855 projects, posts and guides about Jev, the System One model from TypeSafe AI. Each entry links to its source and shows the cost and speed its author reported.
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 cheaper (w/ output tokens free)
• Frontier composable intelligence optimized for decisions
AFAICT the shortest path to AI-based economic revolution
Jev dropped the price of SEO/GEO fixes by 90%
Agents that audit and fix a client's SEO/GEO used to cost us ~$250
Here's where the savings come from:
1/ 30x faster reads of Search Console and PostHog/Mixpanel data
2/ 30x faster checks of what ChatGPT searches on Bing
3/ 30x faster modeling of what users ask Gemini and Claude
4/ 30x faster scans of who ChatGPT and Claude cite
5/ 30x faster analysis of the sources behind those citations
6/ 30x faster gap analysis: why they get cited and we don't
7/ 30x faster fixes across 1,000s of pages on large client sites
8/ 30x faster sorting of which page types ChatGPT cites
9/ 20x faster creation of the pages that make ChatGPT pick you
Available in the Ryze AI app and MCP/Claude Connector, link in the 1st comment 👇
Jev just solved doomscrolling.
You pick a niche, Jev reads 3 days of posts and asks 8 questions each.
It runs in ~2s for $0.007 😅
> removes bait and hidden ads
> judges the text and like/reply/repost ratios
Free, no signup, go try it then touch grass ↓🌲
JEV is insanely fast.
We gave it a massive dataset based on thousands of outreach messages and asked:
Which intent signals generated the most booked demos?
40 seconds later, we had the answer.
Cost: less than $0.20.
JEV can also rank leads, measure prospect-message fit, and uncover what actually drives campaign performance.
Coming soon to @GojiberryAI + MCP.
jev is an insanely cool product
Saw a post about jev and decided to check it out
This thing is straight up gold whoever built it is a genius
jev is the future
Scanned over 700 live ads in 40seconds flat, and it cost me just 4 cents.
If you're in marketing, this kind of crazy fast data crunching is hands down the best thing out there.
Doing this through Opus 5 would run around 2 to 4.5 million tokens, set you back $15 to $50, and take anywhere from 10 minutes to an hour. That’s 200 to 500 times more expensive than Jev, and way slower.
A Jev browser agent in pure Go, attached to a real Chrome.
NPNgoc Phan
1
Marcel Pociot 🧪
@marcelpociot
I built a browser extension with Jev @typesafeai that can hide/collapse posts on X based on natural language.
It's so fast that it's not noticeable and insanely cheap...this must be the future of "ad blockers" and content firewalls.
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!
JEV is INSANE.
We gave it 700 high-intent leads and personalised outreach messages.
In 40 seconds, it predicted how each message would perform, assigned a confidence score and detected lead-message mismatches.
All for just $0.09.
JEV can also score leads, analyse buying signals, match each prospect with the best message and identify the campaigns most likely to perform based on data.
Coming soon to @GojiberryAI+ MCP.
Comment “JEV” for early access.
We just ran Jev on our WebMCP benchmark.
The result: basically broke the benchmark.
Jev + Mercury 2.5 (a fast, low-cost LLM) using WebMCP solved 100% of the tasks at roughly 112× lower model cost than GPT-6 Astra using computer use with code execution. Compared to Astra using screenshot-based computer use, the model cost was 245× lower (!).
We also compared Jev operating the browser with and without WebMCP.
We used Browser Use’s open-source Ultrafast, with some improvements to the harness to make it more reliable across the benchmark.
Jev’s browser-control accuracy on its own was not amazing - adding WebMCP nearly doubled the number of solved tasks, from 25/49 to 49/49, while reducing model cost by 18% (more on why below).
The benchmark and methodology are fully open and reproducible.
Full results: https://webmcp.com/benchmark
A few words on how the Jev + WebMCP harness works and why this is exciting:
Jev receives text as input and a set of discrete options it can choose from. With WebMCP, those options are the tools exposed by the website. At each step, Jev sees the task, the available tools and previous results, then picks what to do next.
The limitation is that Jev can’t generate arbitrary text, which you need for tool arguments. For example, it can choose the search_products tool, but it can’t generate the search query itself.
So we split the work: Jev picks the tool and Mercury 2.5 generates the arguments if needed.
This works well because turns out most of the cognitive load in these tasks is around choosing the right action. The argument generation itself is relatively simple, so we can delegate to a small and very fast model. We used Mercury, which outputs 1,000+ tokens/sec and is very cheap.
The result is a pretty simple combination: Jev for tool selection + Mercury for arguments + WebMCP for the interface. It ends up being very reliable, very fast, and very cheap.
A few words about Ultrafast and why do we think it underperforms:
Without WebMCP, Jev chooses from the page’s controls: which button to click, which field to fill, or which option to select.
But choosing a valid button is different from choosing the right next step. The agent still has to navigate menus, understand forms, recover from errors and recognize when the task is actually complete.
Our hypothesis is that WebMCP makes the decision space much simpler. Instead of figuring out a sequence of clicks through a website, Jev chooses explicit actions that directly advance the task.
@typesafeai itself documents weaker accuracy on questions requiring multiple reasoning steps. WebMCP moves much of that complexity into the website’s tools, leaving Jev with clearer decisions and fewer opportunities to go wrong (in a sense WebMCP "compresses" a sequence of clicks into one tool call).
