Stop Prompting LLMs: Stanford's DSPy Framework Shifts to Programming
mdancho84 · x · 2026-08-02
Stanford NLP's open-source framework DSPy advocates for a shift from writing manual prompts to programming large language models. It allows developers to build enterprise-grade AI by creating modular codebases, enabling rapid iteration and moving away from fragile prompt engineering.
More from coding & agent
- Open-Source Tool Turns YouTube Videos into Xiaohongshu Posts with AI — yangyi · 2026-10-16
- GitHub rewrote the 800k-line Copilot runtime in Rust using AI agents, cutting CPU and memory by over 90% — bibryam · 2026-10-16
- What's the hardest part of deploying AI in real businesses that nobody talks about — djgoel123 · 2026-10-16
- Cross-review coding workflow: Claude writes the plan, Codex audits it — theteknosaur · 2026-10-16
- NPCTalk makes GTA V NPCs conversable in ~1s, open-sourced for any game — ChocolateDull8971 · 2026-10-16
- Simon Willison: code mode is the future of tool calling, if it can be sandboxed — springrod · 2026-10-16