Fixing Failures in Browser-Use Models: Why More Data Isn't Enough (fig.inc) 17 points by jiggle123 19d ago ↗ HN
[–] dippogriff 19d ago ↗ Great work showing on how brittle these GUI benchmarks can be! Love the visuals.I wonder if SFT is the problem here as opposed to the coordinate discretization; what happens with continuous action space?
1 comment
[ 3.0 ms ] story [ 10.6 ms ] threadI wonder if SFT is the problem here as opposed to the coordinate discretization; what happens with continuous action space?