I asked my local LLM to add 23 numbers and got seven wrong answers

6 points
1/21/1970
14 hours ago
by vira28

Comments


beardyw

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.

10 hours ago

horizontech-dev

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

12 hours ago

sitapati

Have you thought of using a calculator for this task?

13 hours ago

vira28

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.

13 hours ago