This work was done during one weekend by research workshop participants and does not represent the work of Apart Research.
ApartSprints
Interpretability
Accepted at the 
Interpretability
 research sprint on 
September 7, 2023

Goal Misgeneralization

The main argument put forward in the papers is that we have to be careful about the inner alignment problem. We could reach terrible outcomes scaling this problem if we continue developing more powerful AI’s. Assuming the use of Reinforcement Learning from Human Feedback (RLHF).

By 
João Lucas Duim
🏆 
4th place
3rd place
2nd place
1st place
 by peer review
Thank you! Your submission is under review.
Oops! Something went wrong while submitting the form.

This project is private