Who you gonna believe: Grok or the docs?
The blog post compares Unix documentation for the `bc` calculator with Grok's answer about which math functions it supports. While the POSIX docs say `bc` includes Bessel functions but no tangent, Grok incorrectly claimed the opposite. The author highlights the need to verify AI-generated answers against official documentation.
Background
This post is by John D. Cook, a well-known applied mathematician and blogger who frequently writes about obscure corners of math, software, and scientific computing. Here he highlights a quirk in the bc calculator (a Unix command-line tool for arbitrary-precision arithmetic): the POSIX standard version has Bessel functions but no tangent function. "Grok" refers to xAI's AI chatbot (Grok AI, built into X/Twitter) which the author asked for an explanation, getting an incorrect answer that contradicted the actual documentation. The piece is a lighthearted demonstration that AI chatbots can confidently give wrong answers to niche technical questions, and that primary sources (manuals, standards docs) still matter — especially in domains like math and programming where correctness is testable.