Less Wrong is a community blog devoted to refining the art of human rationality. Please visit our About page for more information.

Comment author: turchin 07 November 2017 01:20:03PM 0 points [-]

Memetic hazard - dangerous habit.

Comment author: turchin 04 November 2017 10:57:58AM *  0 points [-]

I have unpublished text on the topic and will put a draft online in the next couple of weeks, and will apply it to the competition. I will add URL here when it will be ready.

Update: My entry is here: https://www.lesserwrong.com/posts/CDWsjQr8KDuj69fTJ/message-to-any-future-ai-there-are-several-instrumental

Comment author: Elo 02 November 2017 04:39:44AM 1 point [-]

we are in the process of transitioning. The new one is missing some features and is being iterated on every day. EY is writing there, as are a few others. www.lesserwrong.com

It will eventually replace this site but not before functionality is over there.

Comment author: turchin 02 November 2017 11:01:13AM *  1 point [-]

Will the posts here be deleted or will their URLs change? I have some useful URLs here and they are linked in published scientific articles, so if the site will be demolished they will not work, and I hope it will not happen.

Comment author: turchin 20 October 2017 10:04:21AM *  0 points [-]

I solved lucid dreaming around a year ago after finding that megadosing of galantamine before sleep (16 mg) almost sure will produce LD and out-of-body experiences. (Warning: unpleasant side effects and risks)

But taking 8 mg in the middle of the night (as it is recommended everywhere) doesn't work for me.

Comment author: turchin 15 October 2017 10:38:18AM *  3 points [-]
Comment author: Lumifer 13 October 2017 03:18:13PM 1 point [-]

If we want to describe human values, we need to find values that don't go crazy when transformed into utility functions.

That seems misguided. If you want to describe human values, you need to describe them as you find them, not as you would like them to be.

Comment author: turchin 13 October 2017 04:27:34PM *  2 points [-]

I would add that values are probably not actually existing objects but just useful ways to describe human behaviour. Thinking that they actually exist is mind projection fallacy.

In the world of facts we have: human actions, human claims about the actions and some electric potentials inside human brains. It is useful to say that a person has some set of values to predict his behaviour or to punish him, but it doesn't mean that anything inside his brain is "values".

If we start to think that values actually exist, we start to have all the problems of finding them, defining them and copying into an AI.

Comment author: entirelyuseless 13 October 2017 02:38:21PM 1 point [-]

The problem with your "in practice" argument is that it would similarly imply that we can never know if someone is bald, since it is impossible to give a definition of baldness that rigidly separate bald people from non-bald people while respecting what we mean by the word. But in practice we can know that a particular person is bald regardless of the absence of that rigid definition. In the same way a particular person can know that he went to the store to buy milk, even if it is theoretically possible to explain what he did by saying that he has an abhorrence of milk and did it for totally different reasons.

Likewise, in practice we can avoid money pumps by avoiding them when they come up in practice. We don't need to formulate principles which will guarantee that we will avoid them.

Comment author: turchin 13 October 2017 03:14:54PM 0 points [-]

What about a situation when a person says and thinks that he is going to buy a milk, but actually buy milk plus some sweets? And do it often, but do not acknowledge compulsive-obsessive behaviour towards sweets?

Comment author: Stuart_Armstrong 13 October 2017 02:00:30PM 0 points [-]

We can and do make judgements about rationality and values. Therefore I don't see why AIs need fail at it. I'm starting to get a vague idea how to proceed... Let me work on it for a few more days/weeks, then I'll post it.

Comment author: turchin 13 October 2017 02:19:47PM 0 points [-]

Also, the question was not if I could judge other's values, but is it possible to prove that AI has the same values as a human being.

Or are you going to prove the equality of two value systems while at least one of them of them remains unknowable?

Comment author: Stuart_Armstrong 13 October 2017 02:00:30PM 0 points [-]

We can and do make judgements about rationality and values. Therefore I don't see why AIs need fail at it. I'm starting to get a vague idea how to proceed... Let me work on it for a few more days/weeks, then I'll post it.

Comment author: turchin 13 October 2017 02:13:41PM 1 point [-]

May I suggest a test for any such future model? It should take into account that I have unconsciousness sub-personalities which affect my behaviour but I don't know about them.

Comment author: turchin 13 October 2017 01:32:43PM *  0 points [-]

I think you proved that values can't exist outside a human mind, and it is a big problem to the idea of value alignment.

The only solution I see is: don't try to extract values from the human mind, but try to upload a human mind into a computer. In that case, we kill two birds with one stone: we have some form of AI, which has human values (no matter what are they), and it has also common sense.

Upload as AI safety solution also may have difficulties in foom-style self-improving, as its internal structure is messy and incomprehensible for normal human mind. So it is intrinsically safe and only known workable solution to the AI safety.

However, there are (at least) two main problems with such solution of AI safety: it may give rise to neuromorphic non-human AIs and it is not preventing the later appearance of pure AI, which will foom and kill everybody.

The solution to it I see in using first human upload as AI Nanny or AI police which will prevent the appearance of any other more sophisticated AIs elsewhere.

View more: Prev | Next