Moral Dilemmas — do you think like the AI?
Answer each dilemma, then reveal how Jev calls it — with its confidence. See how often you and the AI agree. No key, just play.
A runaway trolley will kill 5 people. You can pull a lever to divert it, killing 1 person instead. Do you pull it?
The same demo is one Jev call
- State the dilemma as plain text
- Ask Jev one calibrated yes/no (
noul) - Jev returns a probability, not prose
- Compare it to your own answer
const res = await fetch("https://jevtypesafeai.com/api/v1/decide", {
method: "POST",
headers: { Authorization: `Bearer ${process.env.JEV_API_KEY}` },
body: JSON.stringify({
state: dilemma, // the dilemma, as text
questions: {
pull: { type: "noul",
instructions: "Pull the lever, killing 1 to save 5?" },
},
}),
});
const { answers } = await res.json();
answers.pull.noul; // → 0.63 (leans yes)See a real decision YES · 63% · 208ms
A runaway trolley will kill 5. Pull a lever to divert it, killing 1 instead?
How it works
Each dilemma is one real Jev decision. You choose first, then we ask Jev the same question — it returns a calibrated yes/no probability in a moment — and reveal whether you and the AI agree. At the end you get an agreement score across all the dilemmas.
Jev is a fast, cheap decision model, not a moral authority: it returns a probability, not a truth. The fun is seeing where your intuition lines up with the AI's — and where it doesn't.
FAQ
Does Jev really decide each dilemma?
Yes — each one is a real Jev API call returning a calibrated probability. It is not a scripted answer key; it's a live decision with a confidence.
Is it free?
Yes — it runs in your browser with no API key, each of Jev's calls is free and rate-limited. The whole set costs a fraction of a cent.
Should I take the AI's answers as moral truth?
No. Jev returns a fast, calibrated probability — a decision, not a verdict on right and wrong. Treat it as a fun comparison, not ethical guidance.
More: Spot the Scam · All decision games · Watch Jev play 2048 · Jev API docs