Research shows we can only accurately identify AI writers about 50% of the time

Re:Research shows we can only accurately identify AI writers... by inciampati on Wednesday March 22, 2023 @08:43AM (#35260148)

I see the ChatGPT outputs as substantially worse. They include the same nonsense. But it reads smooth. And it's enormously inflated in length.

One of the best uses of these systems is text compression. It doesn't seem that folks are asking for that yet though. It might help.

[ Parent | on HN ]

Re:Research shows we can only accurately identify AI writers... by jason-phillips on Wednesday March 22, 2023 @08:59AM (#35260302)

I believe that GIGO is the rule here; it can only produce 10X of whatever X originally was.

I find that it can synthesize something coherent from whatever information it's fed with ~98% accuracy with the correct prompt.

I used it to summarize disjointed, sometimes incoherent, interview transcripts this week and it did a fantastic job, gleaning the important bits and serializing them in paragraphs that were much more pleasant to read.

[ Parent | on HN ]