sometdog

Last May they introduced a new rate limit for that endpoint of 1 request per minute.

They removed the ability to create "radio" stations off of playlists, which does make discovery somewhat more difficult.

That is true, but you can combine LLMs with other tools to get sourcing and more accurate answers overall. Instead of using the LLM to directly answer a question, you can use the question to search for relevant text in a particular knowledgebase, and then use the LLM to summarize those results.

What would your argument be based on?