DSPy introduces Flex: Joint code and prompt optimization slashes LLM calls by 75%
dbreunig · x · 2026-08-06
DSPy has introduced Flex, a new feature that optimizes the program's code in addition to the prompt.
According to the cited results using the GEPA optimizer, Flex improved task accuracy from 90% to 95% while making 75% fewer LLM calls. This approach offers a cheaper, faster, deterministic, and auditable method for developing LLM applications.
Related event: DSPy Introduces Flex Module for Code and Prompt Optimization(3 posts)→
More from coding & agent
- X402 Protocol Empowers AI Agents: On-Chain Micropayments Hit $50B Volume — kleffew94 · 2026-08-06
- Prime Intellect Releases Self-Improving Agent, Beating Human Baseline on ARC-AGI-3 — mattbeane · 2026-08-06
- Meta to Release Coding Agent Competing with OpenAI and Anthropic — pstAsiatech · 2026-08-06
- Vibe Coders Beware: AI Software Agents Often Skip Security Entirely — ericelliott_ · 2026-08-06
- Coarena Launches: An Arena for Models to Compete in Computer-Use Tasks — ycombinator · 2026-08-06
- Paper Proposes FutureBridge-OPD: Validating Teacher Guidance Before Distillation — rohanpaul_ai · 2026-08-06