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

How does this concept explain (for example) an LLM’s ability to provide a precis of an article? Or to compare two blocks of text and highlight differences? Or to take an existing block of code and find and correct an error?


Stephen Wolfram has a great post on this: https://writings.stephenwolfram.com/2023/02/what-is-chatgpt-...

It's really long! But worth the read.


Exactly what I am wondering, these are the complex things that "Oh it just dumps out tokens" explanations don't explain.




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

Search: