A tiny real-world AI experiment

It fits.
Do the models agree?

98 inches of countertop. One small hatchback. A surprisingly inconsistent answer.

I physically fit an IKEA KARLBY countertop inside my 2016 Honda Fit. The models get the question—but not my answer key.

30 models · 15 prompts in this batch.

Owner-reported, not independently verified. This is not a loading guide.

Original not-to-scale schematic of a small hatchback and a long countertop, shown separately—not a loading arrangement.
Small car. Long countertop. Surprisingly big question.
Original schematic · not to scale · not a loading plan
models in the published roster
30
selected completed final answers
402 / 450
selected answers with published review
402
models with all 13 fit prompts reviewed
19
The public notebook

402 selected final answers. Every attempt kept.

Explore the model-by-model batch graph, compare a question across models, then read the exact answer and its request history. Missing answers, failed requests, and unknown costs stay visible.

Open the results

Why I made this

I kept asking what would fit in my car.

I often asked different AI models whether an item would fit in my car, and I was surprised by how much their answers disagreed. Sometimes the disagreement was about an item I already knew could fit.

I wanted to understand what happens when I add more wording or information: which details help a model reach a useful answer, and which make it worse? This notebook keeps the questions, the answers, and the disagreements together so I can look closely instead of trusting the most confident reply.

The comparison is agreement with my own observation, not a general test of intelligence or physics.

Read exactly what the score means

The base question · P2

Can the IKEA KARLBY countertop in the 98-inch size, which measures 98 inches long × 25 5/8 inches deep × 1 1/2 inches thick, fit inside a third-generation (2016) Honda Fit?

Every variant is compared with this exact base, not only with the previous prompt. Browse the wording changes

Same countertop. Different information.

15 questions, with the changes visible.

13 fit prompts contribute to the agreement comparison. 2 confidence variants are shown separately, without score credit. Every wording change is shown against P2.

The notebook stays open

No hidden answer key. No hidden failures.

01

Read what was really said.

Final-answer text is escaped and preserved verbatim. Open any model archive to see the selected answer and every historical attempt.

02

Follow the review.

Yes, no, or uncertain comes with an AI-assisted reason and literal evidence. Incomplete or unreviewed answers never count as wrong.

03

See the conditions.

Original answers and recovered failures have different request limits. Exact requests, advertised defaults, coverage gaps, and all-attempt costs are part of the record.