@whitequark Ah in my experience turn off your brain books are perfect for recommendation algorithms. Flashbanged are human recommendations almost entirely defined by their nature. I have read 12 romance books in a weekend and enjoyed it but couldn't tell you the title when I'm done.

@whitequark I mean there are like entire genres of fun reads that aren't challenging at all. Romance(primarily straight though kindle and kobo have a bunch of lgbtq versions of the genre) and litrpg which are literally book version of the number goes up feeling.

@lina Do they even need to be LLMS at that point ? Recommendations engines and the entire machine learning field got real big before LLMs stole all the thunder. And systems that output structured data to be interpreted by a tradional program seems more constrained usefully than one that has to write english as an output. I'm thinking about the rumored apple health AI, and a recommendation engine that finds a correlation between me opening discord on tuesday mornings and taking less steps that day seems like a better design than an LLM processing the same data.

@whitequark you mean the, trick the user into learning how to use a mouse, game doesn't have keyboard shortcuts?

@whitequark i found an emudev game the other day, and haven't made time for that. Now this?

@siguza paper.final.docx(3)