Hacker News new | ask | show | jobs
by cornholio 23 days ago
If I understood correctly, the model will get it right because it knows when it isn't right.
3 comments

Essentially, yes that's right! There's some subtlety in how to let it know it was wrong (returning things as tool errors because it trained on that), but that's the gist of it - sort of a self-correcting architecture.
the missile knows where it is because it knows where it isn't