Overview & result
In an a16z interview, TypeSafe AI’s Diogo Almeida joins Ben Horowitz and Martin Casado to discuss Jev, automation and reliability. The central idea is to give software typed choices with confidence signals so code can handle intent and uncertainty. This is a product and architecture discussion, not a runnable project.
From the original post
TypeSafe AI's Diogo Almeida with a16z's Ben Horowitz and Martin Casado on Jev, the model built to live inside software:
Diogo's elevator pitch for Jev is a simple question - where is all the automation?
AI is unbelievably smart, but outside of chatbots and coding agents, it hardly touches any real work. His diagnosis is the industry built models that generate text for humans to read, and software can't consume that output.
Jev reads natural language and returns a choice from a set of options with a confidence level assigned to each, so developers can build programs that reason about intent and make probabilistic decisions rather than relying on human interpretation.
TypeSafe's philosophy is "We build prod, not God."
0:50 "Where the f**k is all the automation?"
2:50 Jev vs. Claude Code and Codex
6:55 Jev is a classifier and classifiers are sick
7:40 Chat vs. code: is Jev a slider?
9:00 Diogo: From mathlete to Kaggle to OpenAI
12:20 "We build prod, not God"
15:55 Reliability over demos
16:55 2021 thoughts: RLHF is AGI?
20:45 Optimizing for the wrong use case
21:50 Is the real world too messy to automate?
25:00 Nobody expected the Jev launch
26:35 Three kinds of reliability
28:05 Good at syntax, bad at architecture
30:00 The inverse SaaSpocalypse
33:40 Why coding agents automate so little
36:05 Probabilistic programming returns
38:45 Jev as the UDP-to-TCP layer for AI
40:20 The 5 stages of grief for embedding AI
41:30 Utopia: AI that actually does what you mean
YouTube: https://youtu.be/Ut3LOjKNJaE
@CompleteSkeptic @typesafeai @bhorowitz @martin_casado
How Jev fits in the loop
- The interview contrasts human-readable generated text with choices that application code can consume.
- Jev is presented as a classifier that reads natural language and returns choices over developer-provided options, with confidence signals.
- The discussion covers reliability, software architecture and probabilistic programming. No repository or reproducible application accompanies this post.
How to reproduce
- Watch the original interview or the YouTube version linked by a16z.
- Use the author-provided timestamps: 6:55 for classification, 15:55 for reliability and 36:05 for probabilistic programming.
- Use TypeSafe’s official API documentation for implementation; the interview is context rather than a setup guide.
Why this build matters
Helps developers decide which parts of an application need bounded decisions and which still need generation.
Limitations
- Interview statements express the speakers’ views and product claims.
- No independent benchmark or runnable implementation is provided by this post.
- Confidence must be evaluated on the application’s own data before it controls consequential actions.