Back to Blog
Dominations base layouts enlightenment6/30/2023 Related: the most accurate map of the territory is the territory itself, but what happens when the territory is slippery ?Īn apocryphal story goes that, when Pope Benedict XI was in search of a fresco artist he sent a messenger to a man named Giotto. Never mind how much it sounds like a wide-eyed Victorian-era gentleman rattling off classics one supposedly has read: reading a whole textbook is not an atomic action, let alone going through entire courses and assuming infinite motivation on the part of the victim. Maybe it's just me, but I get dizzy when every other word of someone's sentence packs months' worth of implied thankless work. What happens in the wild, in contrast, looks something like grocery shopping: "Oh, you need vector calculus, and set theory, and–textbooks? Read Axler, then Jaynes for probability 'cause you don't want to learn from those dirty, dirty frequentists.yeah sprinkle in some category theory as well from Lawvere, maybe basic game theory, then go through MLAB's course." Sure, there's nothing groundbreaking here, but that's precisely the point. How to specify a reward function as Python code.How to train a handwriting classifier on the MNIST dataset.The minimum viable empirical researcher (and by 'minimum', I mean it) should probably know: So for instance, since we’re all trying to get more dignity points in before 2028, let’s consider the case of the empirical alignment researcher. That is, let's invert the question of how to produce experts and instead ask: "What things should I be able to do, to be considered a minimum viable expert in X?" The real problem is not finding better presentations or a better Chatty McTextbook explanation, but can be found by observing what does not change. But alas, my internal model says we will not go from doomed to saved with the nth attempt at prettifying the proof of the rank-nullity theorem. If my intention was merely to add to the growing pile of Intro to AI Safety (Please Don't Betray Us and Research Capabilities Afterward) courses out there then we can all just pack up and go home and forget this poorly-worded post ever existed. The proposal (which I call ' Blackbelt' for obscure reasons) is really simple: a dependency graph of tests of skill. So I figured, third time’s the charm, right? It's just that, for some reason, like moths to a flame or a dog to its vomit I just keep coming back to it. It’s a side project of mine that could be built by your average first-year CS undergrad and that I have shelved multiple times. We don't have a reliable way to gauge the potential of someone we've never met to do great work. LessWrong–and by extension greenfield alignment– is currently teetering on the edge of an Eternal September: most new people are several hundred thousand words of reading away from automatically avoiding bad ideas, let alone being able to discuss them with good truth-seeking norms. Alignment researchers don't seem to stack.It takes up to five years for entrants in alignment research to build up their portfolio and do good work–too slow for short timelines. Upskilling is hard: the available paths are often lonely and uncertain, workshops aren't mass-producing Paul Christianos, and it's hard for people to stay motivated over long periods of time unless they uproot their entire lives and move to London/Berkeley. There seems to be a stupid, embarrassingly simple solution to the following seemingly unrelated problems:
0 Comments
Read More
Leave a Reply. |