Reading up on DSPy

Using mitmproxy to intercept LLM API calls reveals the actual prompts libraries send, enabling users to assess framework necessity and craft better prompts.

Hand-tuning natural language prompts for AI systems accumulates debt that slows iteration, locks teams to one model, and should be replaced with metrics, tests, and automated prompt optimization.

Text optimization—modifying prompts, context, memory, and harnesses—is a legitimate, sample-efficient learning mechanism that deserves the same rigorous study as weight optimization.

Building AI agents reveals nine lessons including using best models for prototyping, fine-tuning for stable tasks, static typing to reduce hallucinated code, and closed-loop prompt optimization.

Recursive Language Models (RLMs) mitigate context rot in LLMs by wrapping long contexts in a REPL environment, turning the problem into a coding and reasoning task.