←back to thread

I'm absolutely right

(absolutelyright.lol)
648 points yoavfr | 1 comments | 05 Sep 25 12:36 UTC | HN request time: 0.001s | source
Show context
ryukoposting ◴[05 Sep 25 13:20 UTC] No.45138240[source]▶
I wonder how much of Anthropic's revenue comes from tokens saying "you're absolutely right!"
replies(3): >>45138562 #>>45138659 #>>45138997 #
alentred ◴[05 Sep 25 13:49 UTC] No.45138562[source]▶
Oh wow, I never thought of that. In fact, this surfaces another consideration: pay-per-use LLM APIs are basically incentivized to be verbose, which may be well in conflict with the user's intentions. I wonder how this story will develop.

In an optimistic sci-fi line of thinking, I would imagine APIs using old-school telegraph abbreviations and inventing their own shortened domain languages.

In practice I rarely see ChatGPT use an abbreviation, though.

replies(1): >>45138784 #
1. SJMG ◴[05 Sep 25 14:07 UTC] No.45138784[source]▶
> pay-per-use LLM APIs are basically incentivized to be verbose There's competing incentives. Being verbose, let's them charge for more tokens, but it's also not prized by text-consumers in the most common contexts. As there's competition for marketshare, I think we see this later aspect dominate. Claude web even ships with a "concise" mode. Could be an issue long term though, we'll have to wait and see!

> In an optimistic sci-fi line of thinking, I would imagine APIs using old-school telegraph abbreviations and inventing their own shortened domain languages.

In the AI world this efficient language is called "neuralese". It's a fun rabbit hole to go down.