Play game
$B$ Confident Bro: Discovering Latent Knowledge In Language Models Without Supervision's itch.io pageResults
| Criteria | Rank | Score* | Raw Score |
| ML Safety | #2 | 3.674 | 4.500 |
| Reproducibility | #13 | 2.041 | 2.500 |
| Generality | #14 | 1.633 | 2.000 |
| Mechanistic interpretability | #14 | 1.225 | 1.500 |
| Novelty | #14 | 2.041 | 2.500 |
Ranked from 2 ratings. Score is adjusted from raw score by the median number of ratings per game in the jam.
Judge feedback
Judge feedback is anonymous.
- This project is intriguing and I am looking forward to seeing its potential real-world application. The implementation of confidence modulation is noteworthy as it seems to bridge the gap between machine knowledge and human understanding, an important consideration for machine learning safety. However, I would appreciate more concrete results and data in the report. Overall, I am excited to see the progress and further development of this work.
What are the full names of your participants?
Faz, Hugo, Sam, Bodgan, Elias
What is your team name?
Ox
What is you and your team's career stage?
meh
Does anyone from your team want to work towards publishing this work later?
Yes
Where are you participating from?
Oxford
Leave a comment
Log in with itch.io to leave a comment.
Comments
No one has posted a comment yet