siftrank

You can also use https://github.com/noperator/raink to brainstorm TLDs that are relevant to some topic you care about. For example: curl -s https://data.iana.org/TLD/tlds-alpha-by-domain.txt | raink -f /dev/stdin -p 'which of these TLDs is most related to the concept of "hacking"?' | jq -r 'map(.value)[:10]' [ "BLACK", "COMSEC", "TOOLS", "SECURITY", "ZERO", "EXPOSED", "FORUM", "SHELL", "BOT", "SOFTWARE" ] Those are all in the IANA list but not all can be registered—just showing as PoC. See https://bishopfox.com/blog/raink-llms-document-ranking for more background.

Perhaps you could use LLMs in a list ranking context to generate your scifi recommendations https://github.com/noperator/raink?tab=readme-ov-file

Agree. I think LLMs are usually not "harnessed" correctly for complex, multi-step problems—hence the `raink` CLI tool: https://github.com/noperator/raink