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.