Watching the shift from hand written prompts to systematically optimizing prompt × model combinations is fascinating. It challenges how I’ve traditionally thought about prompt engineering and points toward a more systems-driven approach to reasoning.
Curious whether this becomes the default for LLM applications, where prompts aren’t static artifacts but continuously optimized components of the stack.
Super cool to see this being shipped.
Watching the shift from hand written prompts to systematically optimizing prompt × model combinations is fascinating. It challenges how I’ve traditionally thought about prompt engineering and points toward a more systems-driven approach to reasoning.
Curious whether this becomes the default for LLM applications, where prompts aren’t static artifacts but continuously optimized components of the stack.
Great read and very cool approach to optimization. Feels like we're getting closer to removing humans from the code review loop entirely.