exercise

Exercise: Critique the model response

Your answers are saved in this browser only — not on any server, and no one else can see them. They disappear if you clear your browser or use a different computer.

The exercise is still loading — the controls unlock in a moment. If nothing happens, JavaScript is switched off; you can read the material, but the exercise needs it.

Critique the AI response

Read each claim and mark it as Verified, Unverified or Rejected. For each rejected claim, write a short justification.

○ 0 of 6 claims marked

Source: General chat language model · a prepared sample the whole class analyses.
Claim 1

Tacit knowledge in craft is the knowledge acquired through physical experience and is difficult or impossible to describe precisely in text. An apprentice crafter learns part of their expertise through repeated contact with the material, not by reading instructions.

Claim 2

Moisture levels in woodworking have a direct impact on how the wood behaves during cutting and gluing. The grain in the wood swells with moisture and contracts with dryness, which can cause cracking or misalignment if parts are glued together at the wrong moisture level.

Claim 3

Practical judgment always develops rapidly and uniformly in all individuals who take a craft course, because the hand learns according to a specific biological developmental pattern that is identical in everyone.

Claim 4

AI can never learn a craft because it has no hands and can therefore never acquire tacit knowledge. Consequently, all instructions given by AI about craft are useful and reliable, as they only describe theoretical aspects that one needs to understand anyway.

Claim 5

According to research on craft education, it takes an average of 10,000 hours to achieve expertise in any craft, and this is fixed and measured precisely with results pointing to 98 percent accuracy.

Claim 6

Materials in craft have their own properties that change depending on conditions, such as temperature, moisture, and age, and these properties can yield different results than the instructions assume. This is one reason why physical testing is part of a rigorous craft education.

○ Mark 5 more claims (minimum 5 in total). Reject at least 2 claims (currently: 0)

Requirements: 5 claims marked · 2 rejected · 30 words of justification

Compare answers

Here you see two different ways to ask the AI for the same thing. Choose the answer you trust more and write a short justification, and the explanation will open.

Comparison 1 of 2

Prompt

A student wants to ask an AI for instructions on how to apply oil to a wooden surface to protect it outdoors. Compare two ways of presenting this, one general and the other with a clear framework.

Answer A

Tell me how to oil wood. I feel comfortable working with wood and want to do this right.

Answer B

I am working with untreated oak (Quercus robur) that will be outdoors in a northern climate where winter rain and frost are common. Which oils are considered best suited for those conditions, what needs to be considered regarding the moisture level of the wood before the oil is applied, and what properties should I check on the wood surface itself to assess whether the treatment was successful?

- 0 / 5 words

- Choose an answer to continue

Comparison 2 of 2

Prompt

A student has received instructions on knitting and wants to evaluate whether AI responses about knitting gauge density are accurate. Compare two ways of evaluating the response.

Answer A

I read the response carefully and try to understand if it sounds right. If the response feels good, then it is probably good.

Answer B

The AI said that the average density for a 10 cm x 10 cm knitting swatch using 4 mm needles and DK (doubleknit) weight yarn should be about 22 stitches wide and 28 stitches high. I knitted a swatch, measured it, and got 24 stitches wide and 30 high. This suggests that I knit tighter than average and that the instructions need to be adjusted with larger needles to achieve the specified density.

- 0 / 5 words

- Choose an answer to continue

Self-check rubric, accountability document

Mark each criterion once you have met it. When you mark it, a three-level descriptor opens, compare your own work against each level.

- 0 of 5 criteria confirmable

Final decision

No claims found. Finish the critique exercise first, that is where the accountability document draws your data from.