Mike Papadakis

Automated test generation achieves near-zero bug detection on LLM-written code not because tests fail to execute the bugs, but because LLM-generated assertions consistently fail to notice when a fault occurs.

Synthetic semantic supervision allows small transformers to outperform larger models in code representation tasks, offering a scalable alternative to traditional methods.

Existing UI test suites validate less than half of the behavioral relations they exercise, exposing critical gaps in testing effectiveness.