very nice idea. Would be nice if you could also keep desired context as a free parameter and let the models tell you what maximum context you could have.
ooo, I was looking for something like this when I was designing our agent architecture. Wish this existed before. Ended up building something quite similar, although this looks more complete and modular. Nice!
When I saw the title, I had assumed it was going to have something to do with formal verification or correct by construction. But obviously different, and a bit over my head. Do you have a real world use case where this would be used that other methods wouldn't work?
Looks very cool, would love to give it a go. A lot of the time an audible book can be ruined by the narration rather than the writing. would be good to try out a few different voices.
Might just be being dense but I tried to drag and drop alice in wonderland and it's complaining that the file is too large. How should one try it out?
Worked for a company that attempted to do something very similar for the global economy. At the time it ended up being too laborious but this was 10 years ago or something. Seems like a good time to do something like this. I'll keep an eye out for you!
I don't actually understand why this sort of thing isn't everywhere theres a discussion. Engineering wise, it's nothing to add. People use grok all the time on twitter.
Seems like that Disney + example can’t be allowed right? Those are two completely different products (theme park/streaming service). Is the law really that f’ed up?