Team Lead for LessWrong
Curated. The ELK paper/problem/challenge last year was a significant piece of work for our alignment community and my guess is hundreds of hours and maybe hundreds of thousands of dollars went into incentivizing solutions. Though prizes were awarded, I’m not aware that any particular proposed solution was deemed incredibly promising (or if it was, it wasn’t something new), so I find it interesting to see what Paul and ARC have generated as they do stick on the same problem, roughly.
Speaking the truth is not something to be traded away, however costly it may be.
Stated without clarification, this is not something I’d say categorically and I suspect neither would you. As the classic example goes, you would probably lie to the Space Gestapo to prevent them from killing your mother.
Curated. I like the central thesis of this post, but a further point I like about it is it takes the conversation beyond a simple binary of “are we doomed or not?”, and “how doomed are we?” to a more interesting discussion of possible outcomes, their likelihoods, and the gears behind them. And I think that’s epistemically healthy. I think it puts things into a mode of “make predictions for reasons” over “argue for a simplified position”. Plus, this kind of attention to values and their origins is also one thing I think that hasn’t gotten as much airtime on LessWrong and is important, both in remembering what we’re fighting for (in very broad terms) and how we need to fight (i.e. what’s ok to build).
This is so neat! I (32M) initially didn’t look at this post (my brain had auto-completed it to “I made an epub” or something), but I’m familiar with this format and find the whole thing very cute. (I don’t know how many people I expect to watch these, but I’m amused the exist. Kudos.)I only watched one but would go for Minecraft or whatever the game with the cars is, less sudden and jerky movement.
See also Two-Level Utilitarianism
Curated. I’ve got to hand it to this post for raw unadulterated expression of pure Ravenclaw curiosity at how the world (and we ourselves) work. It is morbid and it’s perhaps fortunate the images are broken, but I’m just enjoying how much the author is reveling in the knowledge and experience here. I like the generalized lesson here of GO LOOK AT THE WORLD, it’s right there.I don’t know that I have the stomach to do this myself, but glad people are!
This point does not work literally as stated, and is vastly too underspecified to be useful not taken as 100%.
[I appreciate your preamble. Thank you for the feedback and suggestion! Appreciated.]We’ve actually just recently built “rate limits” for accounts as actually something in-between no action and banning. I have a draft post about our moderation philosoph and approach I want to get out in the next few days.In this case I felt that it was better to skip the intermediary steps though, just going on experience with different types of users and likely outcomes.
I am a bit sad too. You might reassured to know that we are generally very reluctant to remove content once posted and practically never do so excepting spam, even if we didn’t think it was great content.
Hi Bernd,I’m very sorry but while I am sympathetic to your viewpoint and arguments, I feel your manner of communication (axe-grindy extremely inappropriately long comments on posts not quite relevant posts, this here comment even lapsing in German without explanation) is not a good fit for LessWrong. After chatting with Raemon, we feel it better if you weren’t on LessWrong and I am regrettably disabling your ability to post and comment. Our experience with other users who had similar commenting patterns is that improvements are unlikely, so I do feel it’s best not to drag things out and go for the full disabling. (Sorry about doing this in public – I like to be transparent about mod actions.If you’d like to discuss, please use firstname.lastname@example.org
Hey there, welcome to LW! I’m a mod and we manually review all first posts before letting them go live. I’m approving this with a downvote since this post doesn’t feel like it’s saying anything clear or specific. I feel pretty confused.I’d encourage you to read the Sequences/Rationality:A-Z, particular the early sections about how theories need to make predictions and precision.
Hey, heads up that I wouldn’t post the same comment in two different places. If it really seems relevant to both, perhaps link to it from the second location.
The Sequences is the original name, but it got edited down and renamed to “Rationality:A-Z”
Moderator here. I approved this post but strong downvoted it (according to the “votes are for what you want to see more/less of” approach). It’s not exactly obviously super wrong, but feels perhaps too basic and I don’t want a tonne more of this on the site. Perhaps it feels like it’s written without building on the Sequences which touches a lot on this. Though I could be pretty wrong and we should encourage people to think about AI wherever there at. Not sure. I think engaging on all previous AI content is unnecessary, but I will downvote if i think content doesn’t feel like the author has read the Sequences. Hence downvote but still approved.
plot a development path based on compute scaling laws are a game of Russian Roulette. You only get it right after finding the magic bullet, and by then, it’s too late.
Scrutiny is mutiny.
Quick note as a mod for the site. I feel this post’s ratio of substance to witty/snarky metaphor/word play isn’t high enough. I downvoted and as part of an effort to nudge the site more towards great content, I’m applying a 1 post/comment per day rate limit to your account (in light of this post and other downvoted posts).We’re a little more trigger-ready with Future Fund Worldview Prizes because it seems the quality is lower than average for LW. And I don’t think that’s just because we’re resistant to contrary opinions.
Sounds a lot like LessWrong, but often competition is healthy ;)
Quick heads up from a moderator. (*waves*) Welcome to LW, TOMOKO, I see you’re a new user. Just noted you were commenting a lot on AI posts. To keep quality high on the site, especially on AI where there’s so much interest now, we’re keeping a closer eye on new users. I’d encourage you to up the quality of your comments a tad (sorry, actually quite hard to explain how), just each marginal user pulls up the average. For now, I’ve applied a rate limit of 1 post and 1 comment per day to your account. Can revisit that if your contributions start seeming great.Thanks and good luck!
Quick heads up from a moderator. I feel this post feels very basic/overly simple and doesn’t quite meet the standards for AI discussion that we’re now targeting. With the large influx of users interested in AI, we’re starting to put more mod effort into ensuring standards are high, that is, that content is well-reasoned and useful.Consider this a light warning to invest a little more effort!
Thanks and good luck!
Quick heads up from a moderator. I feel this post and some of your other comments don’t quite meet the standards for AI discussion that we’re now targeting. With the large influx of users interest in AI, we’re starting to put more mod effort into ensuring standards are high, that is, that content is well-reasoned and useful.
Unfortunately, it’s hard to neatly specify “the standard”, so some quick recommendations:
Check out Stampy, a wiki project and community about AI Safety/Alignment
Comment on the most recent thread for basic questions about AI safety
Read The Sequences as a general boost to rational engagement on tricky topics
For now, I’ve limited you to one post and comment per day. If the mods observe that your contributions are substantial, we will remove the limit.
Thanks and good luck!(forgive the public moderation strategy – we want to be transparent and accountable to all users and are moving away from DMs where had been sending these messages)