LessWrong 2.0 Reader

I think that's their guess but they don't directly check here. 

I also suspect that matters very much. 

• The sinuses have so much NO compared to the nose that this probably doesn't materially lower sinus concentrations. 
• the power of humming goes down with each breath but is fully restored in 3 minutes, suggesting that whatever change happens in the sinsues is restored quickly
• From my limited understanding of virology and immunology, alternating intensity of NO between sinuses and nose every three minutes is probably better than keeping sinus concentrations high^[1]. The first second of NO does the most damage to microbes^[2], so alternation isn't that bad.

I'd love to test this. The device you linked works via the mouth, and we'd need something that works via the nose. From a quick google it does look like it's the same test, so we'd just need a nasal adaptor.

Other options:

• Nnoxx. Consumer skin device, meant for muscle measurements
• There are lots of devices for measuring concentration in the air, maybe they could be repurporsed. Just breathing on it might be enough for useful relative metrics, even if they're low-precision. 

I'm also going to try to talk my asthma specialist into letting me use their oral machine to test my nose under multiple circumstances, but it seems unlikely she'll go for it. 

1. ^{^}

   obvious question: so why didn't evolution do that? Ancestral environment didn't have nearly this disease (or pollution) load. This doesn't mean I'm right but it means I'm discounting that specific evolutionary argument. 

2. ^{^}

   although NO is also an immune system signal molecule, so the average does matter. 

I think self-critique runs into the issues I describe in the post, though without insider information I'm not certain. Naively it seems like existing distortions would become larger with self-critique, though.

For human rating/RL, it seems true that it's possible to be sample efficient (with human brain behavior as an existence proof), but as far as I know we don't actually know how to make it sample efficient in that way, and human feedback in the moment is even more finite than human text that's just out there. So I still see that taking longer than, say, self play.

I agree that if outcome-based RL swamps initial training run datasets, then the "playing human roles" section is weaker, but is that the case now? My understanding (could easily be wrong) is that RLHF is a smaller postprocessing layer that only changes models moderately, and nowhere near the bulk of their training.

I agree! I’ve been writing then generating my own LW inspired songs now.

I wish it was common for LW posts to have accompanying songs now.

Re dictionary width, 2**17 (~131K) for most Gated SAEs, 3*(2**16) for baseline SAEs, except for the (Pythia-2.8B, Residual Stream) sites we used 2**15 for Gated and 3*(2**14) for baseline since early runs of these had lots of feature death. (This'll be added to the paper soon, sorry!). I'll leave the other Qs for my co-authors

To help remember this post and it's methods I broke it down into song lyrics and used Udio to make the song.

Similarly, the lab leak theory—one of the more widely accepted and plausible contrarian views—also doesn’t survive careful scrutiny. It’s easy to think it’s probably right when your perception is that the disagreement is between people like Saar Wilf and government bureaucrats like Fauci. But when you realize that some of the anti-lab leak people are obsessive autists who have studied the topic a truly mind-boggling amount, and don’t have any social or financial stake in the outcome, it’s hard to be confident that they’re wrong.

This is a very poor conclusion to draw from the Rootclaim debate. If you have not yet read Gwern’s commentary on the debate, I suggest that you do so. In short, the correct conclusion here is that the debate was a very poor format for evaluating questions like this, and that the “obsessive autists” in question cannot be relied on. (This is especially so because in this case, there absolutely was a financial stake—$100,000 of financial stake, to be precise!)

This thread seems unproductive to me, so I'm going to bow out after this. But in case you're actually curious: at least in the case of Open Philanthropy, it's easy to check what their primary concerns are because they write them up. And accidental release from dual use research is one of them.

Though the Greeks actually credited the idea to an even earlier Phonecian, Mochus of Sidon.

Through when it comes to antiquity credit isn't really "first to publish" as much as "first of the last to pass the survivorship filter."

1. What plateau?  Why pause now (vs say 10 years ago)?  Why not wait until after the singularity and impose a "long reflection" when we will be in an exponentially better place to consider such questions.
2. Singularity 5-10 years from now vs 15-20 years from now determines whether or not some people I personally know and care about will be alive.
3. Every second we delay the singularity leads to a "cosmic waste" as millions more galaxies move permanently behind the event horizon defined by the expanding universe
4. Slower is not prima facia safer.  To the contrary, the primary mechanism for slowing down AGI is "concentrate power in the hands of a small number of decision makers," which in my current best guess increases risk.
5. There is no bright line for how much slower we should go. If we accept without evidence that we should slow down AGI by 10 years, why not 50? why not 5000?

it very much depends on where the user came from

Can you provide any further detail here, i.e. be more specific on origin-stratified-retention rates? (I would appreciate this, even if this might require some additional effort searching)