Re:Microgpt
by bear3r on Monday March 02, 2026 @12:13AM
(#47214104)
tradeoff worth naming: you avoid the autodiff graph overhead (hence the speedup), but any architecture change means rewriting every gradient by hand. fine for a pedagogical project, but that's exactly why autodiff exists.
[ Parent
| on HN ]
There are no comments on this comment yet.