Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces

Re:Stop Anthropomorphizing Intermediate Tokens as Reasoning/... by wrsh07 on Friday August 21, 2026 @09:33AM (#49387828)

To quote Sarah Constantin:

> Humans Who Are Not Concentrating Are Not General Intelligences^

But yeah, you should still treat them with humanity. (Related: you should treat LLMs well, not because they're human but because you are^^)

^ https://srconstantin.github.io/2019/02/25/humans-who-are-not...

^^ hmm couldn't find this tweet but didn't look too hard

[ Parent | on HN ]

Re:Stop Anthropomorphizing Intermediate Tokens as Reasoning/... by ModernMech on Friday August 21, 2026 @09:40AM (#49387920)

I gotta say though, turning on caps lock does seem to get them to cut out the inane banter.

[ Parent | on HN ]

Re:Stop Anthropomorphizing Intermediate Tokens as Reasoning/... by wrsh07 on Friday August 21, 2026 @10:21AM (#49388556)

There are other methods, including asking them to eg speak using the Google style guide rules, or to speak at 2/10 verbosity, or to speak as if they're talking to a very intelligent middle schooler, or to use simple sentences in subject verb object form

[ Parent | on HN ]

Re:Stop Anthropomorphizing Intermediate Tokens as Reasoning/... by zeryx on Saturday August 22, 2026 @07:30AM (#49398642)

My favorite - reply like I do, review my previous messages to understand my tone and verbosity. As much as needed, as little as possible

[ Parent | on HN ]

Re:Stop Anthropomorphizing Intermediate Tokens as Reasoning/... by ModernMech on Saturday August 22, 2026 @07:36AM (#49398672)

It'll end up like that episode of Dr. Who where they get stranded in a lunar tour bus -- slowly starting to mimic you, and then it'll predict and replace you.

[ Parent | on HN ]