“Takeoff Speeds” has become kinda “required reading” in discussions on takeoff speeds. It seems like Eliezer hadn’t read it until September of this year? He may have other “required reading” from the past four years to catch up on.
Beth Barnes’ “Debate update: Obfuscated arguments problem” may not be as widely cited, but I think it may shed light on the controversy over IDA and related approaches. It exhibits a concrete weakness of IDA/Debate within the IDA/Debate framework, which may or not match up with flaws that were pointed out outside of that framework.
(Of course, if one predictably won’t learn anything from an article, there’s not much point in reading it.)
FWIW, I did not find this weirdly uncharitable, only mildly uncharitable. I have extremely wide error bars on what you have and have not read, and “Eliezer has not read any of the things on that list” was within those error bars. It is really quite difficult to guess your epistemic state w.r.t. specific work when you haven’t been writing about it for a while.
(Though I guess you might have been writing about it on Twitter? I have no idea, I generally do not use Twitter myself, so I might have just completely missed anything there.)
The “weirdly uncharitable” part is saying that it “seemed like” I hadn’t read it vs. asking. Uncertainty is one thing, leaping to the wrong guess another.
Yeah, even I wasn’t sure you’d read those three things, Eliezer, though I knew you’d at least glanced over ‘Takeoff Speeds’ and ‘Biological Anchors’ enough to form opinions when they came out. :)
“Takeoff Speeds” has become kinda “required reading” in discussions on takeoff speeds. It seems like Eliezer hadn’t read it until September of this year? He may have other “required reading” from the past four years to catch up on.
Ajeya Cotra’s “2020 Draft Report on Biological Anchors” is probably the most detailed public model of AI timelines.
Paul Christiano’s “What failure looks like” is a slightly more concrete illustration of Paul’s model of the future. Unfortunately, it avoids talking about human extinction in a way that gives the false impression that it’s a comforting scenario.
Beth Barnes’ “Debate update: Obfuscated arguments problem” may not be as widely cited, but I think it may shed light on the controversy over IDA and related approaches. It exhibits a concrete weakness of IDA/Debate within the IDA/Debate framework, which may or not match up with flaws that were pointed out outside of that framework.
(Of course, if one predictably won’t learn anything from an article, there’s not much point in reading it.)
I read “Takeoff Speeds” at the time. I did not liveblog my reaction to it at the time. I’ve read the first two other items.
I flag your weirdly uncharitable inference.
I apologize, I shouldn’t have leapt to that conclusion.
Apology accepted.
FWIW, I did not find this weirdly uncharitable, only mildly uncharitable. I have extremely wide error bars on what you have and have not read, and “Eliezer has not read any of the things on that list” was within those error bars. It is really quite difficult to guess your epistemic state w.r.t. specific work when you haven’t been writing about it for a while.
(Though I guess you might have been writing about it on Twitter? I have no idea, I generally do not use Twitter myself, so I might have just completely missed anything there.)
The “weirdly uncharitable” part is saying that it “seemed like” I hadn’t read it vs. asking. Uncertainty is one thing, leaping to the wrong guess another.
Yeah, even I wasn’t sure you’d read those three things, Eliezer, though I knew you’d at least glanced over ‘Takeoff Speeds’ and ‘Biological Anchors’ enough to form opinions when they came out. :)
(… Admittedly, you read fast enough that my ‘skimming’ is your ‘reading’. 😶)