Comment by himata4113

I always found it weird that we don't have glacial type input for llms or any kind of active-working memory.

There's no reason why we shouldn't be able to expose active relevant information that is only relevant for the next request: current agents running, time, etc.

There's also no reason why we shouldn't have a cheaper lossy input which uses way less bytes per token - see deepseek flash 4.1.