Post #1987409
2026-05-04 20:52 UTC
LLMs are absolutely stumbling over shit WolframAlpha was able to fifteen years ago for a fraction of the cost
Replies (2)
-
@unlofl@mstdn.social 2026-05-04 23:08
@tholindeth@wizzzard.online And when wolfram alpha made mistakes, they were fun, and still usually technically correct!
-
@tholindeth@wizzzard.online 2026-05-04 20:54
who would win running convex optimization on a few hundred million tokens of scraped text vs a bare minimum amount of programatic effort to analyze common query phrases and connect them to the relevant databases