From what I understand, to work with copyrighted books they need to essentially format shift (i.e., scan and destroy the physical book). So a book vault would not solve this issue. A book vault would still be useful for…
Regarding your first point, if the cost of not doing it while you wait exceeds the cost of training/maintaining the model, then this approach still makes sense. This really depends on how fast you expect cheap (and…
> Then they feed it the original software (AFIK). My understanding is they did do the dance. From the article: "He fed only the API and the test suite to Claude and asked it to reimplement the library from scratch." One…
From what I understand, to work with copyrighted books they need to essentially format shift (i.e., scan and destroy the physical book). So a book vault would not solve this issue. A book vault would still be useful for…
Regarding your first point, if the cost of not doing it while you wait exceeds the cost of training/maintaining the model, then this approach still makes sense. This really depends on how fast you expect cheap (and…
> Then they feed it the original software (AFIK). My understanding is they did do the dance. From the article: "He fed only the API and the test suite to Claude and asked it to reimplement the library from scratch." One…