Tag
Peter Steinberger used Codex to build a fully automated QA bot that automatically generates tests, runs tests after each code commit, and can automatically fix bugs and submit PRs, greatly improving development efficiency.
A discussion about how feedback systems (static analysis, coverage tools, profiling) are more critical than the choice of LLM for making AI agents useful, illustrated by Oracle's work generating tests for GraalVM Native Image reflection metadata.
Rule2DRC introduces a large-scale benchmark for DRC script synthesis with 1,000 tasks and 13,921 evaluation layouts, and proposes SplitTester, which uses execution feedback to improve program selection and functional correctness.