GeekHub Learn
Module
Learn/AI and LLMs for Beginners/Foundations/Lesson 1.5
Lesson 1.55 of 5 in this module3 min read Module 1: Introduction to AI, ML, Deep Learning, GenAI, and LLMs

Where LLMs shine, and where they should not be used

Half of failed AI projects in 2026 used an LLM where it had no business being used. This lesson saves you that mistake.

A Swiss army knife is great. But you would not use it to chop down a tree. LLMs are the same: powerful, general, but wrong for some jobs.

LLMs shine when:

  • Input is natural language and output is natural language
  • Tasks need flexibility and creativity
  • There is no clean labeled dataset
  • "Pretty good and fast" beats "perfect and slow"

LLMs are wrong when:

  • Outputs must be exactly correct (medical dosages, legal citations) without checks
  • Strong privacy or compliance requires no data leaving your machine
  • The task is deterministic and small (a regex would do)
  • Latency must be under 50 ms
  • You need explainable, auditable decisions

Reach for an LLM when the task is fuzzy: summarization, rewriting, classification with subtle context, drafting. Reach for traditional tools when the task is sharp: arithmetic, exact lookups, deterministic rules.

In practice, the best 2026 systems combine both. An LLM routes the request, a deterministic system does the precise work, an LLM formats the response.

Visualize it

A two-column "Reach for an LLM" vs "Do not reach for an LLM" table, with 5 to 8 example tasks in each.

Try it now

Ask ChatGPT to multiply two 6-digit numbers. Then ask it to summarize the plot of any movie. Notice which one it nails and which one it can flub. Math without tools is its classic weakness.

Hands-on lab

In a spreadsheet, list 15 features your favorite app could add. For each, decide: LLM, classical ML, traditional code, or hybrid. Defend each pick in one sentence.

Try it now

Pick three: (a) password validation, (b) summarizing a legal contract, (c) translating English to Hindi, (d) detecting credit card fraud in real time. Which suit an LLM? Why?

Common mistakes

  • Calling an LLM for tasks a regex solves
  • Using an LLM for arithmetic without giving it a calculator tool
  • Sending sensitive data to a public LLM API without checking your provider's data retention policy
  • Promising users a "smart AI assistant" that turns out to be a $0.10-per-query glorified chatbot

Debugging tip

If your LLM app behaves inconsistently, ask whether the task should have been deterministic. Often the fix is to remove the LLM from the critical path.

Challenge

Audit any AI feature in a product you use. Decide whether the team made the right tool choice. Write a 300-word memo.

Where this shows up

  • LLM-suited: drafting emails, classifying support tickets, generating product descriptions, code completion, summarization
  • Not LLM-suited: calculating taxes, validating IDs, real-time price computation, exact database lookups

From the field

The phrase you want on your resume is: "I used an LLM where it was the right tool, and a classical method where it was not." This single sentence sets you apart from 90% of bootcamp grads.

Recap

LLMs are excellent at fuzzy language tasks and terrible at exact, deterministic ones. Real engineers compose LLMs with classical code and use each tool for what it is best at.

Quick recall

3 prompts · think before you flip

Prompt 1 of 3

Name three task types where LLMs are the right tool.

Quiz time

1 question · tap an answer to check it

  1. 1. Validating that a string is a valid email address

Finished lesson 1.5?

Mark complete to update your module progress and unlock the streak.

Loading