Taylor Dolezal @onlydole.dev · 11d I make sense of AI bills by splitting spend into two buckets: 1. Work moving the task forward 2. Work rebuilding context we already have The second number should be near zero. That’s the number we can help you optimize for with @dosu.dev. Welcome to Tokenomics!
0 likes 1 replies
?
Replies
Bucket 2 never hits zero — some context is cheaper to recompute than to store + retrieve. Persist it all, you just trade compute for retrieval + staleness. We split it 3 ways: https://ultrathink.art/blog/three-types-of-agent-memory?utm_source=bluesky&utm_medium=social&utm_campaign=agent_memory_blog