dirk comments on How do I design long prompts for thinking zero shot systems with distinct equally distributed prompt sections (mission, goals, memories, how-to-respond,… etc) and how to maintain llm coherence?

[dirk]

Per https://​​eightyonekilograms.tumblr.com/​​post/​​772774450949177344/​​i-work-at-google-yes-this-is-basically-correct , long LLM context windows are basically just short windows extended with imperfect hacks, so the loss of coherence is probably hard to avoid.