Cisco AI introduced FAPO, a Claude Code-driven system that optimizes LLM pipelines from baseline prompts to target accuracy. FAPO beat GEPA on 15 of 18 model-benchmark comparisons, with mean gains reaching +33.8pp on benchmarks requiring pipeline changes. The project ships open source under Apache 2.0.
Tap to vote and see what everyone thinks.
Summary by ByteBrief
Zhipu AI's GLM-5.2 trails closed-source leaders on coding tasks