ChatGPT co-inventor launches Jev, a decision-optimized frontier model claiming 193x speed, 445x cost savings
mazzaTalk · x · 2026-09-19
CompleteSkeptic, who claims to be a ChatGPT co-inventor, spent two years in stealth building a new training method (RLCD) and a new frontier model called Jev from TypeSafe AI, designed to skip chat and output structured decisions with confidence scores.
- Claimed 20-200x faster and 40-400x cheaper (free output tokens); a Chinese-language repost cites 193x faster and 445x cheaper on specific tasks
- Ships with an open-source plugin that compresses context to fight long-task memory loss
- Author calls it the shortest path to an AI-driven economic revolution
Setup: request access, have Codex install the TypeSafe Skill, create an API key, and append "Use the TypeSafe skill" to prompts. Claims are unverified by third parties.
More from coding & agent
- macOS 27 ships with mlx_whisper built in, letting agents transcribe video locally — vista8 · 2026-09-19
- Custom /jev command in OpenCode turns LLM rambling into instant yes/no answers — TheMoonMidas · 2026-09-19
- Dev pipelines Codex output to Muse via Google Drive, calls it insane — RachelVT42 · 2026-09-19
- Building a Self-Improving Content Skill with Claude Code Artifacts and MCP — alexgoughcooper · 2026-09-19
- Jevable site catalogs 342 demos of Typeface's Jev, from $0.0039 flight search to intent-scored spreadsheets — gaganghotra_ · 2026-09-19
- Omar Khattab: AI-era programs still need real languages, declarative specs and DSPy-style modules — lateinteraction · 2026-09-19