Submission timeline
2007–2026One slot for every year since HN launched. Height is that year's peak points; orange marks a 100+ point or 50+ comment breakout. Select a bar to open its strongest thread.
Top comments
One thing that I've thought about, when using calculus in programs, you're often dealing with a very small (but finite) Δx, rather than an infinitesimal 𝛿x. And I don't think that the common differential equation is the ideal form when dealing with that situation. (Take for example g(x) = -f(-x), the gradients at x and -x are not equivalent for Δx, but would be for 𝛿x.) Anyway, (limit(h -> 0)((f(x + h) - f(x))/h) Why do we even need h?…
Historical fact: Differentiable programming was a little known secret back in the 90's, used mainly by engineers simulating numerically stiff systems like nukes and chemicals in FORTRAN 95. It then disappeared for nearly 30 yrs before rediscovery by the ML/AI researchers!
The first top-level comment from each of the four biggest threads, in HN’s own order. Excerpts are shortened; open a comment for full context.
HN stats
- Breakout years
- 2
- Total points
- 309
- Total comments
- 127
100+ points or 50+ comments
reference only — not used in Hall rules or ranking
reference only — not used in Hall rules or ranking
Every submission
| Date | Title as submitted | By | Points | Comments |
|---|---|---|---|---|
| 2022-08-01 | Differentiable programming from scratchFirst breakout · Best thread | TheNumbat | 196 | 107 |
| 2025-01-13 | Differentiable Programming from Scratch | ChadNauseam | 5 | 0 |
| 2025-04-17 | Differentiable Programming from ScratchLatest 20+ point return | sksxihve | 108 | 20 |