[tovej]

You are interpreting a general statement as a categorical one.

I wasn't really going for an exact, formal statement, but I can give you a formal interpretation of what I said above, if you want to be pedantic.

In general, you can't expect an LLM to produce thorough documentation or robust tests for nontrivial software, because the use of those software (i.e. how their interfaces are expected to behave) contains assumptions from the context in which they are used, and that information will not be encoded in the source.

If the above was somehow ambiguous, this should be clear and uncontroversial.

[mexicocitinluez]

> You are interpreting a general statement as a categorical one.

That is in fact what I did and if you meant otherwise, then yes I agree that currently there are plenty of cases in which those tools fall short and will never replace a human.