News for hackers. Stuff that matters.
Re:Qwen3.7-Max: The Agent Frontier by akoboldfrying on Wednesday May 20, 2026 @11:08PM (#48217368)
The point is that it's not a useful metric on its own. For example, redirecting from /dev/null also achieves a zero hallucination rate.

We want the hallucination rate to decrease while the overall answer rate of queries remains sufficiently high. For more specifics, look into ROC and AUC.

There are no comments on this comment yet.