Actually the Vikram said he had initially added a search feature and it didn't appear to be very useful. He says:
search is an awful way to curate text when your readers don't know what is interesting about it. This is obvious in retrospect, but it didn't occur to me until I showed what I built to folks.
I would be interested to see what an LLM could make out of this archive. How it might categorize the threads or how it might help make sense of it. Vikram's manual curation is the useful part. In the podcast, he mentions he would like to see what could be done with an AI and the archive.