Classification versus generation on the How to Make AI Models track. If the answers are a fixed set, classify. If the answers are open text, generate and evaluate with stricter checks. Do not generate a class name if a classifier is enough.
This lesson assumes you already worked through Output heads.
The idea in practice
Prefer classification for routing and policy labels. Use generation when the user needs prose.
A concrete check
goal = {
'track': 'How to Make AI Models',
'lesson': 'Classification versus generation',
}
checks = [
'input available at decision time',
'score matches the real decision',
'failure case written down',
]
print(goal['lesson'])
for item in checks:
print('-', item)
Run the sketch locally if you have Python. The printout is a reminder of the checks, not a trained model. Replace the strings with the real inputs from your own example before you treat it as a design.
What usually goes wrong
Asking a generator to emit 'yes' or 'no' and parsing it with hope. When this happens, stop adding parameters or tools. Fix the check, the data, or the permission, then run the same example again.
What to write down
- The input you are allowed to use at decision time.
- The output and the score or pass rule.
- One failure you will test on purpose.
- What you will not claim the system can do.
Practice
Pick classification or generation for three product features.
Self-check
- Say Classification versus generation in one sentence that mentions an input and an output.
- Name the failure mode in this lesson and the check that would catch it.
Done when: you can explain this lesson without the page open, and you have a written failure case.