

Collecting code coverage for blackbox binaries the wrong way.


LLM agents increasingly perform autonomous actions through external tools, leading to complex and evolving safety risks. However, existing safety testing targets expert-designed safety violations, and the corresponding outcomes are evaluated by hard-coded
We generated 85K lines of iOS tests with minimal manual effort.






Golden sets are unit tests for probabilistic behavior: curated cases, versioned rubrics, and gates that prevent quality regressions from shipping as surprises.





morphllm.com5mo ago