logoalt Hacker News

iot_devstoday at 3:54 AM1 replyview on HN

I personally read the thinking traces to know if the model is on the right direction


Replies

selestifytoday at 4:37 AM

I'm not saying they're not useful, of course they are. I am disputing that they are part of the agreed bargain between you and the proprietary LLM providers.

They explicitly do not promise reasoning traces. You (general you) agree to those terms and pay for that bargain anyways.

show 1 reply