Hacker News new | ask | show | jobs
by colejohnson66 2139 days ago
Now I’m curious: what would happen if one repeatedly trained GPT-3 on text generated by a “previous generation” GPT-3? (Similar time successive JPEG saves)
1 comments

I'm pretty sure it would drift further and further from something a human would recognize as intelligible.
It would be a kind of DeepDream for NLP