Drahflow

Karma: 220

Drahflow Nov 16, 2011, 8:40 AM
0 points
on: Why an Intelligence Explosion might be a Low-Priority Global Risk

The AGI would have to acquire new resources slowly, as it couldn’t just self-improve to come up with faster and more efficient solutions. In other words, self-improvement would demand resources. The AGI could not profit from its ability to self-improve regarding the necessary acquisition of resources to be able to self-improve in the first place.

If the AGI creates a sufficiently convincing business plan / fake company front, it might well be able to command a significant share of the world’s resources on credit and either repay after improving or grab power and leave it at that.

Drahflow Nov 11, 2011, 12:22 PM
0 points
on: What visionary project would you fund?
Small scale fusion power.

Research challenges: How to get hydrogen to fuse into helium using only 500kg of machinery and less energy than will be produced.

Urgent Tasks: (In-)Validate the results of the fusor people, scale up / down as neccessary.

Reasons: Enormous amounts of energy goes into everything. If energy costs drop significantly, I expect sustained, fast and profound economic growth, in this case without too much ecological impact. Also, a lot of high-energy technology will become way more feasible, e.g. space missions.

Drahflow Nov 6, 2011, 12:36 PM
0 points
on: Selection Effects in estimates of Global Catastrophic Risk
Risk mitigation groups would gain some credibility by publishing concrete probability estimates of “the world will be destroyed by X before 2020” (and similar for other years). As many of the risks are a rather short event (think nuclear war / asteroid strike / singularity), the world will be destroyed by a single cause and the respective probabilities can be summed. I would not be surprised if the total probability comes out well above 1. Has anybody ever compiled a list of separate estimates?

On a related note, how much of the SIAI is financed on credit? Any group which estimates high risks of disastrous events should be willing to pay higher interest rates than market average. (As the expected amount of repayments is reduced by the nontrivial probability of everyone dying before maturity of the contract).

Do-it-yourself-science Wiki

DrahflowJun 22, 2011, 10:25 AM

6 points

1 comment1 min readLW link

Drahflow Feb 15, 2011, 9:55 PM
3 points
in reply to: abramdemski’s comment on: Algorithms as Case Studies in Rationality
My classical example for algorithms applicable to real life: Merge sort for sorting stacks of paper.

Drahflow Jan 12, 2011, 11:02 AM
3 points
in reply to: Nornagest’s comment on: Branches of rationality
A short list for prediction making of groups (and via extension decision making):

Drahflow Dec 16, 2010, 9:07 AM
0 points
on: Confidence levels inside and outside an argument

But it’s hard for me to be properly outraged about this, because the conclusion that the LHC will not destroy the world is correct.

What is your argument for claiming that the LHC will not destroy the world?

That the world still exists albeit ongoing experiments is easily explained by the fact that we are necessarily living in those branches of the universe where the LHC didn’t destroy the world. (On an related side note: Has the great filter been found yet?)

Drahflow Sep 15, 2010, 4:38 PM
4 points
in reply to: katydee’s comment on: Intelligence Amplification Open Thread
It appears slow. In particular I seem to think more things per time, sometimes noticing significant delays between thought and action. However according to the scores, performance improvement is only marginal (but existent). The effect wears off after 10 to 15 minutes according to my experience.

I usually play Quake 3 (just in case anybody want’s to compare effects between games).

Drahflow Sep 15, 2010, 12:53 PM
4 points
in reply to: xamdam’s comment on: Intelligence Amplification Open Thread
Same goes for videos (Yay action movies at 2x).

Bonus points (for fun only): Play action games afterwards. Time sensation is a weird thing.

Drahflow Sep 10, 2010, 5:23 PM
7 points
in reply to: Baughn’s comment on: Memetic Hazards in Videogames
Video game authors probably put a lot of effort into optimizing video games for human pleasure.

Workplace design, User Interfaces etc., they could all be improved if more ideas were copied from video games.

Drahflow Sep 6, 2010, 10:42 AM
2 points
in reply to: Vladimir_Nesov’s comment on: Controlling Constant Programs
The only difference I can see between “an agent which knows the world program it’s working with” and “agent(‘source of world’)” is that the latter agent can be more general.

