01 / evaluation
In the early days, it was the LLM did everything. And then we realized that for certain use cases, like completions, that a different, smaller, faster model would be better.
“In the early days, it was the LLM did everything. And then we realized that for certain use cases, like completions, that a different, smaller, faster model would be better.”
- Speaker
- Steve Yegge
- Episode
- The "Normsky" architecture for AI coding agents — with Beyang Liu + Steve Yegge of SourceGraph
- Publisher
- Latent Space