[catgary]

Generally speaking, I try to ensure that the LLM is using core abstractions throughout the codebase in a consistent manner. This makes it easier for me to review any changes it makes.

[raw_anon_1111]

Sort of a devils advocate question. If you write and review your tests and the functional and non functional requirements and the human tests for usability pass, why does the code matter?

Non functional requirements: performance, security, reliability, logging etc?

[catgary]

Because the code is the actual thing, tests can only show that the code fails in certain cases, they don’t actually prove the code is correct.

[raw_anon_1111]

If you are writing the correct tests that mirror the requirements, why wouldn’t passing tests mean the code is correct?

[catgary]

Because it doesn’t? Thats why the field of formal methods exists.

[raw_anon_1111]

Then that sounds like you aren’t writing good tests…