flâneur

Harness Engineering for Self-Improvement | Lil'Log

lilianweng.github.io · 6,094 words · saved by 19 readers

The concept of recursive self-improvement (RSI) dates back to I. J. Good (1965), where he defined an “ultraintelligent machine” as a system that can surpass humans in all intellectual activities and design better machines to improve itself. Yudkowsky (2008) used the phrase “recursive self-improvement” for a specific feedback loop: an AI uses its current intelligence to improve the cognitive machinery that produces its intelligence. This feedback loop in modern AI may indicate the model rewriting its own weights directly, or more broadly the model improves the training pipeline and the deployment system, which in turn enables a better successor model with improved performance across economically valuable tasks. The speed of research development in AI has been shown to drastically accelerated in frontier labs (Anthropic; OpenAI).

Table of Contents Harness Design Patterns Pattern 1: Workflow Automation Pattern 2: File System as Persistent Memory Pattern 3: Sub-agent and Backend Jobs Case study: Coding Agent Harness Harness Layer vs Core Intelligence? Harness Optimization Context Engineering Workflow Design Self-Improving Harness Evolutionary Search Joint Optimization with Model Weights Future Challenges Citation Appendix: Some useful benchmarks References The concept of recursive self-improvement (RSI) dates back to I. J. Good (1965) , where he defined an "ultraintelligent machine" as a system that can surpass humans in

saved by

related reading