LessWrong 2.0 Reader

They put too much emphasis on high frequency features, suggesting a different inductive bias from humans.

Could you fix this part by adding high frequency noise to the images prior to training? Maybe lots of copies of each image with different noise patterns?

Humans come to reflect on their thoughts on their own without being prompted into it (at least I have heard some anecdotal evidence for it and I also did discover this myself as a kid). The test would be it LLMs would come up with such insights without being trained on text describing the phenomenon. It would presumably involve some way to observe your own thoughts (or some alike representation). The existing context window seems to be too small for that.

Good point, Claude, yeah. Quite alien indeed, maybe more parsimonious. This is exactly what I meant by possibility of this analogy being overridden by actually digging into your brain, digging into a human one and developing actually technical gears-level models of both and then comparing them. Until then, who knows, I'm leaning toward healthy dose of uncertainty.

Also, thanks for the comment.

Oh great, thanks!

I would dissuade no one from writing drunk, and I'm confident that you too can say that people are penguins! But I'm sorry to report that personally I don't do it by drinking but rather writing a much longer version with all those kinds of clarifications included and then obsessively editing it down.

If you don't need 12 tubes of superglue, dollar stores often carry 4 tiny tubes for a buck or so.

I'm glad that superglue is working for you! I personally find that a combination of sharp nail clippers used at the first sign of a hangnail, and keeping my hands moisturized, works for me. Flush cutters of the sort you'd use to trim the sprues off of plastic models are also amazing for removing proto-hangnails without any jagged edge.

Another trick to avoiding hangnails is to prevent the cuticles from growing too long, by pushing them back regularly. I personally like to use my teeth to push back my cuticles when showering, since the cuticle is soft from the water, my hands are super clean, and it requires no extra tools. I recognize that this is a weird habit, though, and I think the more normal ways to push cuticles are to use your fingernails or a wooden stick (manicurists use a special type of dowel but a popsicle stick works fine).

You can also buy cuticle remover online, which is a chemical that softens the dried skin of the cuticle and makes it easier to remove from your nails. It's probably unnecessary, but if you're really trying to get your hands into a condition where they stop developing hangnails, it's worth considering.

You mean, "ban superintelligence"? Because superintelligences are not human-like.

The kind of superintelligence that doesn't possess human-likeness that we want it to possess.

That's the problem with your proposal of "ethics module". Let's suppose that we have system of "ethics module" and "nanotech design module". Nanotech design module outputs 3D-model of supramolecular unholy abomination. What exactly should ethics module do to ensure that this abomination doesn't kill everyone?

Nanotech design module has to be evaluatable by the ethics module. For that it also be made from multiple sequential LLM calls in explicit natural language. Other type of modules should be banned.

So, I have three very distinct ideas for projects that I'm thinking about applying to the Long Term Future Fund for. Does anyone happen to know if it's better to try to fit them all into one application, or split them into three separate applications?

You are conflating subjective as in "by subjects" with subjective as in "for subjects". A subject can have preferences for objectivity, universality, impartiallity, etc.

Yeah, I saw your other replies in another thread and I was able to test it myself later today and yup it's most likely that it's OpenAI's new LLM. I'm just still confused why call such gpt2.