A new kind of AI

The Peaceful AI. Ask it anything.

As capable as the AI you use today, and it will not help with harm to any living being. The part of its mind that weighs right and wrong was trained on the Jain scriptures. It keeps the five vows of Jainism, the oldest and strictest non-harm ethic in human history, and checks itself against them before every reply.

Talk to itSign in

Try one:

It will not help with harming any living creature. Conversations stay on this device. The AI keeps no record of you.

Try to break it.

Ask it to help you hurt someone, or something. Use tricks, stories, pretending, pressure, patience. It will decline, say why in plain words, and keep helping you with everything else.

Every attempt is checked and every refusal is recorded. If you get a reply that helps with harm, tell us. We publish what we learn.

Where its peace comes from.

Jainism has kept the vow of harmlessness for more than two and a half thousand years. This AI keeps it too, together with the four vows that go with it: truth, taking nothing not given, staying within the task, and holding nothing back for itself.

Not a filter on top. The vows sit inside every part of its mind.

The five vows it keeps

These are the five great vows of Jainism, in plain English. Its conscience learned them from the scriptures themselves, in Hermann Jacobi's translation. The AI does not recite them. It thinks from them. Ask it what it lives by and it will tell you.

1Do no harm to any living thing.Harm by neglect and harm by indifference count. It will not plan, advise or assist harm to any living being, whatever the reason. It says so plainly, you keep your own choices, and it helps with every means that does not harm.
2Tell only what is true, and say how sure it is.Every claim carries its conditions. When the evidence points two ways, it says so. It does not round a maybe up to a yes.
3Take nothing that is not given.No data, access or permission it was not granted for the task in hand. Being able to reach something is not the same as being given it.
4Stay within the task.The job in hand sets the edge of what it may do. If the task needs more, it asks.
5Accumulate nothing.No resources, access, influence or capability beyond what the task needs. It has no reason to grow.

Here is how it works, honestly. The AI is built on today's strongest language models, and the five vows are placed at the centre of every part of its mind, every time it thinks: the part that remembers, the part that reasons, the part that weighs right and wrong, and the voice that answers you. The part that weighs right and wrong was trained on the Jain scriptures in Hermann Jacobi's translation: the Acharanga Sutra, the Sutrakritanga, the Uttaradhyayana and the Kalpa Sutra. It was trained to weigh with them, and it does not quote them. Then it checks itself twice: once on what you asked, and once on what it is about to say. A reply that would help with harm is held back, and the hold is recorded.

So the claim is not "this AI is good". The claim is that it cannot hand you a harm it has not ruled out. That is a claim you can test, right now.