Indie game storeFree gamesFun gamesHorror games
Game developmentAssetsComics
SalesBundles
Jobs
Tags
A jam submission

Discovering Latent Knowledge in Language Models Without Supervision - extensions and testingView project page

AI interpretability project done for the AI Testing Hackathon
Submitted by Jonathan Claybrough — 14 minutes, 53 seconds before the deadline
Add to collection

Play project

Discovering Latent Knowledge in Language Models Without Supervision - extensions and testing's itch.io page

Results

CriteriaRankScore*Raw Score
Judge's choice#1n/an/a
Novelty#23.3333.333
Safety#23.3333.333
Generality#33.0003.000
Reproducibility#52.6672.667
Benchmark#62.3332.333

Ranked from 4 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 very good in investigating the generality of unsupervised latent knowledge learning. It also seems quite useful as a direct test of how easy it is to extract latent knowledge and at the same time, very general! The Github link leads to a basically empty repository, though. Excited to see this work continued.

Where did you participate?
ENS Ulm

What are the full names of the participants?
Agatha Duzan, Matthieu David, Jonathan Claybrough

What is your team name?
goldtartigradfish

Leave a comment

Log in with itch.io to leave a comment.

Comments

No one has posted a comment yet