Thanks Nate, this is a great summary of the case for MIRI’s approach!
Out of curiosity, is there an example where algorithms led to solutions other than Bird and Layzell? That paper seems to be cited a lot in MIRI’s writings.
It’s cited a lot in MIRI’s writing because it’s the first example that pops to my mind, and I’m the one who wrote all the writings where it appears :-p
For other examples, see maybe “Artificial Evolution in the Physical World” (Thompson, 1997) or “Computational Genetics, Physiology, Metabolism, Neural Systems, Learning, Vision, and Behavior or PolyWorld: Life in a New Context.” (Yaeger, 1994). IIRC.
Note that always only citing one example easily gives the impression that it’s the only example you know of, or of this being an isolated special case, so at least briefly mentioning the existence of others could be better.
Thanks Nate, this is a great summary of the case for MIRI’s approach!
Out of curiosity, is there an example where algorithms led to solutions other than Bird and Layzell? That paper seems to be cited a lot in MIRI’s writings.
It’s cited a lot in MIRI’s writing because it’s the first example that pops to my mind, and I’m the one who wrote all the writings where it appears :-p
For other examples, see maybe “Artificial Evolution in the Physical World” (Thompson, 1997) or “Computational Genetics, Physiology, Metabolism, Neural Systems, Learning, Vision, and Behavior or PolyWorld: Life in a New Context.” (Yaeger, 1994). IIRC.
Note that always only citing one example easily gives the impression that it’s the only example you know of, or of this being an isolated special case, so at least briefly mentioning the existence of others could be better.
It also is less reliable when you cite only one source because what that source says could be false(either intentionally or accidentally).