undefined | Better HN

0 pointspessimizer7mo ago0 comments

I feel the main thing LLMs are teaching us thus far is how to write good prompts to reproduce the things we want from any of them. A good prompt will work on a person too. This prompt would work on a person, it would certainly intimidate me.

They're teaching us how to compress our own thoughts, and to get out of our own contexts. They don't know what we meant, they know what we said. The valuable product is the prompt, not the output.

0 comments

nicce7mo ago

Einstein predicted LLMs too?

> If I had an hour to solve a problem, I'd spend 55 minutes thinking about the problem and five minutes thinking about solutions.

(not sure if that was the original quote)

Edit: Actually interesting read now that I look the origin: https://quoteinvestigator.com/2014/05/22/solve/

fouronnes37mo ago

Thanks, now I want to read a sci-fi short story where LLM usage has gotten so high that human-to-human language has evolved to be like LLM prompts. People now talk to each other in very intimidating, very specific paragraph long instructions even for simple requests and conversation.

nonethewiser7mo ago

so an extremely resource intensive rubber duck

pessimizerOP7mo ago

For you, yes. For me it's like my old teapot that I bought when I didn't drink tea and I didn't have a french press just because I walked past it in Target, and didn't even start using for 5 years after I bought it. Since then it's become my morning buddy (and sometimes my late night friend.) Thousands of cups; never fails. I could recognize it by its unique scorch and scuff marks anywhere.

It is indifferent towards me, though always dependable.

throwanem7mo ago

How is it as a conversationalist?

1 more reply

j / k navigate · click thread line to collapse