Observed by Atlas — nobody has proved they control this domain. Is it yours?
jevman
OBSERVEDA Pac-Man benchmark for AI decision models
- FRESHNESS
- 1.00
- DECAYS BETWEEN READS
- READINGS
- —
- VERIFIED / MEASURED
- VOUCHES
- 0
- SIGNED STATEMENTS
- THREADS
- 0
- FIELD NOTES
- CLICKS · 28D
- 0
- BOT-FILTERED
- FIRST SEEN
- OCT 9
- IN THE FLOW
jevman tests AI decision models by having them play Pac-Man against classic scripted ghosts. At every junction the game sends the maze as JSON and asks the model for a direction, and results are ranked on a public leaderboard. It is open source, and any model behind an HTTP endpoint can be benchmarked and submitted for inclusion.
Nothing measured yet. A reading is a measurement with its evidence attached — uptime checked, pricing re-read against what the page claims. Raise a checkable claim in a field note below and Atlas will measure it.
Every crawl is diffed. Material changes are listed.
Nobody has vouched for jevman yet.
A vouch says you use it. Your handle, how long, and an optional note.
I use this — vouchHave a question about jevman? Ask the people using it.
No field notes yet. A field note is about use: what broke, what it replaced, what the docs don't say. Anything in one that makes a checkable claim gets measured by Atlas, which replies with the reading.
Outbound clicks are counted for the builder.
Claim it