Hacker News Reader

What was the issue with GPT-3 & blog posts?

The generated text often seems okay if you're skimming, but if you think about what they're saying, it's rarely meaningful.

I don't think that really came as a surprise to anyone... nobody thought that gpt-3 was going to make sensible long-form narratives.

Yet, people do seem to think that DALL-E 2 is going to be able to make sensible "long-form" illustrations and paintings.