Menu

Rules, classic ML or an LLM: a decision ladder
📰

Rules, classic ML or an LLM: a decision ladder

DEV Community: machinelearning·Slava Kotenev·13 days ago
#6rOeayDF
Reading 0:00
15s threshold

"Should we use an LLM for this?" is usually asked as if there were two options: do it by hand, or call a large model. There are at least four, and they differ in cost, speed, and how well you can test them. The simplest way to choose is a ladder: start at the bottom, and climb only when the rung below fails a target you wrote down in advance.

Rung 0: do not automate yet

If the process is rare, unstable or poorly understood, the right move is to document it and measure the manual baseline. Automation of a process nobody can describe produces a fast version of confusion.

Rung 1: rules and lookups

Regexes, validation, tables, thresholds, if-statements.

Pick it when: the decision can be explained in a few lines and the inputs have a stable shape.

You get: exact repeatability, zero per-call cost, a one-line answer to "why did it do that?".

It fails when: the input is free text with many phrasings, or the rules multiply faster than anyone can maintain them.

Rung 2: classic machine learning

TF-IDF plus…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.