be contained: Lessons from Compu... by bryanrasmussen on Tuesday January 12, 2021 @05:38AM (#25744952)
https://www.ldoceonline.com/dictionary/a-frustrated-artist-a... - came up if I search for 'meaning of frustrated poet' which is the kind of thing where the phrasing most often comes up.
[ Parent | on HN ]
Re:Superintelligence cannot be contained: Lessons from Compu... by falseprofit on Tuesday January 12, 2021 @05:33AM (#25744901)
That isn't even the same user.
[ Parent | on HN ]
Re:Superintelligence cannot be contained: Lessons from Compu... by Caylio on Tuesday January 12, 2021 @04:34AM (#25744399)
He is proving his point by contradicting himself, a true mathematician.
[ Parent | on HN ]
Re:Superintelligence cannot be contained: Lessons from Compu... by jacb on Monday January 11, 2021 @07:43PM (#25740652)
Ah, I misunderstood you! I apologize. :)
[ Parent | on HN ]
Re:Superintelligence cannot be contained: Lessons from Compu... by sgillen on Tuesday January 12, 2021 @12:45PM (#25750399)
I think maybe you made a typo in your OP? The authors assume beauty is decidable and use that to show that would imply that the halting problem is undecidable. It applies to anything, like you say, and to me it seems like a silly argument, but I think it’s a valid proof given the premises.
[ Parent | on HN ]
Re:Superintelligence cannot be contained: Lessons from Compu... by dandanua on Tuesday January 12, 2021 @03:17AM (#25743820)
But it's not an argument from the paper. The idea is that superintelligence have to understand a consequence of any program to check for harm. And this is undecidable due to the halting problem. This argument is correct, but trivial and not worth a paper, in my opinion.
[ Parent | on HN ]
Re:Superintelligence cannot be contained: Lessons from Compu... by cambalache on Tuesday January 12, 2021 @12:44PM (#25750395)
The harming algorithm is just used in the paper's proof as a simple wrapper around the halting algorithm.
[ Parent | on HN ]