François Fleuret: proper inductive biases cause gradient spikes, so the community avoids them

francoisfleuret · x · 2026-11-19

Former Meta chief AI scientist François Fleuret argues that the proper inductive bias leads to quasi-deterministic loss reduction, which the learning procedure somatizes as enormous gradient norm spikes and training failures. Consequently, he claims, the whole research community avoids the models that are actually proper for intelligence.

Related event: Fleuret: Perfect inductive bias causes sharp loss drops mistaken for spikes(2 posts)→

Original post →

More from Research

Research channel →