Ask HN: AutoGPT never does something useful. Is it a cool useless idea?
Much hype around language models these days. Has anyone actually accomplished something using AutoGPT, BabyAGI, etc. that they couldn't have done using vanilla GPT-4?
One interesting benefit of projects like AutoGPT is that it will be able to immediately benefit from improved models, assuming access is granted.
Naturally that's trivial to do with a vanilla ChatGPT api. But this is a bit "easier" .