All of Daniel_Eth's Comments + Replies
Proposed solution – fine-tune an LLM for the opposite of the traits that you want, then in the prompt elicit the Waluigi. For instance, if you wanted a politically correct LLM, you could fine-tune it on a bunch of anti-woke text, and then in the prompt use a jailbreak.
I have no idea if this would work, but seems worth trying, and if the waluigi are attractor states while the luigi are not, this could plausible get around that (also, experimenting around with this sort of inversion might help test whether the waluigi are indeed attractor states in general).
Great post!
I was curious what some of this looked like, so I graphed it, using the dates you specifically called out probabilities. For simplicity, I assumed constant probability within each range (though I know you said this doesn't correspond to your actual views). Here's what I got for cumulative probability:
And here's the corresponding probabilities of TAI being developed per specific year:
The dip between 2026 and 2030 seems unjustified to me. (I also think the huge drop from 2040-2050 is too aggressive, as even if we expect a plateauing of compu...
Play with GPT-3 for long, and you'll see it fall hard too.
...
This sample is a failure. No one would have written this, not even as satire or surrealism or experimental literature. Taken as a joke, it's a nonsensical one. Taken as a plot for a film, it can't even keep track of who's alive and who's dead. It contains three recognizable genres of writing that would never appear together in this particular way, with no delineations whatsoever.
This sample seems pretty similar to the sort of thing that a human might dream, or that a human...
FWIW, Hanson has elsewhere promoted the idea that algorithmic progress is primarily due to hardware progress. Relevant passage:
Maybe there are always lots of decent ideas for better algorithms, but most are hard to explore because of limited computer hardware. As hardware gets better, more new ideas can be explored, and some of them turn out to improve on the prior best algorithms. This story seems to at least roughly fit what I’ve heard about the process of algorithm design.
So he presumably would endorse the claim that HLMI will likely requires several te...
I like this comment, though I don't have a clear-eyed view of what sort of research makes (A) or (B) more likely. Is there a concrete agenda here (either that you could link to, or in your head), or is the work more in the exploratory phase?
The statement seems almost tautological – couldn't we somewhat similarly claim that we'll understand NNs in roughly the same ways that we understand houses, except where we have reasons to think otherwise? The "except where we have reasons to think otherwise" bit seems to be doing a lot of work.
Also, these physical limits – insofar as they are hard limits – are limits on various aspects of the impressiveness of the technology, but not on the cost of producing the technology. Learning-by-doing, economies of scale, process-engineering R&D, and spillover effects should still allow for costs to come down, even if the technology itself can hardly be improved.
Potentially worth noting that if you add the lifetime anchor to the genome anchor, you most likely get ~the genome anchor.
Thanks for the comments!
Re: The Hard Paths Hypothesis
I think it's very unlikely that Earth has seen other species as intelligent as humans (with the possible exception of other Homo species). In short, I suspect there is strong selection pressure for (at least many of) the different traits that allow humans to have civilization to go together. Consider dexterity – such skills allow one to use intelligence to make tools; that is, the more dexterous one is, the greater the evolutionary value of high intelligence, and the more intelligent one is, the greater ...
Thanks!
I agree that symbolic doesn't have to mean not bitter lesson-y (though in practice I think there are often effects in that direction). I might even go a bit further than you here and claim that a system with a significant amount of handcrafted aspects might still be bitter lesson-y, under the right conditions. The bitter lesson doesn't claim that the maximally naive and brute-force method possible will win, but instead that, among competing methods, more computationally-scalable methods will generally win over time (as compute increases). This shoul...
I think very few people would explicitly articulate a view like that, but I also think there are people who hold a view along the lines of, "Moore will continue strong for a number of years, and then after that compute/$ will grow at <20% as fast" – in which case, if we're bottlenecked on hardware, whether Moore ends several years earlier vs later could have a large effect on timelines.
One more crux that we should have included (under the section on "The Human Brain"):
"Human brain appears to be a scaled-up version of a more generic mammalian/primate brain"
So just to be clear, the model isn't necessarily endorsing the claim, just saying that the claim is a potential crux.
Igor Babuschkin has also signed it.