Probably the distinction is messier in real life, and there are lots of different sub-levels.
These posts both focus on the difference between two ways that a higher-level optimizer (evolution, gradient descent) can train an intelligence: instincts vs. These might be different proxy objective evolution gave me, maybe a little more robust, but not fundamentally different from the sex one. I just want kids because I like kids and feel some vague moral obligations around them. How awkward is that for this argument? I think not very - I don’t want to, eg, donate to hundreds of sperm banks to ensure that my genes are as heavily-represented in the next generation as possible. I feel compelled to admit that I do want to have kids. I’m out of its control, doing my own thing. Evolution got one chance to set my value function when it created me, and if it screwed up that one chance, it’s screwed. That is, just because I’m smart enough to know that evolution gave me a sex drive so I would reproduce - and not so I would have protected sex with somebody on the Pill - doesn’t mean I immediately change to wanting to reproduce instead. I know this and I am pretty smart and that doesn’t matter. Now in the modern world, evolution’s proxy seems myopic - sex is a poor proxy for reproduction. In the ancestral environment, where there was no porn or contraceptives, sex was a reliable proxy for reproduction there was no reason for evolution to make me mesa-optimize for anything other than “have sex”. But my sex drive is just that: a sex drive. Evolution “wants” us to reproduce and pass on our genes. The classic example, again, is evolution. Mesa-optimizers would have an objective which is closely correlated with their base optimizer, but it might not be perfectly correlated. It instilled the hunger drive, and I figured out that the best way to satisfy it was to open my fridge and eat cheese. Evolution didn’t mechanically instill the behavior of opening my fridge and eating a Swiss Cheese slice. Evolution gave them drives, like hunger and lust, and the animals figured out ways to achieve those drives in their current situation. As animals became more complicated, they started to do some of the work themselves. For a long time, it did so very mechanically, inserting behaviors like “use this cell to detect light, then grow toward the light” or “if something has a red dot on its back, it might be a female of your species, you should mate with it”. Two paragraphs from the mesa-optimizers post, which I quoted again in the adaptation-executors post:Ĭonsider evolution, optimizing the fitness of animals.
0 kommentar(er)
