I guess the end-goal is the same as "Acceptance Testing", have the LLMs write both unit tests and implementation. Just missing the piece of letting the LLMs debug the inevitable crashes that will happen in production, and be able to hotfix it, so the website visitors (LLM crawlers) don't complain.
[0] https://github.com/pythagora-io/gpt-pilot
[1] https://marketplace.visualstudio.com/items?itemName=Pythagor...
Best UX so far.
Wish it had FIM completion via local LLM or Gemini Flash like models and better Git GUI, it would have replaced vscode for me already then.
https://blog.pythagora.ai/2024/10/01/pythagora_v1-release-re...