[–] nithiink 10d ago ↗ How do you handle prompt caching? A lot of cost savings for a single model chat come from cache hits on the conversation context, and switching models invalidates that cache — the new model has to reprocess everything at full input price. [–] [dead] FrancescoMassa 7d ago ↗ [flagged]
[–] patch_dev 10d ago ↗ What does this solve that well used subagents doesn't solve already? [–] FrancescoMassa 10d ago ↗ On our tests subagents & well used workflows are 20-30% more expensive for context & token efficiency
[–] FrancescoMassa 10d ago ↗ On our tests subagents & well used workflows are 20-30% more expensive for context & token efficiency
5 comments
[ 3.0 ms ] story [ 20.3 ms ] thread