Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

GPT-3 is useful for a lot of things. It can write essays, it can write technical documentation, it can write speeches, it can write fiction, it can write poetry, it can write jokes, it can write jokes about jokes, it can write jokes about jokes about jokes, it can write jokes about jokes about jokes about jokes, it can write jokes about jokes about jokes about jokes about jokes, it can write jokes about jokes about jokes about jokes about jokes about jokes, it can write jokes about jokes about jokes about jokes about jokes about jokes about jokes.

This answer was written by GPT-J when I gave it the following prompt:

question: I lack imagination. What is GPT-3 (and generative text models in general) useful for, other than toys? It can write essays, can we expect it to replace writers for newspapers and magazines? Can it write coherent technical documentation? Replace speechwriters?

answer:



>it can write technical documentation

For the love of god please NO.


This is hilarious.


At least it didn’t go into an infinite loop. Maybe there’s explicit logic to prevent that.


What are thresholds used in generative text to stop generating characters?


I'm not sure about GPT-3 specifically, but often these models are trained with an explicit "stop token", which the model can output when generating text to indicate that no more text should be produced.

That said, there's no reason it couldn't go into an infinite loop, just that the models are pretty sophisticated and therefore are less likely to do this than earlier generations of models (like predictive text on smart phones in the past)


There's a penalty for generating text it's generated before (two penalties, actually, one for words and one for phrases).


Must be a bit more sophisticated than that, as it forms a complete sentence.


I had no idea that there were so many jokes about Church encoding.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: