I’ve always found it a bit odd that Alignment Forum submissions are automatically posted to LW.
If you apply some of these norms, then imo there are questionable implications, i.e. it seems weird to say that one should have read the sequences in order to post about mechanistic interpretability on the Alignment Forum.
If you apply some of these norms, then imo there are questionable implications, i.e. it seems weird to say that one should have read the sequences in order to post about mechanistic interpretability on the Alignment Forum.
The AI Alignment Forum was never intended as the central place for all AI Alignment discussion. It was founded at a time when basically everyone involved in AI Alignment had read the sequences, and the goal was to just have any public place for any alignment discussion.
Now that the field is much bigger, I actually kind of wish there was another forum where AI Alignment people could go to, so we would have more freedom in shaping a culture and a set of background assumptions that allow people to make further strides and create a stronger environment of trust.
I personally am much more interested in reading about mechanistic interpretability from people who have read the sequences. That one in-particular is actually one of the ones where a good understanding of probability theory, causality and philosophy of science seems particularly important (again, it’s not that important that someone has acquired that understanding via the sequences instead of some other means, but it does actually really benefit from a bunch of skills that are not standard in the ML or general scientific community).
I expect we will make some changes here in the coming months, maybe by renaming the forum or starting off a broader forum that can stand more on its own, or maybe just shutting down the AI Alignment Forum completely and letting other people fill that niche.
similarly, I’ve been frustrated that medium quality posts on lesswrong about ai often get missed in the noise. I want alignmentforum longform scratchpad, not either lesswrong or alignmentforum. I’m not even allowed to post on alignmentforum!
some recent posts I’ve been frustrated to see get few votes and generally less discussion:
There’s been a lot of really low quality posts lately, so I know I’ve been having to skim more and read fewer things from new authors. I think resolving general issues around quality should help valuable stuff rise to the top, regardless of whether it’s on AF or not.
[Justification for voting behavior, not intending to start a discussion. If I were I would have commented on the linked post]
I’ve read the model distillation post, and it is bad, so strong disagree. I don’t think that person understands the arguments for AI risk and in particular don’t want to continuously reargue the “consequentialism is simpler, actually” line of discussion with someone who hasn’t read pretty basic material like risks from learned optimization.
I’ve always found it a bit odd that Alignment Forum submissions are automatically posted to LW.
If you apply some of these norms, then imo there are questionable implications, i.e. it seems weird to say that one should have read the sequences in order to post about mechanistic interpretability on the Alignment Forum.
The AI Alignment Forum was never intended as the central place for all AI Alignment discussion. It was founded at a time when basically everyone involved in AI Alignment had read the sequences, and the goal was to just have any public place for any alignment discussion.
Now that the field is much bigger, I actually kind of wish there was another forum where AI Alignment people could go to, so we would have more freedom in shaping a culture and a set of background assumptions that allow people to make further strides and create a stronger environment of trust.
I personally am much more interested in reading about mechanistic interpretability from people who have read the sequences. That one in-particular is actually one of the ones where a good understanding of probability theory, causality and philosophy of science seems particularly important (again, it’s not that important that someone has acquired that understanding via the sequences instead of some other means, but it does actually really benefit from a bunch of skills that are not standard in the ML or general scientific community).
I expect we will make some changes here in the coming months, maybe by renaming the forum or starting off a broader forum that can stand more on its own, or maybe just shutting down the AI Alignment Forum completely and letting other people fill that niche.
similarly, I’ve been frustrated that medium quality posts on lesswrong about ai often get missed in the noise. I want alignmentforum longform scratchpad, not either lesswrong or alignmentforum. I’m not even allowed to post on alignmentforum!
some recent posts I’ve been frustrated to see get few votes and generally less discussion:
https://www.lesswrong.com/posts/JqWQxTyWxig8Ltd2p/relative-abstracted-agency—this one deserves at least 35 imo
www.lesswrong.com/posts/fzGbKHbSytXH5SKTN/penalize-model-complexity-via-self-distillationhttps://www.lesswrong.com/posts/bNpqBNvfgCWixB2MT/towards-empathy-in-rl-agents-and-beyond-insights-from-1
https://www.lesswrong.com/posts/LsqvMKnFRBQh4L3Rs/steering-systems
… many more open in tabs I’m unsure about.
There’s been a lot of really low quality posts lately, so I know I’ve been having to skim more and read fewer things from new authors. I think resolving general issues around quality should help valuable stuff rise to the top, regardless of whether it’s on AF or not.
[Justification for voting behavior, not intending to start a discussion. If I were I would have commented on the linked post]
I’ve read the model distillation post, and it is bad, so strong disagree. I don’t think that person understands the arguments for AI risk and in particular don’t want to continuously reargue the “consequentialism is simpler, actually” line of discussion with someone who hasn’t read pretty basic material like risks from learned optimization.
I still think this one is interesting and should get more attention, though: https://www.lesswrong.com/posts/JqWQxTyWxig8Ltd2p/relative-abstracted-agency
fair enough. I’ve struck it from my comment.