LessWrong 2.0 Reader

while, at the same time, the reach of his actions and opinions have also maximized

I disagree. Companies will become complacent and stagnant very fast if leadership is not going hard against it. I'm not sure I'd like to work for him but my impression is that he really pushes his teams to go for more faster and results have shown up. I'm not sure "dumb"(at first look) ideas like Mechazilla would exist without him being willing to try cool things.

I'm on the fence for X, there have been good changes and the site feels a bit less like an echo chamber but there have also been negatives and I'm concerned by his recent implications in politics because I don't think he can bring much value, especially compared to his companies. 

Neuralink could also be very important. 

Overall, he would benefit from talking less but you can't have everything. I still think very much net positive.

The answer surely depends mostly on what his impact will be on AI developments, both through his influence on the policy of the new administration and what he does with xAI. While I understand that his political actions might be mind-killing (to say the least) to many of his former fans, I would much prefer a scenario where Elon has infuriating politics but a positive impact on solving alignment over one with the opposite outcome.

Oops, you're of course right. I'll change my comment.

P(doom) can be approximately measured. 
If reality fluid describes the territory well, we should be able to see close worlds that already died off.

For nuclear war we have some examples.
We can estimate the odds that the Cuban missile crisis and Petrov's decision went badly. If we accept that luck was a huge factor in us surviving those events (or not encountering events like it), we can see how unlikely our current world is to still live.

A high P(doom) implies that we are about to (or already did) encounter some very unlikely events that worked out suspiciously well for our survival. I don't know how public a registry of events like this should be, but it should exist.

Our self-reporting murderers or murder-witnesses should be extraordinarily well protected from leaks however, which in part seems like a software question.

Yes, this seems unlikely to happen, but again if your P(doom) is high, then we are only to survive in unlikely worlds. Working on this, to me, seems dignified: a way to make those unlikely worlds a bit less unlikely.

It's impossible to know until he is done/defeated, because the things he experiences due to his actions now could cause huge swings in his impacts on the future.

Net negative & net positive are hard to say.

Some one seemingly good might be a net negative by displacing some one better.

And some one seemingly bad might be a net positive by displacing some one worse.

And things like this are not particularly farfetched.

Does anyone know research on how to correct, regulate and interact with organisations with secrets that can't be known due to their info hazard nature?  It seems that this might be a tricky problem we need to solve with AI.

My new TAP for the year is - When I fail: try twice more. Then stop.

I'm persistent but unfortunately I don't know when to quit. I fall a foul of that saying "the definition of insanity is to try the same thing over and over again and expect different results". Need a pitch for a client? Instead of one good one I'll quota fill with 10 bad ones. Trying to answer a research question for a essay - if I don't find it in five minutes, guess I'm losing my whole evening on a Google Books/Scholar rabbit hole finding ancillary answers.

By allowing myself only two more tries but no more, that should mean that I get three failures instead of burnout-1 failures. It should mean I'll be, per the saying, less insane.

Three is an arbitrary number, it could easily be 4 or 5, but if I had to post-rationalize it then it would be: if you fail three consecutive times, then your chance of success was lower than 33.3% which means you need a better tactic or approach.

Three is a good balance between repetition without causing burnout, it also is low investment, which means that it encourages me to try again, and quickly.

Of course this approach only works if there is a postmortem. Try twice more, stop, then analyze what happened.

I can't say I'm proud of the fact that I need such a simple rule. But if it works, then I shouldn't feel ashamed for improving my behavior because of it.

 

“The reasons why super human AI is a very low hanging fruit are pretty obvious.”

“1) The human brain is meager in terms of energy consumption & matter.”

“2) Humans did not evolved to do calculus, computer programming & things like that.”

“3) Evolution is not efficient.”

“Neural networks don't need to have immaculate design -- otherwise human intelligence never would have evolved in the 1st place”

(Meta: Apologies for running the clock, but it is 1:45am where I am and I'm too sleepy to keep going on this thread, so I'm bowing out for tonight. I want to respond further, but I'm on vacation right now so I do wish to disclaim any expectations of a speedy follow-up.)