Researcher: Dropping 'everything must be differentiable' could unlock AI's next leap

PMinervini · x · 2026-09-30

PMinervini argues that giving up on "everything needs to be differentiable" (i.e. backprop-friendly, since argmax is technically differentiable but its gradient is zero almost everywhere or undefined) may unlock the next big steps in AI/ML — much like abandoning that constraint did for global optimization.

Original post →

More from Research

Research channel →