About genetic algorithms versus backpropagation, prompted by the universal weight subspace hypothesis.
Has this happened?
Yes 0 (0%)Not sure 45 (45%)No 56 (55%)
Votes cast 1–2 October 2026: 100,590 votes from 9,694 people.
Hacker News has set AI a lot of challenges over the years. Which ones has it met?
About genetic algorithms versus backpropagation, prompted by the universal weight subspace hypothesis.
Votes cast 1–2 October 2026: 100,590 votes from 9,694 people.
My entire motivation for using GAs is to get away from back propagation. When you aren't constrained by linearity and chain rule of calculus, you can approach problems very differently.
For example, evolving program tapes is not something you can back propagate. Having a symbolic, procedural representation of something as effective as ChatGPT currently is would be a holy grail in many contexts.