Computer Science · Software
An exploratory study compared four ways to develop software with and without conversational AI systems. Human–AI collaboration produced higher-quality, better-organized test suites, while autonomous AI agents generated functionally correct code more quickly but added complexity and untested decisions.
A system called IntentionTest generates software tests from a developer’s description of what a function should do in a particular situation. Across 3,680 test cases from 12 open-source projects, it outperformed four other test-generation methods on measures of relevance, coverage and successful execution.
AI vulnerability detectors often perform less well on software projects outside their training data. A study finds that cleaner, more varied training data and an encoder-based design improved detection, including a reported 6.8% gain in recall on the BigVul benchmark.
