DSPy Introduces Flex: Optimizing Code Alongside Prompts
lateinteraction · x · 2026-08-06
The DSPy framework has introduced Flex, expanding its capabilities from prompt optimization to program code optimization. According to the quoted tweet, combined with GEPA, Flex improved accuracy on a task from 90% to 95% while reducing LLM calls by 75%.
Additionally, the upcoming Bay Area DSPy Meetup will focus on framework features and tricks. Michael Isaac will detail Flex's goals and implementation, alongside lightning talks on using DSPy and GEPA to match writing tone and other topics.
Related event: DSPy Introduces Flex for Code-Level Optimization, Slashing LLM Calls(6 posts)→
More from coding & agent
- Mastra launches skill search for agents with on-the-fly loading — ycombinator · 2026-08-26
- GitHub Spec Kit booms: Spec-driven development replaces vibe coding — Shruti_0810 · 2026-08-26
- FreeLLMAPI Aggregates 34 Free LLM Providers into Single OpenAI-Compatible Endpoint — tom_doerr · 2026-08-26
- OpenAI demos WebMCP: Building agent-ready sites for 3D collaboration — OpenAI · 2026-08-26
- OpenAI desktop app adds WebMCP support, enabling Codex to deploy apps to Sites — OpenAIDevs · 2026-08-26
- devOS: MCP Server for Collaborative Memory in Coding Agents — black_phoenix9 · 2026-08-26