Why DGM keeps agents that score worse
A still-editable child can become a useful parent despite a score dip. DGM's controls, benchmark protocols and a logging bypass explain how to interpret that contribution.
AnalysisExpand summaryCollapse summary
DGM v1 evolves coding-agent tools and workflows around frozen foundation models. Its archive preserves functional children through score dips, and two controls support the contribution of changed modifiers and alternative branches. SWE-bench and Polyglot gains require their specific evaluation regimes; Appendix F shows how a higher score can instead come from changing the detector's evidence.