Follow-ups that find the weak joint

Stop asking whether it is sure

Are you sure? is the most common follow-up and one of the least useful. It is another prompt, and the model has no lookup to consult. Worse, the tuning that makes assistants agreeable means a challenge often produces a retraction whether or not the original was wrong. You can talk a correct model out of a correct answer, which should tell you exactly how much information the retraction carries.

So replace it. The follow-ups below are the ones that actually move you forward, because each asks for something that can be checked outside the conversation or that changes the shape of the answer rather than its confidence.

The five that earn their place

1. What would make this wrong?

What would have to be true for this answer to be incorrect? What is the strongest case against it?

This converts an assertion into a claim with stated conditions. It surfaces the assumptions and it works in every subject. In an essay it gives you your counterargument paragraph; in a lab report it gives you your limitations section.

2. Which part of this are you least confident about?

Not a real confidence report, for reasons already covered. But it reliably points at the parts that are unusual, contested or specific, because those are what surrounding text hedges about. Treat the answer as a list of things to verify, not as a probability.

3. Argue the opposite, as strongly as you can.

The best single move for essay subjects. Ask for the strongest version of the position you disagree with, written by somebody who believes it. Then look at whether your own argument survives it. If the opposing case is easy to write and hard to answer, you have picked the wrong thesis, and it is much better to find that out now.

4. What would a marker in this subject criticise?

Better with the mark scheme pasted in, but useful even without. Framing the model as an examiner rather than a helper changes the output substantially, because it shifts from completion to critique.

5. What am I not asking that I should be?

Works surprisingly well when you are new to a topic and do not know its shape. It surfaces the standard next questions in a field. Verify anything specific that comes back, as always.

The rephrase-and-repeat check

When a specific answer matters, do this:

1. Open a new chat.
2. Ask the same question in different words, without pasting the earlier answer.
3. Compare.

Stable answers across cold rephrasings are more likely to reflect well-represented knowledge. Divergent answers mean you need a real source. It costs one message and it is the closest thing to a free reliability test you have.

The reason it must be a new chat: everything in the current context conditions the next token strongly. A model that has just written an answer will tend to be consistent with it. Consistency inside a conversation measures almost nothing.

Asking it to disagree with itself

A structured variation worth knowing:

Here is an answer to a problem. Act as a sceptical examiner. Find the weakest step. Do not be polite about it.

Paste the previous answer into a fresh conversation rather than continuing the old one. Stripped of the context in which it produced the answer, the model critiques much more freely. This is not magic and it will sometimes invent objections, but the objections are cheap to evaluate and it catches real errors often enough to be worth the message.

The follow-up that is actually about you

The last one is not addressed to the model:

Can I now explain this without the window open?

If yes, the session worked. If no, you have a fluent answer and no new capability, and the right move is to close it and try to reconstruct from memory before reading again. Everything in Module 3 is built on that question.

What to do when it will not budge

Sometimes a model repeats the same wrong thing however you ask. This usually means the error is well-represented in its training data: a common misconception, an outdated standard, a widely-copied wrong answer. That is a signal, not a nuisance. Go and find out why the wrong version is so common; it is often the exact thing your marker is testing whether you know.