Comment by astrange
6 hours ago
The GPT3 base model was pretty funny if you like nonsense. Instruct tuning and RLHF seem to destroy it when they recalibrate everything.
6 hours ago
The GPT3 base model was pretty funny if you like nonsense. Instruct tuning and RLHF seem to destroy it when they recalibrate everything.
No comments yet
Contribute on Hacker News ↗