(danieldelaney.net)

858 points cryptophreak | 1 comments | 04 Feb 25 16:06 UTC | HN request time: 0.227s | source

Show context

croes ◴[04 Feb 25 16:22 UTC] No.42934439[source]▶

Natural language isn’t made to be precise that’s why we use a subset in programming languages.

So you either need lots of extra text to remove the ambiguity of natural language if you use AI or you need a special precise subset to communicate with AI and that’s just programming with extra steps.

replies(10): >>42934517 #>>42934537 #>>42934619 #>>42934632 #>>42934651 #>>42934686 #>>42934747 #>>42934909 #>>42935464 #>>42936139 #

kokanee ◴[04 Feb 25 17:17 UTC] No.42935464[source]▶

>>42934439 #

> or you need a special precise subset to communicate with AI

haha, I just imagined sending TypeScript to ChatGPT and having it spit my TypeScript back to me. "See guys, if you just use Turing-complete logically unambiguous input, you get perfect output!"

replies(1): >>42947232 #

1. charlieyu1 ◴[05 Feb 25 11:51 UTC] No.42947232[source]▶

>>42935464 #

I guess we could have LLM to translate natural language to some precise subset, get it processed, then translate the output back to natural language

↑

Chat is a bad UI pattern for development tools