If GenAI is as powerful, reliable, and transformative as trumpeted in this Pollyannish survey (🤨), then there would be no need to produce those communication artifacts that create shared context between people.

Tests - why LLM test cases? Just tell GenAI: “Fix this bug and enforce correctness”. Correctness is the objective, not writing tests.

I have so many questions.

“Exploring the Intersection of Generative AI and Software Development.” arXiv [Cs.SE]. arXiv. http://arxiv.org/abs/2312.14262.

Mastodon Source 🐘