Said Achmiz

• Said Achmiz 17 Dec 2024 21:48 UTC

  2 points

  0

  on: Try­ing to trans­late when peo­ple talk past each other

  With that, I could imagine another shape behind B’s reaction. Some betrayal in her past, where someone else had unilaterally changed an agreement because they thought the consequences were the same, when they were very much not the same to B, and then rejected B’s objections as invalid… that this situation was now reminding her of.

  Why is it necessary (or even relevant) to imagine anything like this? It seems like this part is wholly superfluous (at best!); remove it from the reasoning you report, and… you still have your answer, right? You write:

  B was insisting that what we had agreed upon before was important. A was saying that the previous agreement didn’t matter, because the consequences were the same. That was triggering to B; B perceived it as A saying that he could unilaterally change an agreement if he experienced the consequences to be the same (regardless of whether he had checked for B’s agreement first).

  B was saying that it didn’t matter what move they ultimately played, that was all the same, but she needed A to acknowledge that he’d unilaterally changed an agreement, and she needed to be able to trust that A would not do that.

  …

  Viewed from that perspective, everything that B had said suddenly made sense. Indeed, what A actually played or didn’t play wasn’t the point. The point was that, as a matter of principle, A could not unilaterally declare a previous agreement to not matter without checking other people’s opinions first. Even if everyone did happen to agree in this case, sometimes they might not, with much more serious consequences. And if people always had nagging doubts about whether A’s commitments were trustworthy, that would be damaging.

  This seems like a complete answer; no explanatory components are missing. As far as I can tell, the part about a “betrayal in [B’s] past … that this situation was now reminding her of” is, at best, a red herring—and at worst, a way to denigrate and dismiss a perspective which otherwise seems to be eminently reasonable, understandable, and (IMO) correct.

• Said Achmiz 17 Dec 2024 10:49 UTC

  2 points

  0

  in reply to: MichaelDickens’s comment on: Effec­tive Altru­ism FAQ

  There were two different clauses, one about malaria and the other about chickens. “Helping people is really important” clearly applies to the malaria clause, and there’s a modified version of the statement (“helping animals is really important”) that applies to the chickens clause. I think writing it that way was an acceptable compromise to simplify the language and it’s pretty obvious to me what it was supposed to mean.

  A strange objection—since if you are correct and this is what was meant, then it strengthens my point. If thinking that helping people is really important AND that we should help more rather than less doesn’t suffice to conclude that we should give to chicken-related charities, then still less does merely one of those two premises suffice.

  (And “helping animals is really important” is, of course, quite far from an uncontroversial claim.)

  “We should help more rather than less, with no bounds/​limitations” is not a necessary claim. It’s only necessary to claim “we should help more rather than less if we are currently helping at an extremely low level”.

  No, this does not suffice. It would only suffice if giving to chicken-related charities were the first (or close to the first) charity that we’d wish to give to, if we were increasing our helping from an extremely low level to a higher one. Otherwise, if we believe, for instance, that helping a little is better than none, and helping a reasonable and moderate amount is better than helping a little, but helping a very large amount is worse (or even just no better) than the preceding, then this threshold may easily be reached long before we get anywhere near chickens (or any other specific cause). In order to guarantee the “we should give to chicken-related charities” conclusion, the “helping more is better than helping less” principle must be unbounded and unlimited.

• Said Achmiz 16 Dec 2024 22:39 UTC

  2 points

  0

  on: Effec­tive Altru­ism FAQ

  Minor correction: missing the hyphen in Sam Bankman-Fried’s last name.

• Said Achmiz 16 Dec 2024 22:35 UTC

  7 points

  1

  on: Effec­tive Altru­ism FAQ

  To think you should give to charities preventing kids from getting malaria, or making it so that chickens don’t have to languish for their whole life in a cage, you don’t have to think anything controversial about moral philosophy. You just have to think that helping people is really important, and we should help more rather than less! But that’s common sense.

  This is not correct, for two reasons:

  1. Thinking that helping people is really important, and that we should help more rather than less, does not suffice to conclude that we should give to charities aimed at doing anything to, with, or about chickens. (Because chickens are not people.)

  2. Thinking that we should help more rather than less—as a general principle that is not bounded or limited by anything—is, actually, a controversial claim of moral philosophy.

• Said Achmiz 9 Dec 2024 6:46 UTC

  3 points

  0

  in reply to: omnizoid’s comment on: The Case For Giv­ing To The Shrimp Welfare Project

  Sure, the report isn’t perfect, but it’s better than alternatives.

