FAQCommon questions and answers about using WecoGetting Started What's the easiest way to get started with Weco?How does the onboarding copilot (preview) work?How do I log in to Weco?How do I log out?Which Python versions are supported?Does Weco work on Windows, macOS and Linux?Where can I view my run history? Basic Usage & Setup What does weco run modify?How do I keep my original file safe?What does --eval-command do?Where does the evaluation script run?Which LLMs does Weco support? Evaluation Scripts & Metrics Does my evaluation script need to be in Python?Does the evaluation script have to match my code's language?How does Weco read my metric?How do I choose a metric and goal?Does the metric name need to exactly match the --metric flag?How do I pass environment variables?Are there evaluation script examples?What is reward hacking and how do I prevent it? Optimization Capabilities Which kinds of tasks can Weco optimize?Which programming languages can Weco modify?What metrics can I optimize for?Can I point Weco at a directory instead of a single file?Can Weco optimize multiple files at once?How do I constrain the search space? Performance & Best Practices How long can my evaluation take?Can I optimize for multiple metrics?Is nondeterminism in my evaluation a problem?How can I provide richer feedback than just one number?How do I pass extra context? Advanced Features & Troubleshooting What does the solution tree show?How do I download a specific solution?How do I share solutions with teammates?How do I limit runtime or cost?Can I run multiple Weco runs in parallel?Does Weco support private/self-hosted LLM endpoints?Can Weco auto-stop when the metric plateaus? Privacy & Security What data does Weco send to the cloud?Prompt EngineeringIteratively improve a prompt for solving AIME problems
