Did you read the paper you are linking to? It records a 0% false positive rate for evaluation of human-authored controls, and fewer than 5% of the hybrid and humanized papers had their AI levels overestimated by pangram. It is not completely clear from the data, but it seems that depending on whether the n=2 overestimates were “100% ai generated” assessments, the study you link says pangram’s 100% AI assessments were right anywhere from 95-100%
loading story #49051699
My citation was correct. To question to ask yourself: For my use case, is it okay that Pangram can't reliably tell the difference between "100% AI generated" and "AI assisted"?
{"deleted":true,"id":49051062,"parent":49050981,"time":1785010264,"type":"comment"}
{"deleted":true,"id":49051170,"parent":49050981,"time":1785010988,"type":"comment"}