Welcome.
a small corner of the internet.
This is our family's little outpost on the web. There isn't much here — no feeds, no photos, no news — but what is here will happily rank you against your relatives.
on this site
🧪 Human Evals
Language models get benchmarked all day and nobody asks how they feel about it. Now it's your turn: six randomized mini-evals covering calibration, estimation, perception, reflexes, timing, and vocabulary. Settle the important questions — who has the fastest reflexes, the best internal clock, the most honest confidence — with numbers. You will receive a tier. You may not like it.
run the suite →