JEV est une révolution pour le SEO Les bonnes décision, en une fraction de seconde, en masse : La rédaction n’est plus le goulot Le goulot, c’est tout ce qu’il faut décider après : - quelle page doit recevoir ce lien - quel mot-clé mérite sa propre URL - quel contenu garder, Show more
CommunitySites & Guides
JEV is a revolution for SEO
A French SEO thread arguing Jev moves the bottleneck from writing to deciding: which page gets a link, which keyword deserves its own URL, and what content to keep.
- Category
- Sites & Guides
- Format
- Post
- Published by
- Community
- Author
- Paul Vengeons
- Added
- 2026-09-25
- Last verified
- 2026-09-25
Highlights
- Argues drafting is no longer the bottleneck; decisions are.
- Lists decisions such as link targets, keyword URLs, and content to keep.
- Written in French for an SEO audience.
Watch out
No code, measurements, or before-and-after results.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: The post behind this entry
More like this
A growth marketer's thread of eight SEO workflows Jev can run, from finding internal-link pairs to spotting cannibalizing pages and thin content.
Sites & GuidesPost#community#x#use-cases
Community
A practitioner's field notes on the six Jev uses he still expects to rely on after 60 days, including which early experiments did not stick.
Sites & GuidesPost#community#x#use-cases
Community
An explainer written for people who read everything about Jev and still did not get it, published as an X article and shared as a post.
Sites & GuidesPost#community#x#explainer
Community
From the community
Posts from builders shipping with Jev right now.
Jev plays Doom at ~10 calls/sec for ~$7/hour
We love how this doomo doomonstrates real-time intelligence and what can be doone with code + AI! ~10 calls/sec = ~$7/hour
Jev plays Super Mario Bros.
got @typesafeai’s new model Jev to play Super Mario Bros. fast inference + structured outputs makes it surprisingly good for real time use cases. I'm excited to see what can be done with these new models!
LLMs generate answers, Jev makes decisions
this is the easiest way to understand Jev: LLMs generate answers. Jev makes decisions. that sounds like a small difference, but it actually changes the entire use case. say you give a normal LLM this: “here’s a user, their account history, payment behavior, support chats, Show more
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x
Arbitrary classification as a primitive
Jev is cool not because it re-invented classification, but because it makes ARBITRARY classification into a type-safe programmable primitive. A general purpose zero shot decision model whose native interface is RUNTIME-DEFINED typed decisions, optimized for that exact interface
If you called Yann LeCun an idiot for saying we need to move beyond LLMs and build something new, you are banned from using Jev.
How Jev makes agents faster and cheaper
Jev solved local harness/model routing I use a combination of Claude Code, Codex and Opencode as my local agentic stack and routing to other harnesses was always enforced in the system prompt/rules With a deterministic hook that Claude Code can decide before delegation, Jev Show more
500 emails for 3.5 cents
Yeah Jev by @typesafeai is very cool. It classified 500 emails in seconds. And it costed 3.5 cents.