Remix.run Logo
I asked my local LLM to add 23 numbers and got seven wrong answers(viggy28.dev)
6 points by vira28 13 hours ago | 4 comments
beardyw 9 hours ago | parent | next [-]

This kind of thing beats me. Why should a "Large Language Model" be expected to act as a calculator. Clue one is on the name, clue two might be an understanding that it is based on statistics, it is not the deterministic tool you need.

horizontech-dev 10 hours ago | parent | prev | next [-]

Though it’s obvious, nice write up. This is the kinda rabbit hole I enjoy going through and reading.

sitapati 12 hours ago | parent | prev [-]

Have you thought of using a calculator for this task?

vira28 11 hours ago | parent [-]

Did exactly that for the actual filing — Python, mentioned in the post. The 23 numbers were a probe, not the goal: I wanted to understand how it works.