I apologise as my field is not related to proteins, but I do recall an interesting read about the subject from a few months ago. Here is the link if you wanna follow it yourself.

https://news.ycombinator.com/item?id=32262856

There are some interesting criticisms from the language, to the results, to the limitations of AlphaFold that I think seem to represent the prevailing opinion from biologists about the current scope of what ML can achieve on their field.

There is also push back to the complaints and some very optimistic people about Deep learning models on the field so perhaps you are right.

> It seems to me that the quality of any public discussion tends to increase when it’s relevant to the expertise in the room, and decrease when it involves people’s casual reads of complicated stuff about which they have vague but emotionally-charged impressions. HN folks have great, nuanced discussions about a wide range of technical questions, but we’re much less likely to collectively know what we’re talking about in questions of the latest hot-button political mudslinging.

The expertise on HN is indeed unrivaled.

If I want to learn about the quirks of a variational autoencoder in some neural network, I read the discussion between experts here on HN [1].

If I want to learn about protein folding, I can find relevant domain experts answering questions here on HN [2].

But why do you and so many others think that there is a covid-shaped hole in the expertise on HN? Do you really believe that out of all domain experts, the covid ones decided to stay away from here?

[1] https://news.ycombinator.com/item?id=39215242

[2] https://news.ycombinator.com/item?id=32262856