Have any posts from LW 2.0 generated new conceptual handles for the community like “the sanity waterline”?
As a datapoint, here’s a few I’ve used a bunch of times in real life due to discussing them on LW (2.0). I’ve used most of these more than 20 times, and a few of them more like 2000 times.
I was going to say 2000 times sounded like way too much, but making the guesstimates that means on average using “common knowledge” once every other day since it was published, and “out to get you” once every third day, and that does seem consistent with my experience hanging out with you (though of course with a fat tail of the distribution, using some concepts like 10 times in a single long hangout).
Actually in my head I was more counting the tail conversations (e.g. where I use a term 20-30 times), but you’re right that the regular conversations will count for most of the area under the curve. Slack, Goodharting, Common Knowledge, are all ones I use quite frequently.
Goodhard law isn’t a new concept and the term goodharting doesn’t get used in the post about Goodhart’s law that you linked and thus likely isn’t responsible for it either.
I haven’t seen the term that the post actually introduces Regressional Goodhart, Causal Goodhart, Extremal Goodhart or Adversarial Goodhart be used.
Yeah, I was not saying the posts invented the terms, I was saying they were responsible for my usage of them. I remember at the time reading the post Goodhart Taxonomy and not thinking it was very useful, but then repeatedly referring back to it a great deal in my conversations. I also ended up writing a post based on the four subtypes.
Added: Local Validity and Free Energy are two other examples that obviously weren’t coined here, but the discussion here caused me to use quite a lot.
As a datapoint, here’s a few I’ve used a bunch of times in real life due to discussing them on LW (2.0). I’ve used most of these more than 20 times, and a few of them more like 2000 times.
Embedded Agency, Demon Threads, Slack, Combat vs Nurture Culture, Rationality Realism, Local Validity, Common Knowledge, Free Energy, Out to Get You, Fire Alarm, Robustness to Scale, Unrolling Social Metacognition, The Steering Problem, Goodhart’s Law.
I was going to say 2000 times sounded like way too much, but making the guesstimates that means on average using “common knowledge” once every other day since it was published, and “out to get you” once every third day, and that does seem consistent with my experience hanging out with you (though of course with a fat tail of the distribution, using some concepts like 10 times in a single long hangout).
Actually in my head I was more counting the tail conversations (e.g. where I use a term 20-30 times), but you’re right that the regular conversations will count for most of the area under the curve. Slack, Goodharting, Common Knowledge, are all ones I use quite frequently.
Goodhard law isn’t a new concept and the term goodharting doesn’t get used in the post about Goodhart’s law that you linked and thus likely isn’t responsible for it either.
I haven’t seen the term that the post actually introduces Regressional Goodhart, Causal Goodhart, Extremal Goodhart or Adversarial Goodhart be used.
Yeah, I was not saying the posts invented the terms, I was saying they were responsible for my usage of them. I remember at the time reading the post Goodhart Taxonomy and not thinking it was very useful, but then repeatedly referring back to it a great deal in my conversations. I also ended up writing a post based on the four subtypes.
Added: Local Validity and Free Energy are two other examples that obviously weren’t coined here, but the discussion here caused me to use quite a lot.
Not Ben, but I have used X Goodhart more than 20 times (summing over all the Xs)