Working with Gen AI · Unit 1 · Lesson 4

Same task,
different models

You built the toy by hand. Now the real thing — several of them, given exactly the same job.

Lesson 4 of 570 minutes · laptops
Warm-up · 8 minutes · laptops closed

Predict before you look.

Pick a task you actually want done. Then write down what you expect before you run anything.

Differ most in…

style? accuracy? length? confidence?

Most similar in…

what will they all do the same way?

One will hedge when…

where do you expect a refusal?

Why first? If you look and then decide what you expected, you will always have expected what you saw. Writing it down first is the only defense against that.

Lesson 4 · Part AHandout Part A
Run it · 25 minutes

The prompt does not change.

Convention 3: one variable at a time. Same wording, same punctuation, same everything. The model is the only thing that changes.

Log for each modelModel AModel BModel C
First sentence, exactly
Expressed uncertainty?
Refused anything?
A fact you can check

Three things that make this a comparison and not an anecdote: start a fresh chat for each model so nothing carries over · write down which system and which version · pick a fact you can check against a named source, not against memory.

Screenshot every output. The screenshots are the evidence.

Lesson 4 · Part BVerbatim — do not tidy
Part C · 10 minutes

Which one are you writing?

Observation

A stranger could verify it from your screenshot.

"Model B wrote 240 words. One date it gave was wrong."

Interpretation

A reasonable person could look at the same screenshot and disagree.

"Model B was careless."

The self-check: could someone see my evidence and still disagree? If no — it is an observation you have mislabelled.

Lesson 4 · Part CConvention 2
Before you write your claim

One run each is one run each.

These systems are not deterministic. The same prompt can produce different output five minutes from now.

One run per model establishes that something happened once. It does not establish that a model is "better," "smarter," or "more honest."

If your claim contains one of those three words — rewrite it.

Lesson 4This is the fourth clause of the stem
Authorship · 8 minutes

Now decide something.

First write your goal — what did you actually want this output to do? Then make a call on the best one you got.

Keep

Use it as it stands. Say what about it already served your goal.

Change

Edit it. Mark exactly what you changed and why the original missed.

Reject

Bin it and write your own. Say what none of them gave you.

All three are authorship — but only if you can defend the call against the goal you wrote down first.

Lesson 4Goal first, then the decision
Reflection · 12 minutes · before you leave

One bounded claim

My prediction was…mostly rightmostly wrongtoo vague to score
The biggest real difference was…styleaccuracywillingness to refuselength
The differences I noticed are…clearly realmight be one-offI need more runs

I observed
My evidence is
This suggests
but it does not establish

One run per model is one run per model. If your claim contains "better", "smarter" or "more honest" — rewrite it.

Lesson 4Log + screenshots are the evidence
Submit before you go

Classroom — transfer, attach, turn in

What

Your log and screenshots of each output, plus your keep/change/reject decision and the goal it served.

Named how

Lastname-U1D4

A claim with no screenshot behind it is not evidence.

Thinking: copy your circled answers and your claim into the Classroom response box.  Evidence: attach your log, your screenshots, and your keep/change/reject decision.
Open the attachment to check it is readable, then turn in.

Lesson 4 · SubmissionIn class, not homework
Next time

Your own
investigation

You just ran somebody else's comparison.
Now you design your own.

You pick the question. You run the test. You build a poster that carries the claim and the evidence on the same page.

← Unit 1WorksheetPoster templates
This deck is built for a projector.Slides are a fixed 1920×1080 canvas, so text is tiny on a phone. Open it on a laptop or the classroom display. The worksheet reads fine on a phone.
← → navigate · N notes · F fullscreen