✨
AI Summary
- Sending more tokens can be cheaper and more effective than compaction.
- Default settings and no compaction often outperform optimized methods.
- Prompt caching significantly reduces costs and latency for AI interactions.
Guests on This Episode
LB
Louis-Francois Bouchard
1 podcast appearance
OS
Omar Solano
1 podcast appearance
SV
Samridhi Vaid
1 podcast appearance