  As you well know, I have already responded to this claim as well.

• Said Achmiz 23 Nov 2024 19:31 UTC

  4 points

  0

  in reply to: Brendan Long’s comment on: Which things were you sur­prised to learn are metaphors?

  The density of butter is reasonably close to 1 avoirdupois ounce per 1 fluid ounce, but is definitely not exactly equal:

  https://​​kg-m3.com/​​material/​​butter gives the density as 0.95033293516 oz./​​fl. oz., or 0.911 kg/​​m^3.

  (The link you provide doesn’t give a source; the data at the above link is sourced from the International Network of Food Data Systems (INFOODS).)

  ---

  Further commentary:

  The density of water (at refrigerator temperatures) is ~1 g/​cm^3. 1 oz. = ~28.35 g; 1 fl. oz. = ~ 29.57 cm^3; thus the density of water is (1/​28.35) /​ (1/​29.57) = ~1.043 = oz./​fl. oz. (This is, of course, equal to 0.95033293516 /​ 0.911, allowing for rounding and floating point errors.)

  Note that the composition of butter varies. In particular, it varies by the ratio of butterfat to water (there are also butter solids, i.e. protein, but those are a very small part of the total mass). American supermarket butter has approx. 80% butterfat; Amish butter, European butters (e.g. Kerrygold), or premium American butters (e.g. Vital Farms brand) have more butterfat (up to 85%). Butterfat is less dense than water (thus the more butterfat is present, the lower the average density of the stick of butter as a whole—although this doesn’t make a very big difference, given the range of variation).

  Given the numbers in the paper at the last link, we can calculate the average density (specific gravity) of butter (assuming butterfat content of a cheap American supermarket brand) as 0.8 * 0.9 + 0.2 * 1.0 = 0.92. This approximately matches our 0.911 kg/​m^3 number above.

• Said Achmiz 22 Nov 2024 14:40 UTC

  2 points

  0

  in reply to: Brendan Long’s comment on: Which things were you sur­prised to learn are metaphors?

  No, you’re misunderstanding. There is no ¹⁄₂ cup of butter anywhere in the above scenario. One stick of butter is 4 oz. of butter (weight), but not ¹⁄₂ cup of butter (volume).

• Said Achmiz 22 Nov 2024 4:35 UTC

  13 points

  −7

  on: Which things were you sur­prised to learn are metaphors?

  Tablespoons of butter.

  A tablespoon is a unit of volume. Namely, it is one-sixteenth of a cup.

  Now, there are two distinct units called “ounces” that are commonly used in the United States. One is the avoirdupois ounce, also know as the United States customary ounce, which is a unit of weight; it is one-sixteenth of a pound. The other is the U.S. customary fluid ounce, which is a unit of volume; it is one-eighth of a cup.

  One-sixteenth of a cup is a tablespoon. One-eighth of a cup is an ounce (fluid). One-eighth of one-half of a cup is a tablespoon. These are all measures of volume.

  Butter, however, is sold by weight:

  

  The 16-oz. package of butter in the photo above says that it contains four sticks. This is one stick:

  

  The stick is divided into eight “tablespoons”.

  But the “tablespoons” of butter depicted above are not one tablespoon each in volume. And there is no such thing as a unit of weight called the “tablespoon”.

  So what is this? Well, one stick of butter is 4 ounces in weight. 8 ounces in volume is one cup. By analogy, if we think of 8 ounces in weight as a “cup” in weight (which is not actually a real weight unit!), then one-sixteenth of that weight is a “tablespoon” in weight (by analogy with one-sixteenth of a cup in volume being a tablespoon in volume). Neither cups nor tablespoons are real weight units! But if we call an 8-oz. weight a “cup”, then we can call a ¹⁄₂ oz. weight a “tablespoon”.

  Sticks of butter are divided into metaphorical tablespoons of butter.

