Is Your AI Hallucinating? vs Spot the Cue

How our white-box proxy model gives you a per-token hallucination score, including exactly what it costs.

A friendly way to get better at reading social cues, tone, body language, subtext, group dynamics, conflict, pressure and manipulation, plus practice saying it out loud....

About Is Your AI Hallucinating?

How our white-box proxy model gives you a per-token hallucination score, including exactly what it costs. We ship an API that returns a hallucination score for every token that a frontier language model generates. Before describing how it works, here is the most important thing about it: the percentage score that we return is not actually the probability that the token is wrong. The obvious problem is that frontier models do not expose the hidden states that we would need to probe to reveal their thoughts.

About Spot the Cue

A friendly way to get better at reading social cues, tone, body language, subtext, group dynamics, conflict, pressure and manipulation, plus practice saying it out loud. Short interactive scenarios, free to start, no sign-up, no ads. How it works Every rep is three beats, and a reason. Each one is a real moment, your read of it, and a short explanation of why, so the next one lands faster. Often more than one is defensible, the app says so.