CommunityJev Media & Talks
IBM Technology: a model that does not write
Martin Keen, on IBM Technology, explains Jev as a System One model whose output is a decision rather than generated text.
- Format
- Video
- Published by
- Community
- Author
- IBM Technology
- Last verified
- Oct 2026
Works forJev for Classification
Used inJev for Software & DevTools
Highlights
- IBM Technology's explainer, presented by Martin Keen.
- The title question is what changes when the model does not generate text.
- The description links an IBM page on newer frontier models.
Watch out
Distinct from the IBM Developer clip. Neither is an independent benchmark.
Questions about this entry
Short answers drawn from the linked project or page.
Not independent evidence, and the entry copy does not claim it is. The caveats say neither IBM clip is an independent benchmark, and the description simply restates Jev as a System One model whose output is a decision. The captured source page is only the title and YouTube boilerplate, so there is no transcript to audit.
No. The entry caveats rule out both IBM clips as benchmarks, and the captured source page contains nothing beyond the video title and YouTube boilerplate. No figures are published, so nothing here is measured or vendor-reported that you can verify.
The source does not document that. The description and highlights only frame the output as a decision rather than generated text, and the highlights point at a separate IBM page on newer frontier models instead of covering limits or failure modes.
They are separate videos. The entry copy distinguishes this IBM Technology clip from an IBM Developer clip and says neither is an independent benchmark. The System 1 framing comes from the description, not from anything the captured page documents.
Martin Keen presents it on IBM Technology. The entry distinguishes this from the IBM Developer clip presented by Max Jesch.
What changes when the model does not generate text. The description frames Jev as a System One model whose output is a decision rather than generated text.
An IBM page on newer frontier models. The entry notes that link but records no figures or benchmark from either IBM clip.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
YouTube: Martin Keen on IBM Technology explains a model whose output is a decision, not text.
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
More Jev resources like this
Max Jesch, on IBM Developer, walks Jev as a System One model that returns probabilities for classification instead of generating text.
Jev Media & TalksVideo#community#video#explainer
Community
Fireship on Diogo Almeida's System One launch claims: no chat output, and the headline 200× speed and 400× cost multiples.
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
plain. on Jev as typed answers over state, the September 2026 launch, DCVC seed funding, and Diogo Almeida's InstructGPT background.
Jev Media & TalksVideo#community#video#explainer
Community
VikStack lists ten concepts for Jev: non-autoregressive parallel sampling, 70–500 ms claims, and boolean, enum, and rubric answer shapes.
Jev Media & TalksVideo#community#video#explainer
Community
Innovations for Education explains Jev for no-code and vibe coders when if-then rules need judgment calls like spam or toxicity without burning tokens.
Jev Media & TalksVideo#community#video#explainer
Community
From the Jev community
Posts from builders shipping with Jev right now.