Florian Schaffner retweetledi

I think there's maybe really something here, look at this. I got GPT to respond to the prompt from this uml.edu/docs/sample-es…. Then I got a sequence of embeddings for each word in both the human- and GPT- authored essays. You can see how the human one moves around more.
GIF
Find me on bsky @colin-fraser.net@colin_fraser
I think any point in that sequence is probably not that informative but the trajectory might be highly informative. Intuitively, natural writing isn’t done by always choosing the most likely next token whereas robot writing is and you might be able to see that in the trajectory.
English











