This is of course my own take (what with having explicitly predicted this). But I do think you want to hold out a space for others to say, "Well *I* didn't predict it, and now I've updated."
@esyudkowsky
-
OpenAI Sora milestone prediction assessment February 2024
By
–
(I don't consider OpenAI Sora to have hit this mark yet. Though there's still 6 months until August 2024 to prove me wrong on the early side of this prediction.) https://
x.com/Im_actuallyaca
/Im_actuallyacat/status/1758268812640538946
… -
The Founder of e/acc Movement Speaks
By
–
The founder of e/acc speaks. Presented without direct comment.
-
Natural Selection’s Simple Rules Produce Unexpectedly Complex Human Outcomes
By
–
Natural selection is simple. A complicated story then happens, and human beings come out the other end in a way that doesn't match up to the simple stuff natural selection optimized for. I could indeed make this story more complicated; this doesn't help the safety-is-easy case.
-
Complexity in AI Alignment: Why Precision Matters for Safety
By
–
From my perspective, the more complicated you say these relationships are, the worse for anybody trying to build them out in some precise way that doesn't killeveryone. Rockets are complicated and that doesn't make them easier to notexplode.
-
Utility Function Terminology and Human Evolutionary Misalignment
By
–
I think that "utility function" in retrospect is a mathematical word of power that I should not have expected lay computer scientists to understand, so let's drop that. With humanity, the outer optimization criterion was inclusive fitness; our inner preference was not aligned.
-
Intelligence and Outcome Matching: The Core Problem Beyond Utility Functions
By
–
It isn't about "simple" utility functions or "monomania". The problem is just any sufficiently smart system whose work, on some level, can be viewed as matching up outputs and results, and learning.
-
Learning Reality and Selecting Outputs for Desired Outcomes
By
–
The problem that 'learn how reality works' and 'select outputs which, when they interact with reality, lead to X happening' is a simple great way of doing Y for a lot of possible Y. For example, with humans, Y is inclusive genetic fitness and X is all the stuff that humans want.
-
KQV matrices: wrong level of abstraction for AGI safety concerns
By
–
If you want something about kqv matrices, you're asking for an explanation on the wrong level of abstraction; if the problem was specific to kqv matrices we'd advocate "stop using transformer layers" not "shut down AGI research".