logoalt Hacker News

Xirdustoday at 4:07 PM2 repliesview on HN

Unironically, LLM is absolutely amazing at giving you the right answers when you put in wrong input, compared to every other algorithm ever invented.


Replies

throwaway27448today at 8:15 PM

I was hoping a lossy semantic reasoning machine would put to bed words such as "right" and "wrong" outside of formal logic, but apparently this fight has just begun

antonvstoday at 7:58 PM

That’s one of the properties that distinguishes intelligence from traditional deterministic algorithms.

show 1 reply