• Said Achmiz 21 Nov 2024 3:32 UTC

  5 points

  0

  in reply to: trevor’s comment on: Lighthaven Se­quences Read­ing Group #12 (Tues­day 11/​26)

  “A space Odyssey” is not watchable without discussing historical context

  … why? I’ve watched this movie, and I… don’t think I’m aware of any special “historical context” that was relevant to it. (Or, at any rate, I don’t know what you mean by this.) It seemed to work out fine…

• Said Achmiz 18 Nov 2024 15:21 UTC

  3 points

  1

  in reply to: TurnTrout’s comment on: An­nounc­ing turn­trout.com, my new digi­tal home

  The main problem with your approach is not that it is counterintuitive (although it is, and more so than ours!), but that there is no way to return to “auto” mode via the site’s UI!^[1] Having clicked the mode selector, how do I go back to “no, just use my browser preference”? A two-state selector with a hidden, ephemeral third state, which cannot be retrieved once abandoned is, I’m afraid, the worst approach…

  ---

  1. ↩︎

     You can go into your browse’s dev tools and deleting the localStorage item, or clear all your saved data via the browser’s preferences. (Well, on desktop, anyway; on mobile—who knows? Not the former, at least, and how many mobile users even know about the latter? And the latter is anyhow an undesirable method!)

• Said Achmiz 18 Nov 2024 7:33 UTC

  10 points

  2

  in reply to: MichaelDickens’s comment on: An­nounc­ing turn­trout.com, my new digi­tal home

  Do you think a 3-state dark mode selector is better than a 1-state (where “auto” is the only state)? My website is 1-state, on the assumption that auto will work for almost everyone and it lets me skip the UI clutter of having a lighting toggle that most people won’t use.

  Gwern discusses this on his “Design Graveyard” page:

  Auto-dark mode: a good idea but “readers are why we can’t have nice things”.

  OSes/​browsers have defined a ‘global dark mode’ toggle the reader can set if they want dark mode everywhere, and this is available to a web page; if you are implementing a dark mode for your website, it then seems natural to just make it a feature and turn on iff the toggle is on. There is no need for complicated UI-cluttering widgets with complicated implementations. And yet—if you do do that, readers will regularly complain about the website acting bizarre or being dark in the daytime, having apparently forgotten that they enabled it (or never understood what that setting meant).

  A widget is necessary to give readers control, although even there it can be screwed up: many websites settle for a simple negation switch of the global toggle, but if you do that, someone who sets dark mode at day will be exposed to blinding white at night… Our widget works better than that. Mostly.

  Is it possible that someday dark-mode will become so widespread, and users so educated, that we could quietly drop the widget? Yes, even by 2023 dark-mode had become quite popular, and I suspect that an auto-dark-mode would cause much less confusion in 2024 or 2025. However, we are stuck with the widget—once we had a widget, the temptation to stick in more controls (for reader-mode and then disabling/​enabling popups) was impossible to resist, and who knows, it may yet accrete more features (site-wide fulltext search?), rendering removal impossible.

  (The site-wide fulltext search feature has since been added, of course.)

  What links here?

  • gwern's comment on An­nounc­ing turn­trout.com, my new digi­tal home by TurnTrout (18 Nov 2024 14:53 UTC; 8 points)

• Said Achmiz 17 Nov 2024 21:22 UTC

  3 points

  0

  on: An­nounc­ing turn­trout.com, my new digi­tal home

  Not bad at all! Needs some work on the details and some bug fixes, but—really not bad! The dropcaps, in particular, are well done; and the overall theme is elegant.

• Said Achmiz 16 Nov 2024 5:09 UTC

  6 points

  0

  on: The Case For Giv­ing To The Shrimp Welfare Project

  I’m just going to link the comment I wrote the last time you mentioned that Rethink Priorities report. That report continues to be of very little use in supporting such arguments as you present here.

Gw­ern Bran­wen in­ter­view on Dwarkesh Pa­tel’s pod­cast: “How an Anony­mous Re­searcher Pre­dicted AI’s Tra­jec­tory”

• Said Achmiz 2 Nov 2024 1:53 UTC

  2 points

  −7

  in reply to: Raemon’s comment on: Jar­gonBot Beta Test

  I in fact don’t use Google very much these days, and don’t particularly recommend that anyone else do so, either.

  (If by “google” you meant “search engines in general”, then that’s a bit different, of course. But then, the analogy here would be to something like “carefully select which LLM products you use, try to minimize their use, avoid the popular ones, and otherwise take all possible steps to ensure that LLMs affect what you see and do as little as possible”.)

• Said Achmiz 2 Nov 2024 1:50 UTC

  0 points

  −2

  in reply to: Raemon’s comment on: Jar­gonBot Beta Test

  The most important thing is “There is a small number of individuals who are paying attention, who you can argue with, and if you don’t like what they’re doing, I encourage you to write blogposts or comments complaining about it. And if your arguments make sense to me/​us, we might change our mind. If they don’t make sense, but there seems to be some consensus that the arguments are true, we might lose the Mandate of Heaven or something.”

