[leobg]

I made something like this for my kids:

1. Take a science book. I used one Einstein loved as a kid, in German. But I can also use Asimov in English. Or anything else. We’ll handle language and outdated information on the LLM level.

2. Extract the core ideas and narrative with an LLM and rewrite it into a conversation, say, between a curious 7 year old girl and her dad. We can take into account what my kids are interested in, what they already know, facts from their own life, comparisons with their surroundings etc. to make it more engaging.

3. Turn it into audio using Text-to-Speech (multiple voices).

[GeoAtreides]

Why wouldn't you just let the kid read (not listen) the book on their own and then have a conversation with them about it?

[leobg]

Because it may be in another language or aimed at another audience beyond my kid’s reading level.

[flakiness]

How do you get the source data (text) from a book? To me it is the major roadblock for LLM-based commercial content consumption.

[leobg]

Old books are on Gutenberg, archive.org etc.

Physical ones, I scan. Cutting the spine is easiest. But today you can also just take pics with your phone.

Many retailers also sell EPUB. Which is just HTML.

Obviously, that’s all for private consumption only. (Unless you’re OpenAI I guess. :-P)

[flakiness]

Oh you gotta serious! Salute to you from a lazy dad.