A can think of a few objections to that argument. First, evolution isn't 'over' for any of the species on that list, and if any of those seemingly maladaptive traits really do cause serious problems for those species, we would expect them to be selected against (there are some cases where they are associated with other traits that are important and helpful, and so won't be tossed overboard even then). Evolution also proceeds fairly slowly, in the sense that it may take many generations for a mutation to really become a positive adaptation and not just an oddity.

I agree, the examples aren’t the best chosen. But there are cases which are pretty well established in biology as being maladaptations. — The laryngeal nerve is the most famous of those [1] because there’s really no advantage to the way it develops, and its characteristics poses significant health problems that do affect evolutionary fitness negatively. Yet there’s no easy fix to solve its positioning through gradual mutations.

[1] https://en.wikipedia.org/wiki/Recurrent_laryngeal_nerve#Evid...

That nerve seems like an example of a local optimum. The way to avoid this is either to increase the mutation rate, or modify the fitness function so the intermediate states aren't so heavily penalised.

We can't easily do that with real evolution but it's configurable with evolutionary algorithms, as with most machine learning algorithms. The hard part is finding those parameters.

Biological evolution seem pretty susceptible to overfitting to ecological circumstances—I worry that there would be an analog for these techniques with NNs

There are well known problems that evolutionary systems are much better at solving than NNs. The multiplexer problem, for instance, or sorting networks, where the search space is too rugged or deceptive for neural network solutions.

Yeah, agreed -- evolution doesn't produce best, just good enough. But for large classes of 'problems', we can't (from a computational complexity standpoint) find best outcomes efficiently.

'Evolutionary' techniques, are, in some sense, 'trial and error'. For many tasks where we already have efficient algorithms, this isn't particularly useful. However, where we DONT have efficient algorithms, or know what the concept of what an 'efficient' algorithm even is, trial and error techniques, like evolutionary algorithms, seem like great choices.

In a rainforest there is no ‘best’ solution - John Holland

What’s the definition of best

Not having a 5 meter detour [1] of a nerve.

[1] https://en.wikipedia.org/wiki/Recurrent_laryngeal_nerve

350,000 species of beetles.

In music, evolution produced Bach, so it can't really be considered a failure.

It took a while though, and it's possible alternative approaches would have been produced a similar result more efficiently.

It also produced Justin Bieber and Weird Al. Point being, if the goal of your evolutionary algorithm is Bach, how do you filter for that result among the other million possibilities? And what makes Bach the success of music? Maybe more people prefer listening to Taylor Swift.

I love HN community. Awesome responses!