[bboy13]

GPT-3 was trained on internet texts, not causal/logical-reasoning only texts. Without context, there is a good chance that samples will match the distribution it was trained on.

This is a non-result, posing as something critical or important. These conclusions are obvious given the model and a basic knowledge of statistics/the transformer architecture.

A bit shameful for someone to ride on the anti-hype wave like this, I'd hope there'd be a more balanced/scientific approach to analyzing legitimate weaknesses rather than setting up strawmen then claiming victory.

[sheeshkebab]

It’s doubtful that training on static representation of dynamic physical systems would make the text model be able to reason about changing physical environments described in words/question. It would likely continue producing word salad output, but prove me wrong.