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

> can still be predicted and understood (no matter how difficult that is).

If we're making up hypotheticals, then LLMs can be predicted and understood (no matter how difficult that is). They don't run on pixie dust.



It's qualitatively different to go through source code and specifications to understand how something works than to look at a database with all the weights of an LLM and pretend like you could predict the output.


you don't have to - just run the matrix multiplication. it's no different from using a pocket calculator.




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

Search: