No significant takeaways yet (~1/5th of the way through on some protected classes). I think the one notable thing is that they have to try really hard to tell the AI that woke racism is different from non-woke racism, which is funny
— Brian Chau (@psychosort) December 16, 2022
ML engineer analyzes what ChatGPT marks as hate speech: "I think the one notable thing is that they have to try really hard to tell the AI that woke racism is different from non-woke racism, which is funny"
https://x.com/psychosort/status/1603593272911269888
- 19
- 112
Now playing: Donkey Kong December National Anthem.mp3
Jump in the discussion.
No email address required.
this guy passes better than most trains
Jump in the discussion.
No email address required.
More options
Context