Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Let's grant that context engineering is here to stay and that we can never have context lengths be large enough to throw everything in it indiscriminately. Why is this not a perfect palce to train another AI whose job is to provide the context for the main AI?


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: