You are the great commander of many robotic soldiers. Each soldier has two robotic kidneys. In war time they frequently need another one. If they don’t, they break (100%). If they do, the donor might break (1%). If all soldiers were equally good at war and equally willing to give...
Executive summary: heavy on Westworld, SF, AI, Cognitive Sciences, metaphysical sprouting and other cracked poteries. // Supplementary tag: lazystory, which means a story starting short and dirty, then each iteration is refined and evolved with the help of muses, LLMs and other occasional writers. // Rules: if we need a...
edit: see below for clarifications by expert domain rpglover64 and a good pick of references from the gears to ascenscion. My one (cheatingly long) sentence takeaway is: it’s clear training does not automatically lead to DP, it’s unclear if DP can always or seldom help training, it’s likely that easy...
Commit to only use superhuman persuasion when arguing towards a valid conclusion via valid arguments, in a manner that doesn't go against the interests of the person being persuaded.
In this plan, how should the AI define what’s in the interest of the person being persuaded? For example, say you have a North Korean soldier who can be persuaded to quite for the west (at the risk of getting the shitty jobs most migrants have) or who can be persuaded to remain loyal to his bosses (at the risk of raising his children in the shitty country most north korean have), what set of rules would you suggest?
the asteroid would likely burn up, but perhaps you have a solution for that
Yes, there’s a well known solution: just make the asteroid fast enough, and it will burn less in the atmosphere.
My understanding of this framework is probably too raw to go sane (A natural latent is a convolution basis useful for analyzing natural inputs, and it’s powerful because function composition is powerful) but it could fit nicely with Agency is what neurons in the biological movement area detect.
That’s great analogy. To me the strength of the OP is to pinpoint that LLMs already exhibit the kind of general ability we would expect from AGI, and the weakness is to forget that LLMs do not exhibit some specific ability most thought easy, such as the agency that even clownfishes exhibit.
In a way this sounds like again the universe is telling us we should rethink what intelligence is. Chess is hard and doing the dishes is easy? Nope. Language is hard and agency is central? Nope.
Thanks for the prompt! If we ask Claude 3 to be happy about x, don’t you think that counts as nudging it toward implementing a conscious being?
Perhaps you could identify your important beliefs
That part made me think. If I see bright minds falling in this trap, does blindness goes with importance of the belief for that person? I would say yes I think. As if that’s where we tend to make more « mistakes. that can behave as ratchets of the mind ». Thanks for the insight!
that also perhaps are controversial
Same exercise: if I see bright minds falling in this trap, does blindness goes with controversial beliefs? Definitely! Almost by definition actually.
each year write down the most likely story you can think of that would make it be wrong
I don’t feel I get this part as well as the formers. Suppose I hold the lab leak view, then notice it’s both controversial (« these morons can’t update right »), and much more important to me (« they don’t get how important it is for the safety of everyone »). What should I write?
Yup. Thanks for trying, but these beliefs seem to form a local minima, like a trap for the rational minds -even very bright ones. Do you think you understand how an aspiring rationalist could 1) recover and get out of this trap 2) don’t fall for it in the first place?
To be clear, my problem is not with the possibility of a lab leak itself, it’s with the evaluation that present evidences are anything but posthoc rationalizations fueled by unhealthy levels of tunnel vision. If bright minds can fall for that on this topic specifically, how do I know I’m not making the same mistake on something else?
(Spoiler warning)
(Also I didn’t check the previous survey nor the comments there, so expect some level of redondance)
The score itself (8/18) is not that informative, but checking the « accepted » answers is quite interesting. Here’s my « errors » and how much I’m happy making them:
You should be on the outlook for people who are getting bullied, and help defend them against the bullies.
I agree some rationalist leaders are toxic characters who will almost inevitably bully their students and collaborators, and I’m happy to keep strongly disagreeing with that. [actually most rationalists taking the survey agree with the statement, see tailcalled below]
... (read more)Modern food is more healthy because we have better hygiene than people did in
I am an old person. They may not let you do that in chemistry any more.
Absolutely! In my first chemistry lab, a long time ago, our teacher warned us that she had just lost a colleague to cancer at the age of forty, and she swore that if we didn't follow the security protocols very seriously, she would be our fucking nightmare.
I never heard her swear after that.
You are the great commander of many robotic soldiers. Each soldier has two robotic kidneys. In war time they frequently need another one. If they don’t, they break (100%). If they do, the donor might break (1%).
If all soldiers were equally good at war and equally willing to give one kidney, there would be little to discuss. But war is not that simple.
In your army 1/10 are 2 times better than the median, 1/100 are 4 times better than the median, 1/1000 are 16 times better than the median, 1/10000 are 256 times better than the median, etc.
If « better » would only meant « better at war », there would be little to discuss. But... (read more)
Executive summary: heavy on Westworld, SF, AI, Cognitive Sciences, metaphysical sprouting and other cracked poteries.
//
Supplementary tag: lazystory, which means a story starting short and dirty, then each iteration is refined and evolved with the help of muses, LLMs and other occasional writers.
//
Rules: if we need a safe space to discuss please shoot a private message and I’ll set the first comment for your thread with our agreed local policy. You can also use the comment system as usual if you’d like to suggest the next iteration for the main text, or provide advices on potential improvements.
//
Violence is the last refuge of the incompetent. You’re with me on this, Bernaaard?
//
What I... (read 828 more words →)
edit: see below for clarifications by expert domain rpglover64 and a good pick of references from the gears to ascenscion. My one (cheatingly long) sentence takeaway is: it’s clear training does not automatically lead to DP, it’s unclear if DP can always or seldom help training, it’s likely that easy algorithms are not available yet, it’s unlikely that finding one is low hanging fruit.
From wikipedia, « an algorithm is differentially private if an observer seeing its output cannot tell if a particular individual's information was used in the computation ». In other words, if some training process asymptotically converges toward generalisable knowledge only, then it should tend to become differentially private.
…or so it... (read more)
That may be too strong of a statement. Say some new tool helps improve AI legislation more than AI design, this might turn slowing down the wheel.