“allow it to change its own harness for better context management, etc”
It gets a little too hand-wavey there. If it were that simple, wouldn’t coding agents be doing this already? In my experience the memories CC creates for itself are like any other LLM writing: overly verbose and full of irrelevant details, often missing the point of the feedback that caused it to create the memory in the first place. LLMs are really bad at knowing how to prompt LLMs, and that makes perfect sense for because they’re incapable of introspection.
Whose taste...
I think good taste is objective to an extent, especially given a particular production context.
i dont think there is any LLM which is perfect...everyone is trained on different data....so its obviuos everyone don't like it....
“allow it to change its own harness for better context management, etc”
It gets a little too hand-wavey there. If it were that simple, wouldn’t coding agents be doing this already? In my experience the memories CC creates for itself are like any other LLM writing: overly verbose and full of irrelevant details, often missing the point of the feedback that caused it to create the memory in the first place. LLMs are really bad at knowing how to prompt LLMs, and that makes perfect sense for because they’re incapable of introspection.