Test an AI claim against a simple baseline
Explain why headline accuracy can conceal a useless classifier.
Start or resume with saved notes →Situation
The Researcher · fictional example
The situation
In 100 fictional messages, 95 are ordinary and 5 need urgent human attention. An AI tool labels every message ordinary and claims 95% accuracy.
Before you continue
What would you predict? Say it aloud or write a line on paper. Then compare your reasoning with the example.
Starting knowledge: Understand a percentage and a correct/incorrect prediction.
Need a hint or a clearer next step?
Work through Test an AI claim against a simple baseline with a focused prompt. Your notes stay private unless you choose to paste an excerpt here.
Use fictional examples. Leave out names, contact details, passwords and private records.
Get an answer here with my own OpenAI API key
Requires an active learning profile. Your provider may charge you; API billing is separate from ChatGPT. EaseBrain has no paid-key fallback.
Key clears after each attempt. EaseBrain saves only a daily request count, not your key, prompt or answer. OpenAI’s data policies apply. Up to 500 output tokens and 20 attempts a day; no automatic retries. These limits do not guarantee a spending ceiling.
Preview notes stay in this page only. Download before leaving.
Keep your work for later
Download a lesson backup, then open the saved workspace and restore it there. Preview work is not stored in this browser after you leave.