What it does
Jev plays a coherent, roughly tight-aggressive game, with one clear flaw: it opens less from the button than from the cutoff, where every reference player widens.
Benchmarks & research
Reduces 845 preflop spots to a single fold, call or raise decision, asks Jev five times each, and compares the result with four deterministic reference styles.
Only you can see your notes.
Screenshot unavailable. Open the experiment ↗
Jev plays a coherent, roughly tight-aggressive game, with one clear flaw: it opens less from the button than from the cutoff, where every reference player widens.
You can test how an artificial intelligence model handles game choices by comparing its picks to established strategy charts. Start by listing common card situations with the standard fold, call, or raise answers. A developer can then ask the model for its choices and score them against your baseline rules.