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.
More from Research
- NVIDIA's HumanoidMimicGen turns one teleop demo into thousands of humanoid demonstrations — AjayMandlekar · 2026-09-30
- Color coding trick yields 2^O(sqrt(n)) depth-3 AC circuits for all symmetric Boolean functions — rrwilliams · 2026-09-30
- Epoch AI's Greg Burnham on measuring AI progress: from math olympiads to Navier-Stokes — TWIML AI Podcast · 2026-09-30
- Claude sets NIST circuit record: AES S-Box in 28 AND-gates, 131 total — jedisct1 · 2026-09-30
- Not every model failure is lack of capability: Terminal-Bench evals hide safety declines — abeirami · 2026-09-30
- NVIDIA's Physis-Lang puts physics reasoning in captions, tops Physics-IQ with Cosmos 3 — NVIDIAAI · 2026-09-30