Easy answer. Ask ChatGPT to write testable code, and tests for the code, then just verify the tests. If the tests don't work, have ChatGPT use the test output to rewrite the code until it does.
If you can't have ChatGPT write testable code because of your architecture, you have other problems. People with bad process and bad architecture saying AI is bad because it doesn't work well with their dumpster fire systems, 100% facepalm.
> If you can't have ChatGPT write testable code because of your architecture, you have other problems.
There exist lots of reasons why code is hard to test automatically that have nothing to do with the architecture of the code, but with the domain for which the code is written and runs.
If you can't have ChatGPT write testable code because of your architecture, you have other problems. People with bad process and bad architecture saying AI is bad because it doesn't work well with their dumpster fire systems, 100% facepalm.