This is a classic sequence post: (mis)appropriated Japanese phrases and cultural concepts, references to the AI box experiment, and links to other sequence posts. It is also especially ironic given Eliezer’s recent switch to doomerism with his new phrases of “shut it all down” and “AI alignment is too hard” and “we’re all going to die”.
Indeed, with developments in NN interpretability and a use case of making LLM not racist or otherwise horrible, it seems to me like their is finally actually tractable work to be done (that is at least vaguely related to AI alignment)… which is probably why Eliezer is declaring defeat and switching to the podcast circuit.
Huh. I’d assumed that Yud misunderstood every concept he’d self-educated on to the point of squeezing something he didn’t really grok into his biases, but he also misses the mark where he *has* had formal education (halacha) –
In the post first linked from that one, he says
“There’s no exemption whereby, if you manage to go without stealing all year long, you can skip the word gazalnu and strike yourself one less time. That would violate the community spirit of Yom Kippur, which is about confessing sins—not avoiding sins so that you have less to confess.”
And he’s *so close*. You can’t exempt yourself from communal ashamnu because it’s communal. It’s not about avoiding sins as an individual, it’s about acknowledging that we are a community and share responsibility for living in one.
A LessWrong nightmare, tbf.
(Also, Leizerle, kinderle, are you telling me you’ve never been stiff necked? Never given harmful advice? Never scoffed? It’s a pretty general list, Yud.)