Hacker News Reader

Agreed that people should pay attention to cherry-picking of model outputs.

For this one in particular, here are a few more results for Battlestar and The Office:

https://twitter.com/Miles_Brundage/status/153247388947686195...

Imagine a crowd sourced metadataset of which model output is "good". What happens when we try to incorporate that knowledge into the pre-existing model? Will it learn to generate more "good"looking output?

Yes. This is already done in research and commercially (https://openai.com/blog/instruction-following/).

Reply on news.ycombinator.com