It should be posted, but by someone who can more rigorously describe its application to an optimizer than “probably needs to be locally smooth-ish.”
khafra
Karma: 2,573
Point 8, about the opacity of decision-making, reminded me of something I’m surprised I haven’t seen on LW before:
LIME, Local Interpretable Model-agnostic Explanations, can show a human-readable explanation for the reason any classification algorithm makes a particular decision. It would be harder to apply the method to an optimizer than to a classifier, but I see no principled reason why an approach like this wouldn’t help understand any algorithm that has a locally smooth-ish mapping of inputs to outputs.
provably secure software mechanisms rely on an idealized model of hardware
In my experience, they also define an attacker model against which to secure. There are no guarantees against attackers with greater access, or abilities, than specified in the model.
Dave Asprey says, with a reasonably large set of referenced studies, that it’s the mold in food which reduces your fed performance.
If you think this is wrong, take it up with the people whose work I am both quoting and analyzing in this paper, because THAT IS WHAT THEY ARE CLAIMING. I am not the one saying that “the AI is programmed with good intentions”, that is their claim.
I think I spotted a bit of confusion: The programmers of the “make everyone happy” AI had good intentions. But the AI itself does not have good intentions; because the intent “make everyone happy” is not good, albeit in a way that its programmers did not think of.
If that data is encrypted (assuming no headers or footers or obvious block divisions), then it will appear to an attacker like random bytes. Whether or not that’s distinguishable from the original image depends on whether the low bits of the original image are observably nonrandom, and that’s not something I know offhand
It’s super-easy to spot in a histogram, so much so that there’s ongoing research into making it less detectable.
Presumably it’s in conflict with the instrumental values of retaining resources which could be used for other terminal values (the money she would save, going with the fuel cell), and the combination of instrumental and terminal values represented by the improved acceleration of the fuel cell.
Do you have plans for when your term life insurance expires, but you’re still alive (which is, actuarially speaking, fairly certain)?
2) A fanfic where smarter versions of canon characters fight each other with complicated plots.
...supporters say the opposition leader was assassinated to silence him...
I see headlines like this fairly regularly.
Does anybody know of a list of notable opposition leaders, created when all members of the list were alive? Seems like it could be educational to compare the death rate of the list (a) across countries, and (b) against their respective non-notable demographics.
I just want to know about the actuary from Florida; I didn’t think we had any other LW’ers down here.
Your observation of the reading on the scale is true, of course. Your observation that the weight is 51 grams is false.
“This weight masses 51 grams” is not an observation, it’s a theory attempting to explain an observation. It just seems so immediate, so obvious and inarguable, that it feels like an observation.
No observation is false. Any explanation for a given observation may, with finite probability, be false; no matter how obvious and inarguable it may seem.
an AI will not have a fanatical goal of taking over the world unless it is programmed to do this.
It is true that an AI could end up going “insane” and trying to take over the world, but the same thing happens with human beings
Are you asserting that all the historic conquerors and emperors who’ve taken over the world were insane? Is it physically impossible to for an agent to rationally plan to take over the world, as an intermediate step toward some other, intrinsic goal?
there is no reason that humans and AIs could not work together to make sure this does not happen
If the intelligence difference between the smartest AI and other AIs and humans remains similar to the intelligence difference between an IQ 180 human and an IQ 80 human, Robin Hanson’s malthusian hellworld is our primary worry, not UFAI. A strong singleton taking over the world is only a concern if a strong singleton is possible.
If you program an AI with an explicit or implicity utility function which it tries to maximize...
FTFY.
But if you program an AI without an explicit utility function, just programming it to perform a certain limited number of tasks, it will just do those tasks.
Yes, and then someone else will, eventually, accidentally create an AI which behaves like a utility maximizer, and your AI will be turned into paperclips just like everything else.
Are there lists of effective charities for specific target domains? For social reasons, I sometimes want to donate to a charity focused on some particular cause; but given that constraint, I’d still like to make my donation as effective as possible.
Do not spam high-status people, and do not communicate with high-status people in a transparent attempt to affiliate with them and claim some of their status for yourself.
I would have given a response for digit ratio if I’d known about the steps to take the measurement before opening the survey, or if it were at the top of the survey, or if I could answer on a separate form after submitting the main survey. I didn’t answer because I was afraid that if I took the time to do so, the survey form, or my https connection to it, or something else would time out, and I would lose all the answers I had entered.
To implement Bayes’ Theorem, the prior of something must be known
Not quite the way I’d put it. If you know the exact prior for the unique event you’re predicting, you already know the posterior. All you need is a non-pathologically-terrible prior, although better ones will get you to a good prediction with fewer observations.
Tangentially, there’s an upcoming Netflix six-episode series named “The Heavy Water War,” that should cover both this event, and the sabotage of the heavy water production facility that led up to it.