KICK TECH BROS OUT OF 196
1 point
This may provide interesting avenues to model refinement that aren’t spitting things out and being retrained by “consciousness” telling it yes or no, or feeding it additional info.
1 point
Only if the “direction of truth” exists in the wild with unchecked training data.
That clustering is a representation of the nature of the data fed to the model: all their training data was unambitious true or false… It’s not surprising that it clusters.
1 point