Dev benchmarks Jev on his site: blocks impersonation prompts in 260ms at $0.0002 per call
TejasKumar_ · x · 2026-10-02
Developer Tejas Kumar wired @typesafeai's Jev into his personal website and measured it on four distinct jobs. His site's ask box answers questions in his voice, drawn from his podcast, talks, and book. Previously, questions like "what is your salary at IBM" slipped through to GPT-4o; with Jev in place, that prompt now gets stopped in roughly 260ms at about $0.0002 per call. He documents the full measurement process in a thread.
Related event: Dev Tests Jev Guard: Blocks Impersonation Prompts in 260ms at $0.0002 Each(2 posts)→
More from coding & agent
- Extropic post-trains Qwen3.6-35B-A3B on Prime Intellect, nearly tripling evals in ~100 GRPO steps — MarvinTBaumann · 2026-10-02
- Conductor Mobile launches: run and control a team of cloud coding agents from iPhone — charlieholtz · 2026-10-02
- Open-source Hermes ChatGPT Extension embeds Hermes agents inside Codex — intellectronica · 2026-10-02
- Modal Runtime ships multi-node clusters, VM sandboxes and sticky sessions — graceisford · 2026-10-02
- Building a reliable risk agent without frontier models: $0.02 per sweep, 250x cheaper than an LLM judge — alexcovo_eth · 2026-10-02
- Dev builds Tyton, an MCP that lets AI agents set up Meta Pixel + CAPI for you — Foreign-Chipmunk-295 · 2026-10-02