This is really interesting. We have a company that claims to have an AI that can reason about text and that same company uses an old school hard coded censorship list. When a company doesn't use their own products, it usually tells you the product isn't up to the task.
Your strawmaning MS: pointing out a place where they don’t use their products doesn’t "prove" they don’t use it at all. They very probably use it somewhere else, and arbitrate that this particular functionality would be better served by "old school hard coded list", which also a very valable choice in many casses
I didn't intend to imply that, but I see how my wording was unclear.
I mean that LLMs don't appear to be up for these censorship-like tasks. The evidence being that a highly visible team using LLMs uses much older tech for a highly visible function. It's useful to know the limits of tech, especially novel tech, and this use case appears to be one.