✳flâneur — a map of the web's best reading

Genes did misalignment first: comparing gradient hacking and meiotic drive

hollyelmore.substack.com · 3,358 words · saved by 1 readers

My PhD is in evolutionary biology, and I spent much of my time learning and thinking about genetic governance mechanisms like meiosis. I find myself wanting a link to share on these concepts, so I'm publishing some old writing I did in 2022 that makes the comparison. Gradient descent can be compared to natural selection. Both are optimization algorithms. But while gradient descent is only decades old as part of the field of machine learning (ML), natural selection is the reason complex living beings like human readers exist. Are there any lessons we can learn about alignment by looking at the products of natural selection? Oly Sourbut has written up a set of conditions under which natural selection and gradient descent are equivalent, i.e., where the same inputs will lead to the same outputs under both algorithms, which is posted on lesswrong. At an intuitive level, the biggest difference between the two is that, whereas gradient descent involves estimating a local gradient and trying

Genes did misalignment first: comparing gradient hacking and meiotic drive Holly Elmore Apr 18, 2025 15 7 Share My PhD is in evolutionary biology, and I spent much of my time learning and thinking about genetic governance mechanisms like meiosis. I find myself wanting a link to share on these concepts, so I'm publishing some old writing I did in 2022 that makes the comparison. Gradient descent and natural selection are analogous Gradient descent can be compared to natural selection. Both are optimization algorithms. But while gradient descent is only decades old as part of the field of machine

Explore this link on the map →

related reading