[nicksrose7224]

i think this is a bit pessimistic. You can also use GPT-3 or similar technologies to much more easily train a fine-tuned "real vs fake" review classifier with fewer training examples than was previously necessary.

GPT-3 like all tech is double-edged I think. Has good & bad things about it

[moonchrome]

I doubt this will happen - at some point the generated content should be indistinguishable from human written text - and AI can produce it in droves and learn to exploit existing algorithms.