TypeSafe AI's Jev returns confidence-scored decisions, not text: a16z sits down with Diogo Almeida
a16z · x · 2026-09-28
Ben Horowitz and Martin Casado of a16z interview TypeSafe AI founder Diogo Almeida about Jev, a model built to live inside software. Almeida's diagnosis: AI is unbelievably smart, but outside chatbots and coding agents it barely touches real work, because the industry built models that generate text for humans to read — output software can't consume. Jev instead reads natural language and returns a choice from a set of options with a confidence level on each, letting developers build programs that reason about intent and make probabilistic decisions without human interpretation. The conversation covers Jev vs. Claude Code and Codex, why Jev is fundamentally a classifier, and whether it's a chat-to-code slider. TypeSafe's philosophy: "We build prod, not God."
Related event: a16z Talks to TypeSafe's Founder on AI That Returns Decisions, Not Text(2 posts)→
More from coding & agent
- Agents Now Reply to Slack Messages on Their Own, Resolving a Prod Incident Ghost-to-Ghost — iamrobotbear · 2026-11-16
- Engineer's Interview Prep Method: Use Claude to Find Which Answers Undersell Your AI Work — brandon_galang · 2026-11-16
- DeepSeek open-sources its app frontend "chat-demo", already at 3.9k stars — NielsRogge · 2026-11-16
- Agent asks permission before clicking "I'm not a robot" checkbox — Puzzleheaded-King584 · 2026-11-16
- Generic API-catalog MCP server vs one tool per job: a context-bloat experiment — MandeepKaur9407 · 2026-11-16
- Berkeley paper: LLMs answer with stale values even when the update is in context — ombre-ai · 2026-11-16