CaveJev: forcing the Jev judgment model to speak word by word like an LLM
_rchaves_ · x · 2026-09-18
Developer Rogerio Chaves introduced CaveJev: he gave Typesafe's judgment model Jev—a model that returns typed verdicts rather than text—a caveman's vocabulary and forced it to choose the next word like an LLM, letting it "talk." His punchline: "why waste time, say lot word when few jev do trick?" Measured results and benchmarks live in his follow-up thread and the jev-experiments repo.
Related event: Dev Forces Judge Model Jev to Talk at 3 tok/s(3 posts)→
More from Fun
- America.gov's AI chatbot refuses a geography riddle — unless you ask about exactly 3 states — conitzer · 2026-11-02
- Letting Claude run wild in an endless loop, showing only what it thinks is cool — rachittshah · 2026-11-02
- Even a skeptic almost fell for an AI fruit cartoon reel — menhguin · 2026-11-02
- Sole Intentions: a film-noir style AI short film starring a sloth at an office desk — heresalexandria · 2026-11-02
- Founder Tries Building a Custom CRM, Ends Up Integrating 3 Existing Tools Instead — menhguin · 2026-11-02
- Designer calls out peer for near-verbatim copy of his Figma-to-Claude workflow thread — hewarsaber · 2026-11-02