Article
CommunityJev Guides & Articles
TWIML #779: Diogo Almeida on Jev and machine-native AI
TWIML episode 779 features TypeSafe co-founder and CEO Diogo Almeida on Jev, the company's model for bringing fast, reliable intelligence directly into software, and why text-generating models are poorly suited to many real-world automation decisions.
- Format
- Article
- Reading time
- 2 min
- Published by
- Community
- Author
- TWIML
- Last verified
- Oct 2026
Highlights
- TypeSafe co-founder and CEO Diogo Almeida joins TWIML episode 779 to discuss Jev and what he calls machine-native intelligence.
- Almeida argues models optimized for generating text are poorly suited to many of the decisions required for real-world automation.
- The episode covers how Jev differs from traditional classifiers and LLM-based approaches, and the role of reinforcement learning from calibrated decisions.
- The summary frames calibration and reliability as central to making AI useful as a software primitive.
- Almeida also discusses why AI systems should become more engineered and how Jev-like models could reshape agents and tool use.
Watch out
Copy reviewed against the published episode page on 2026-10-17. The entry is grounded on the page's episode summary rather than the audio, and the speed, calibration and reliability claims discussed are TypeSafe's own.
Questions about this entry
Short answers drawn from the linked project or page.
Episode 779 of TWIML, The Voice of Machine Learning and AI, features TypeSafe co-founder and CEO Diogo Almeida discussing Jev and the idea of bringing fast, reliable intelligence directly into software.
Diogo Almeida, co-founder and CEO of TypeSafe. The episode page describes him discussing machine-native intelligence and why models optimized for generating text are poorly suited to many automation decisions.
The episode summary says Almeida explains the differences and covers the role of reinforcement learning from calibrated decisions, or RLCD, in how Jev is trained.
They are framed as central to making AI useful as a software primitive, per the episode summary, alongside Almeida's argument for fast, reliable intelligence inside software.
Almeida discusses it and argues that AI systems should become more engineered rather than relying on a single model to do everything, according to the episode summary.
The conversation covers how they could reshape agents, tool use and the architecture of AI-powered software, per the episode page.
It is grounded on the episode page's summary rather than the full audio, and the claims about Jev's speed, calibration and reliability are TypeSafe's and Almeida's, not independent findings.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
Hacker News: Simon Willison's overview of Noul, Choice, and Score, and where a decision model fits.
benwerd53 pointsJev introduces a new shape of LLMRead the thread on Hacker NewsHacker News: swyx posts the Latent Space interview with Diogo Almeida.
swyx4 pointsJev: System One Models for Prod, Not God – With Diogo Almeida, CEO, TypeSafe AIRead the thread on Hacker NewsX: Diogo Almeida in five minutes
X: LLMs vs. Jev, clearly explained
More Jev resources like this
Ian Maurer's ThinkThen analysis argues Jev's faster and cheaper are measurable today while its better is a bet on RLCD: unlike RLHF, which pleases humans, and RLVR, which optimizes benchmarks, Jev is trained to be reliable for programmatic use, in Diogo Almeida's own framing.
Jev Guides & ArticlesArticle#community#press#explainer
Community
On The MAD Podcast, Matt Turck talks with TypeSafe CEO Diogo Almeida about why intelligence per dollar matters more than enterprise adoption, and why RLVR benchmark gains still leave models 95% Einstein, 5% Mr. Bean.
Jev Guides & ArticlesArticle#community#press#podcast
Community
Pillar Security analyzes Jev and System One models: a smart-home demo answered three typed questions in about 200 ms with no language model in the loop, while prompt scanning, output filtering and chain-of-thought monitoring all have nothing to inspect. TypeSafe's docs say state is not treated as hostile by default.
Jev Guides & ArticlesArticle#community#press#security
Community
Rogue Security's post uses Jev and System One models to frame agentic security as a decision problem: the same send_file action should be allowed, blocked or reviewed depending on who requested it and where the data goes, illustrated with policy case files rather than product results.
Jev Guides & ArticlesArticle#community#press#security
Community
A podcast episode on Jev as a decision model rather than a chat model: hosts Luis Calderon and Carina discuss roughly 20x faster Coach testing, why that preliminary figure differs from TypeSafe's vendor benchmarks, and why type safety does not guarantee a correct decision.
Jev Guides & ArticlesArticle#community#press#podcast
Community
A BIG CHANGE analysis of the Diogo Almeida Latent Space interview: Jev's most consequential proposition is the unit of automation, a bounded judgment inside an existing process, and the launch claim that Jev can't hallucinate needs a narrow reading because schema matching does not establish truth.
Jev Guides & ArticlesArticle#community#press#explainer
Community
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.