CommunityJev Media & Talks
Where a decision model sits in the architecture
Aishwarya Srinivasan's 22-minute end-to-end on using System One models inside software, instead of sending every structured check to a text model.
- Format
- Video
- Published by
- Community
- Author
- Aishwarya Srinivasan
- Last verified
- Oct 2026
Highlights
- Listed as a 22-minute end-to-end, longer than the one-minute explainers.
- The description focuses on placement inside software architecture.
- The suggested swap is structured checks that do not need generated text.
Watch out
An architecture overview. It is not a latency or accuracy table.
Questions about this entry
Short answers drawn from the linked project or page.
Just placement. The caveats say it is an architecture overview rather than a latency or accuracy table, so there is nothing measured here to compare your existing text-model check against before you migrate it.
The source does not document a decision test for that. The description only says the suggested swap is structured checks that do not need generated text, and the captured source page is just the title plus YouTube boilerplate.
You cannot tell from the entry copy. The highlights note only that it is a 22-minute end-to-end and that it focuses on placement inside software architecture. No chapter list or transcript is captured to check.
Nothing in this entry says so. The caveats scope it to an architecture overview, and neither the description nor the captured source page discusses agent tooling or replacing an existing model. Its stated swap is narrower.
Aishwarya Srinivasan's 22-minute end-to-end. The entry lists it as longer than the one-minute explainers, and the description focuses on where a decision model sits inside software.
Placement of System One models inside software architecture, instead of sending every structured check to a text model. The entry's caveat is that it is an architecture overview, not a latency or accuracy table.
Structured checks that do not need generated text. The source does not document a test for deciding which of your checks qualify, so the entry gives you the suggested swap without a selection method.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
YouTube: Aishwarya Srinivasan's 22-minute placement of System One inside software architecture.
X: LLMs vs. Jev, clearly explained
X: Jev Clearly Explained
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 NewsMore Jev resources like this
LangChain maps Kahneman's split onto models: System 1 as the fast automatic decision, System 2 as the slow deliberate one, with Jev in the first role.
Jev Media & TalksVideo#community#video#explainer
Community
Dots and Arrows on production checks that need one answer in about 200 milliseconds, and why that is a different job from streaming tokens.
Jev Media & TalksVideo#community#video#explainer
Community
Ben Horowitz and Martin Casado interview Diogo Almeida on why capable models have not automated ordinary software, and what Jev is for instead.
Jev Media & TalksVideo#community#video#explainer
Community
Tim Lin's visual explainer on System 1 versus System 2, the Choice, Score, and Noul primitives, and how JevScout uses Jev inside a coding agent.
Jev Media & TalksVideo#community#video#explainer
Community
Riley Brown on a decision model that cannot write: a model router, Choice, Score, and Noul, then speed, cost, and where to get access.
Jev Media & TalksVideo#community#video#explainer
Community
Telusko Alien Coach on why generating text is overhead for a classifier, with Vercel's reported speedup and Armin Ronacher's objection.
Jev Media & TalksVideo#community#video#explainer
Community
From the Jev community
Posts from builders shipping with Jev right now.