Our modified Ultrafast setup solved 25/49 tasks - that is a result for our particular implementation and benchmark, not a universal limit on Jev or Browser Use. We are open to more harness optimization to get this result to perform better, feel free to directly contribute to the benchmark here: https://github.com/nekuda-ai/WindTunnel
Browser-use ultrafast: https://github.com/browser-use/jev-ultrafast
Just trying out Jev, I made a Chrome extension that:
- Listens to your YouTube audio (optional)
- Detects if it gets to a sponsor segment
- Skips it ➡️➡️➡️
- All in real-time while costing ~$0.005 per video
Prototype project, BYOK, open-source:
github.com/trungdq88/yout…
Just created this with Jev by @typesafeai. A live viral post analyzer. As soon as you stop typing for .5 seconds it analyzes the viral potential.
Going to try and actually make this good, will need to scrape a lot of twitter data...
Notice how it also categorizes the tweet live... I could have it surface similar tweets on the right side for inspiration... idk just experimenting.
found the perfect use case for @typesafeai Jev:
instant compaction
in 2026, why is compaction still a summarization prompt?
Jev can make it instant by scoring every tool call and dropping what’s irrelevant
Jev + Kimi K3 for fraud detection!
TLDR: Jev classified 100 emails in 1.42 seconds, then I routed the uncertain cases to Kimi K3. The full pipeline got 96/100 correct for only ~$0.07.
Video is not sped up, check out the live run!
Here was my process:
I gave Jev 100 emails to classify (a mix of 50 legit & 50 fraudelent emails). It classified all of them in 1.42 seconds.
An underrated feature about Jev is it will give you the confidence score for a classification, so I routed any prediction under 95% confidence to Kimi K3 to be fully sure.
31 emails fell below that threshold. After routing those to Kimi K3, the combined pipeline reached 96% accuracy.
The full run took 16 seconds & ~$0.07 in inference costs:
- $0.068 from Kimi K3 on @togethercompute
- $0.003 (1/3 of a cent) from Jev on @typesafeai.
I think this is a really interesting pattern: use a fast specialized model like Jev for the narrow task, then route the uncertain cases to a larger LLM.
I feel like this kind of approach could be a game changer for use cases like fraud or anything realtime. You can use the speed & low cost of Jev while having a larger LLM as a fallback to ensure high accuracy.
I think I just cooked something 🔥
jev(): a PostgreSQL extension that searches your whole database in natural language. No index, no embeddings, just one function.
WHERE jev(people, 'could work from home')
or
WHERE jev(people, 'name sounds european')
129 rows judged in ~1s for $0.0009. Second run: 6ms from cache.
Okay so Jev can actually do computer use really well
Without any screenshots, or LLMs and no Pixels leave my mac
I dont even read the Dom elements
A local CoreML model segments every button and UI element on screen.
On-device OCR reads the labels. That text is all Jev gets.
It returns a probability across those elements and tells me the best one to click.
Then it clicks, re-runs detection, and decides again. In a loop until the goal is done.
~90ms per decision. Faster than any LLM computer use I've tried.
Blazing fast computer use, without any latency
@typesafeai is building something really interesting
Cloudflare Workers has Jev now so I'm putting it to the test on keep.md
- 7x faster search rerank compared to the current hybrid
- 50x faster tagging of content vs GLM 4.7 Flash with no failures
built `jev-review` @typesafeai
it's an experimental, local-first MCP plugin that gives coding agents a score quality feedback loop across different metrics.
agents call jev while they work, get scored, make improvements, and repeat the loop
try below 👇
got @typesafeai's new model Jev as a chief of staff for bots
Jev reads the task, wakes the right teammates off the bench
and gives each one the right model
It is possible on OpenMausBot as it supports all the LLMs from your existing subscriptions
Jev as a decision engine is great
Acabo de terminar la implementación de @typesafeai + Chromium Headless para que mis agentes puedan navegar por internet a una buena velocidad!
En este ejemplo le pido al agente que entre a la página del término "Café" en Wikipedia y navegue por los hipervínculos hasta terminar en la página "Inteligencia artificial"
Logra completar la prueba en 20 segundos. Creo que pocos humanos podrían hacerlo en ese tiempo.
A browser you control by voice, from Moritz Kremb’s Jev tutorial.
MKMoritz Kremb
404
nader dabit
@dabit3
Also have been playing with @typesafeai Jev, insane!
So many immediate use cases and new apps are possible. What a time to be a builder!
Sharing some experiments here starting with:
Keystroke oracle / predictive launcher:
Your launcher ranks by aliases, fuzzy match, and habit.
Jev reads intent: type "the pdf I just downloaded" and the newest PDF is already the top hit with a full confidence on every keystroke, in ~100 ms
Now using @typesafeai Jev in http://aiseotracker.com, http://linkdr.com, http://genppt.com, etc
AI ends up vibe coding so much AI regex slop if you don't read the code, so I can finally move all this hard-coding to Jev and it's insanely fast!
Also for regular LLM calls, it is around 10x faster, 50% cheaper
Claude me integró Jev con Playwright para buscar usados. Lee unos 26 artículos por minuto y decide qué hacer con cada uno en 406 milisegundos
Descartó los que no encajaban con lo que busco, ofertó por los que sí y hasta les mandó un mensaje a los vendedores cuando faltaba algún dato en la publicación.
Toda la búsqueda salió USD 0,00085. O sea: con un dólar revisás unas 26.000 publicaciones.
Una IA que por fin puede navegar por internet más rápido que nosotros es un game changer
Same directory, different order: the entries added most recently, rather than the curated order the home page opens in. The date on a card is the day it was added here, not the day its author published it — this directory is newer than most of the work in it.
