News for hackers. Stuff that matters.

A comment on GLM-4.5: Reasoning, Coding, and Agentic Abililties. Parent comment

Re:GLM-4.5: Reasoning, Coding, and Agentic Abililties by Jabrov on Monday July 28, 2025 @04:40PM (#44715342)
Not exactly true ... KV and prompt caching is a thing
[ Parent | on HN ]
Re:GLM-4.5: Reasoning, Coding, and Agentic Abililties by yahoozoo on Monday July 28, 2025 @05:06PM (#44715642)
Assuming you include the same prompts in the new request that were cached in the previous ones.
[ Parent | on HN ]
Re:GLM-4.5: Reasoning, Coding, and Agentic Abililties by throw310822 on Monday July 28, 2025 @06:57PM (#44716766)
As far as I understand, the entire chat is the prompt. So at the each round, the previous chat up to that point could already be cached. If I'm not wrong, Claude APIs require an explicit request to cache the prompt, while OpenAI's handle this automatically.
[ Parent | on HN ]
Re:GLM-4.5: Reasoning, Coding, and Agentic Abililties by littlestymaar on Tuesday July 29, 2025 @09:14AM (#44722934)
I don't understand how you are downvoted…
[ Parent | on HN ]