  There’s not, like, anything necessarily wrong with this, on its own terms, but… this is definitely not what “being held accountable” is.

  It happening at all already constitutes “going wrong”.

  This particular sort of comment doesn’t particularly move me.

  All this really means is that you’ll just do with this whatever you feel like doing. Which, again, is not necessarily “wrong”, and really it’s the default scenario for, like… websites, in general… I just really would like to emphasize that “being held accountable” has approximately nothing to do with anything that you’re describing.

  As far as the specifics go… well, the bad effect here is that instead of the site being a way for me to read the ideas and commentary of people whose thoughts and writings I find interesting, it becomes just another purveyor of AI “extruded writing product”. I really don’t know why I’d want more of that than there already is, all over the internet. I mean… it’s a bad thing. Pretty straightforwardly. If you don’t think so then I don’t know what to tell you.

  All I can say is that this sort of thing drastically reduces my interest in participating here. But then, my participation level has already been fairly low for a while, so… maybe that doesn’t matter very much, either. On the other hand, I don’t think that I’m the only one who has this opinion of LLM outputs.

• Said Achmiz 1 Nov 2024 20:14 UTC

  −7 points

  −7

  in reply to: habryka’s comment on: Jar­gonBot Beta Test

  Do you not use LLMs daily?

  Not even once.

  In general, I think Gwern’s suggested LLM policy seems roughly right to me.

  First of all, even taking what Gwern says there at face value, how many of the posts here that are written “with AI involvement” would you say actually are checked, edited, etc., in the rigorous way which Gwern describes? Realistically?

  Secondly, when Gwern says that he is “fine with use of AI in general to make us better writers and thinkers” and that he is “still excited about this”, you should understand that he is talking about stuff like this and this, and not about stuff like “instead of thinking about things, refining my ideas, and writing them down, I just asked a LLM to write a post for me”.

  Approximately zero percent of the people who read Gwern’s comment will think of the former sort of idea (it takes a Gwern to think of such things, and those are in very limited supply), rather than the latter.

  The policy of “encourage the use of AI for writing posts/​comments here, and provide tools to easily generate more AI-written crap” doesn’t lead to more of the sort of thing that Gwern describes at the above links. It leads to a deluge of un-checked crap.

• Said Achmiz 1 Nov 2024 19:41 UTC

  −3 points

  −9

  in reply to: Raemon’s comment on: Jar­gonBot Beta Test

  I welcome being held accountable for this going wrong in various ways.

  It happening at all already constitutes “going wrong”.

  Also: by what means can you be “held accountable”?

• Said Achmiz 1 Nov 2024 19:40 UTC

  −7 points

  −28

  in reply to: habryka’s comment on: Jar­gonBot Beta Test

  If this is true, then it’s a damning indictment of Less Wrong and the authors who post here, and is an excellent reason not to read anything written here.

• Said Achmiz 30 Oct 2024 6:34 UTC

  16 points

  0

  in reply to: habryka’s comment on: Habryka’s Short­form Feed

  Well, let’s see. Calibri is a humanist sans; Gill Sans is technically also humanist, but more more geometric in design. Geometric sans fonts tend to be less readable when used for body text.

  Gill Sans has a lower x-height than Calibri. That (obviously) is the cause of all the “the new font looks smaller” comments.

  (A side-by-side comparison of the fonts, for anyone curious, although note that this is Gill Sans MT Pro, not Gill Sans Nova, so the weight [i.e., stroke thickness] will be a bit different than the version that LW now uses.)

  Now, as far as font rendering goes… I just looked at the site on my Windows box (adjusting the font stack CSS value to see Gill Sans Nova again, since I see you guys tweaked it to give Calibri priority)… yikes. Yeah, that’s not rendering well at all. Definitely more blurry than Calibri. Maybe something to do with the hinting, I don’t know. (Not really surprising, since Calibri was designed from the beginning to look good on Windows.) And I’ve got a hi-DPI monitor on my Windows machine…

  Interestingly, the older version of Gill Sans (seen in the demo on my wiki, linked above) doesn’t have this problem; it renders crisply on Windows. (Note that this is not the flawed, broken-kerning version of the font that comes with Macs!)

  I also notice that the comment font size is set to… 15.08px. Seems weird? Bumping it up to 16px improves things a bit, although it’s still not amazing.

  If you can switch to the older (but not broken) version of Gill Sans, that’d be my recommendation.

  If you can’t… then one option might be to check out one of the many similar fonts to see if perhaps one of them renders better on Windows while still having matching metrics.