Tag: bfcl
skill
★ 137
Adversarial Code Review for Pipeline Hardening
This skill facilitates the systematic hardening of BFCL training and evaluation pipelines through iterative adversarial review rounds. It employs an external LLM to identify potential bugs, which are then verified against the codebase to en…
skill
Adversarial Code Review for ML Pipelines
Systematically hardens complex ML pipelines, such as BFCL, through iterative adversarial review rounds using external LLMs. This process tracks cumulative fixes and focuses on identifying subtle bugs that cause data corruption or evaluation…