Drahflow Sep 6, 2010, 10:36 AM
0 points
on: Controlling Constant Programs
If agent() is actually agent(‘source of world’) as the classical newcomb problem has it, I fail to see what is wrong with simply enumerating the possible actions and simulating the ‘source of world’ with the constant call of agent(‘source of world’) replaced by the current action candidate? And then returning the action with maximum payoff obviously.

Drahflow Sep 3, 2010, 10:34 AM
1 point
in reply to: CronoDAS’s comment on: Rationality quotes: September 2010
Loyality to petrified opinion has already kept chains from being closed and souls from being trapped.

Drahflow Sep 3, 2010, 10:30 AM
6 points
in reply to: RobinZ’s comment on: Rationality quotes: September 2010
But some thoughts are both so complex and so irrelevant that a correct analysis of the thought would cost more than an infrequent error about thoughts of this class (costs of necessary meta-analysis included).

Drahflow Aug 27, 2010, 6:32 PM
1 point
on: Exploitation and cooperation in ecology, government, business, and AI
What is the difference between non-nested and modular? (Or between non-modular and nested?)

The pictures seem to be rotated by 180 degrees essentially.

Drahflow Aug 11, 2010, 11:35 PM
3 points
in reply to: NancyLebovitz’s comment on: Five-minute rationality techniques
Decreasing frequency of surprising technology advancements are caused by faster and more frequent information of the general public about scientific advancements.

If the rate of news consumes grows faster than the rate of innovations produced, the perceived magnitude of innovation per news will go down.

Drahflow Jul 21, 2010, 10:23 AM
2 points
on: Missed opportunities for doing well by doing good
If you are out for the warm fuzzies: According to my experience fuzzies / $ is optimized via giving a little often.

Microfinancing might be an option, as the same capital can be lend multiple times, generating some fuzzies each time.

Then again, GiveWell seems not too decided on the concept: http://www.givewell.org/international-giving-marketplaces

Drahflow Apr 22, 2010, 8:15 AM
0 points
in reply to: Jack’s comment on: Fusing AI with Superstition
I fail to understand the sentence about overthinking. Mind to explain?

As for the condition of removing all energy and mass in a part of space not being sufficient to destroy all agents therein, I cannot see the error. Do you have an example of an agent which would continue to exist in those circumstances?

That the condition is not necessary is true: I can shoot you, you die. No need to remove much mass or energy from the part of space you occupy. However we don’t need a necessary condition, only a sufficient one.

Drahflow Apr 22, 2010, 6:05 AM
0 points
in reply to: RobinZ’s comment on: Fusing AI with Superstition
Not having heard your argument against “Describing …” yet, but assuming you believe some to exist, I estimate the chance of me still believing it after your argument at 0.6.

Now for guessing the two problems:

The first possible problem will be describing “mass” and “energy” to a system which basically only has sensor readings. However, if we can describe concepts like “human” or “freedom”, I expect descriptions of matter and energy to be simpler (even though 10.000 years ago, telling somebody about “humans” was easier than telling them about mass but that was not the same concept of “humans” we would actually like to describe). And for “mass” and “energy” the physicists already have at quite formal descriptions.

One other problem is that mass and energy might not be contained within a certain part of space, as per physics, it is just the probability of it having an effect outside some space going down to pretty much zero the greater the distance. Thus removing all energy and matter somewhere might produce subtle effects somewhere totally different . However I do expect these effects to be so subtle not even to matter to the AI because they become smaller than the local quantum noise for very short distances already.

Regarding the condescending: “I say this...” I would have liked it more if you would have stated explicitly that your preference originates from a wish to further my learning. I have no business optimizing your value function. Anyway, I operate by Crocker’s Rules.

Drahflow Apr 22, 2010, 4:26 AM
2 points
in reply to: RobinZ’s comment on: Fusing AI with Superstition
The claim is relevant to the question of whether giving an action description for the red wire which will fit all of human future is not harder than constructing a real moral system. That the claim is trivial is a good reason to use “certainly”.

Drahflow

Do-it-your­self-sci­ence Wiki

Do-it-yourself-science Wiki