workbreak
Re:GLM Built Its Own Inference Infrastructure
on Thursday September 17, 2026 @08:43AM (#49739909)
Every tool call is essentially entire prompt so far sent again with the response and that's why cache rates are so high for agentic workloads.
This really bites when using expensive models since most models are 1/10 for cached input.
Re:Ask HN: Comment here about whatever you're passionate about at the ...
on Monday November 06, 2023 @08:46PM (#38172095)
You might find this video interesting: https://www.youtube.com/watch?v=kse87ocS0Uo
It talks about different levels of thinking without going into any religion or culture.
PS: The YouTube channel seems to be related to dating, but this particular video doesn't have any of that.