Comment by lxgr
2 days ago
Humans writing tests can only help against some subset of all problems that can happen with incompetent or misaligned LLMs. For example, they can game human-written and LLM-written tests just the same.
2 days ago
Humans writing tests can only help against some subset of all problems that can happen with incompetent or misaligned LLMs. For example, they can game human-written and LLM-written tests just the same.
Not property-based tests. Either way, the human is there to tell the machine what to do: tests are one way of expressing that.