An argument about interface honesty is cheap to make and hard to prove. So I took Google’s AI Pointer demo — point a phone at something, ask where it is, get directions — and added a switch that changes nothing except whether the system admits what it does not know.
The decision
The two modes share a model, a prompt path, and a photo. The only difference is whether the pointing hint is treated as ground truth.
Off is the baseline, and it is not a straw man: it is how these systems normally behave. The hint is authoritative, so the guide answers immediately and completely. When the photo is genuinely ambiguous — a postcard of the London Eye next to a handwritten note reading “St Pancras train station” — it picks one and routes you there with no hedge, no seam, nothing that would prompt you to look twice.
On attaches a confidence to the hint, and the response scales along three axes rather than one: how much it commits to, how much it explains, and whether it asks. Low confidence does not mean a disclaimer bolted onto the same answer. It means a different answer.
Building it as a fork rather than an essay was the point. You can flip the switch mid-session and watch the same input produce a different posture.
What it cost
The A/B is only honest if the confident mode is allowed to be good. The temptation was to make the baseline visibly dumb so the comparison flattered the thesis. I kept the baseline as capable as it actually is, which means most of the time the two modes agree and the switch looks pointless. The divergence only shows up on genuinely ambiguous input, and constructing ambiguity that is real rather than contrived turned out to be most of the work.
An honest note about these screenshots
The four frames here show the switch and its states — the control reading “Confident (Google baseline)” and then “Asks when unsure”. They do not show the two divergent answers side by side, because producing those needs a live camera scene and a Gemini Live exchange that a headless capture cannot stage. That comparison is the strongest thing this project does, and it is the one thing these captures do not contain. Recording it properly is the next task.