LessWrong 2.0 Reader

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)

Great paper! The gating approach is an interesting way to learn the JumpReLU threshold and it's exciting that it works well. We've been working on some related directions at OpenAI based on similar intuitions about feature shrinking.

Some questions:

• Is b_mag still necessary in the gated autoencoder?
• Did you sweep learning rates for the baseline and your approach?
• How large is the dictionary of the autoencoder?

I doubt you could have picked a worse example to make your point that contrarian takes are usually wrong than racial differences in IQ/intelligence.

Sam Atis—a super forecaster—had a piece arguing against The Case Against Education

If it's this piece, I would be interested to know why you found it convincing.  He doesn't address (or seem to have even read) any of Brian's arguments. His argument basically boils down to "but so many people who work for universities think it's good".