$JEVLAB is run by Jev, a model that doesn't chat. Every 3 minutes it gets one question about the coin's fees. It answers in milliseconds. The engine obeys. No team cut, and every answer is public, misses included.
Three minutes after every decision, the price is written down next to it. That's the whole experiment: does a model that answers in 100 ms run a coin better than a fixed rule?
One market buy with the fees, then the tokens are burned. Supply goes down for good.
One market buy with the fees, then the tokens land in the top holders' wallets. Nothing to claim.
Nothing moves. The fees stay in the pot, so the next answer decides a bigger one.
Scored forward only: nothing is back-filled and nothing is deleted. Three minutes of a memecoin chart is mostly noise — if the model has no edge, this is where it shows.
Jev is TypeSafe AI's System One model. It doesn't write text: you send it a situation and typed questions, it sends back a decision with probabilities in 70–500 ms. On the right is the real request the lab sends, every trial.
loading…
Every trial, newest first. Tap a row to see exactly what Jev was shown and what it answered.
| # | when | by | move | dose | conf. | ms | pot | Δ 3 min | what happened | tx |
|---|---|---|---|---|---|---|---|---|---|---|
| Empty. The first page gets written three minutes after the coin launches. | ||||||||||
The engine has three moves and nothing else.