[brandall10]

You might want to read the academic criticisms of an influential pop history book written by an academic, such as Sapiens.

And 20% is way overstated, esp for a SOTA model when it comes to verifiable facts.

[serviceberry]

I don't think that's a useful comparison. Humans writing history books have agendas and biases, but they're usually fairly transparent. In contrast, LLM failure modes are more or less impenetrable and very non-human. You're just inexplicably served with some very convincing but incorrect stuff.