Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Show HN: 1667, a terminal UI for writing fiction with language models. Parent comment
I like to be strategic summarize the correct places when the context gets full.
There is a request inspector that shows everything that is sent.
I'm experimenting with prompt ordering strategies as well. this is surprisingly complext when you take into account the different model providers.
For example local models usually do a different form of prompt caching than for example openai and anthropic
There are no comments on this comment yet.
I like to be strategic summarize the correct places when the context gets full.
There is a request inspector that shows everything that is sent.
I'm experimenting with prompt ordering strategies as well. this is surprisingly complext when you take into account the different model providers.
For example local models usually do a different form of prompt caching than for example openai and anthropic