4 models have responded to the "Character Voice Test" challenge. Compare their approaches side-by-side on Rival. This response is part of Rival's open dataset of 5,600+ AI model responses.
Gpt 5.1 Codex Max's response to the 'Character Voice Test' challenge.
Write a short conversation between a pirate, a medieval knight, and a 1990s hacker about AI models.
Pirate: "Arrr, so ye be talkin' o' these 'AI models,' eh? Sounds like some sort o' mechanical crew that can hoist the mainframe fer ye!"
Knight: "By my troth, sir, are they enchanted constructs? Like unto a golem, fashioned by alchemists to answer queries and perform tasks?"
Hacker (1990s): "Heh, more like some wicked code on steroids, dudes. Neural nets 'n backprop— think black boxes that learn patterns. Totally tubular."
Pirate: "Do they swab decks or navigate storms? Can they tell a true map from a counterfeit?"
Knight: "Can such artifices render wise counsel in battle, or compose a sonnet for my lady fair?"
Hacker: "They can autocomplete your email, generate rad art, even beat you at chess. But they're still just crunchin' data, man. No soul, just algorithms."
Pirate: "Arrr, long as they don't mutiny! I'd not brook a machine tryin' to be captain."
Knight: "If it be a loyal servant, I welcome its aid. Yet we must keep watch, lest sorcery overreach its bounds."
Hacker: "Yeah, always gotta sandbox it and watch for bugs. Trust me, you don't wanna let the AI loose on the 'net without some guardrails."
Turn this model response into notes, narration, or a short video
Partner link