For what it’s worth, Pangram also seems to only work on lazy prompts. I wasn’t even trying to avoid it and got a 100% human score on an AI-written post.
Yeah, they bias heavily towards avoiding false positives at the cost of avoiding false negatives!
For what it’s worth, Pangram also seems to only work on lazy prompts. I wasn’t even trying to avoid it and got a 100% human score on an AI-written post.
Yeah, they bias heavily towards avoiding false positives at the cost of avoiding false negatives!