LessWrong 2.0 Reader

Also my impression is that business or political assassinations exist to this day in many countries; a little searching suggests Russia, Mexico, Venezuela, possibly Nigeria, and more.

Oh definitely. In Mexico in particular business pairs up with organized crime all of the time to strong-arm competitors. But this happens when there's an organized crime tycoons can cheaply (in terms of risk) pair up with. Also, OP asked about why companies don't assassinate whistlebowers all the time specifically.

a lot of hunter-gatherer people had to be able to fight to the death, so I don't buy that it's entirely about the human constitution

That was not criminal murder by the standards of the time. Arguably a lot of gang murders committed in the United States are committed by people not capable or willing to go out and murder people on their own.

Update: there's now a YouTube link

In brief: large amounts of high quality process based RL might result in AI being more useful earlier (prior to them becoming much smarter). This might be expensive and annoying (e.g. it might require huge amounts of high quality human labor) such that by default labs do less of this relative to just scaling up models than would be optimal from a safety perspective.

Most people do not have the constitution or agency for criminal murder

I think my model of people is that people are very much changed by the affordances that society gives them and the pressures they are under. In contrast with this statement, a lot of hunter-gatherer people had to be able to fight to the death, so I don't buy that it's entirely about the human constitution. I think if it was a known thing that you could hire an assassin on an employee and unless you messed up and left quite explicit evidence connecting you, you'd get away with it, then there'd be enough pressures to cause people in-extremis to do it a few times per year even in just high-stakes business settings. Also my impression is that business or political assassinations exist to this day in many countries; a little searching suggests Russia, Mexico, Venezuela, possibly Nigeria, and more.

I generally put a lot more importance on tracking which norms are actually being endorsed and enforced by the group / society as opposed to primarily counting on individual ethical reasoning or individual ethical consciences.

(TBC I also am not currently buying that this is an assassination in the US, but I didn't find this reasoning compelling.)

IDK, I think this comment warrants the level of karma. OP is proposing messing around with a drug class that kills thousands of people per year. Even only counting benzo overdoses that don't involve opioids, it kills ~1500 people per year. Source: https://nida.nih.gov/research-topics/trends-statistics/overdose-death-rates (you can download the data from that page to see precise numbers).

It's not often that a forum comment could save a life!

I can see some arguments in your direction but would tentatively guess the opposite. 

Maybe we have different definitions of DSA: I was thinking of it in terms of 'resistance is futile' and you can dictate whatever terms you want because you have overwhelming advantage, not that you could eventually after a struggle win a difficult war by forcing your opponent to surrender and accept unfavorable terms.

If say the US of 1965 was dumped into post WW2 Earth it would have the ability to dictate whatever terms it wanted because it would be able to launch hundreds of ICBMS at enemy cities at will. If the real US of 1949 had started a war against the Soviets it would probably have been able to cripple an advance into western Europe but likely wouldn't have been able to get its bombers through to devastate enough of the soviet homeland with the few bombs they had.

Remember the soviets did just lose a huge percentage of their population and industry in WW2 and kept fighting. The fact that it's at all debatable who would have won if WW3 started in the late 1940s at all (see e.g. here) makes me think nuclear weapons weren't at that time a DSA producer.

I'm interested in using the SAEs and auto-interp GPT-3.5-Turbo feature explanations for RES-JB for some experiments. Is there a way to download this data?

Yeah, seems like a kinda bad feedback loop. It doesn't seem to usually happen in that the comments I've seen upvoted in that section usually don't get this extremely many upvotes on a comment this short.

I don't have a great solution. We could do something that's more clever and algorithmic, which doesn't seem crazy but I am also hesitant to do because it's a lot of work and also I like more straightforward and simple algorithms for transparency reasons.

Oh, very cool, thanks! Spoiler tag in markdown is:

:::spoiler
text here
:::