Lesson 1082 of 1455
Why ChatGPT Confidently Suggests Code That Doesn't Run
AI chatbots can't actually run your code — they pattern-match what code usually looks like, which sometimes invents APIs that don't exist.
Builders · AI-Assisted Coding · ~4 min read
The big idea
When ChatGPT or Claude writes code, it's predicting tokens, not executing them. It's seen millions of similar snippets and stitches together what looks right. That means imported functions might not exist and library versions might be wrong — confidently.
Some examples
- Claude suggests `array.sortBy()` in JavaScript — but that method doesn't exist in vanilla JS, only in Lodash.
- ChatGPT writes `from openai import ChatCompletion` using an old API style that broke in v1.0.
- Copilot autocompletes a `df.merge_asof_unique()` pandas call that isn't real.
- Cursor invents a Tailwind class like `bg-gradient-rainbow` that doesn't ship with the framework.
Try it!
Ask an AI for a small script using a library you know well. Read carefully — try to catch one made-up function before you run the code.
Key terms in this lesson
Practice this safely
Try this with a school, hobby, or family example where the stakes are low. Use the AI output as a draft you can question, not as the final answer.
- 1Ask AI to explain hallucination in plain language, then underline anything that sounds uncertain or too broad.
- 2Give it one detail from "Why ChatGPT Confidently Suggests Code That Doesn't Run" and ask for two possible next steps plus one reason each step might be wrong.
- 3Check API invention against a trusted source, teacher, adult, expert, or original document before you use it.
End-of-lesson quiz
Check what stuck
8 questions · Score saves to your progress.
Lesson help
Questions are best handled with a grown-up here.
For this age range, Tendril keeps freeform AI chat paused until parent/guardian consent and child-safe moderation are fully verified. Use the quiz, notes, and related lessons below, or ask a parent, guardian, teacher, or librarian to work through the question with you.
Progress saved locally in this browser. Sign in to sync across devices.
Related lessons
Keep going
Builders · 35 min
When AI Writes Buggy Code — How to Read It Critically
The AI will hand you code that looks right but isn't. Here are the most common bugs and the habits that catch them before they bite.
Builders · 35 min
Tests as Prompts — an Unexpected Superpower
Writing a test first is not just good engineering. It is the clearest possible prompt for an AI. Let's use tests to make AI code reliable.
Builders · 30 min
Python File I/O
Reading and writing files is where real scripts start. Learn the with-statement, path handling, and JSON round-trips.