A browser agent that finds flights in seven seconds. A Claude session cut from a million tokens to 86,000 in one second. A WHERE clause that reads plain English. Vercel's safety reviewer. We are collecting what people built with Jev in its first days, and what they argued about, each in their own words. Nobody in these bylines is on eChai, and every entry links back to where it was posted.
9 entries Clear
Taras builds Flowsery, a session-replay tool. Three million replay events: in 40 seconds Jev watched 3,247 sessions, flagged 132 rage clicks, 116 dead clicks and 95 JavaScript errors, and opened 213 draft pull requests, for $2.17. The numbers are the author's.
Taras
4h
JEV is INSANE.
We gave it 3 million replay events
In 40 seconds, it watched 3,247 sessions, caught 132 rage clicks, 116 dead clicks and 95 JavaScript errors, and opened 213 draft PRs to fix them.
All for just $2.17.
JEV can also flag abandoned forms, rank every issue by severity, count how many sessions each bug hit and write the repro steps for your team.
Coming soon to Flowsery + MCP.
Comment "JEV" for early access.
Jack Cheng's second demo, on the Bluesky public firehose: every English post, first whether it mentions an animal and then whether that is a real animal, a sports team or a figure of speech, close to real time.
Jack Cheng
5h
Another demo to show Jev’s speed. Here it takes all the english language posts from the Bluesky/AT protocol public firehose and 1) figures out which have an animal in them and 2) classifies whether it’s an actual animal, sports team, a figure of speech, etc, pretty much real-time
Ian Nuttall runs keep.md and put Jev to work on it the day it landed on Cloudflare Workers: a search rerank seven times faster than the hybrid it had, and content tagging fifty times faster than GLM 4.7 Flash with no failed calls.
Ian Nuttall
12h
Cloudflare Workers has Jev now so I'm putting it to the test on https://keep.md
- 7x faster search rerank compared to the current hybrid
- 50x faster tagging of content vs GLM 4.7 Flash with no failures
Kush Bhuwalka, of Puffle, with the two-line observation several people then built: retrieve as usual, run Jev over every chunk, delete the ones that are not relevant. Precision in RAG has been the half nobody could afford at retrieval time, since the fix was another model call per chunk.
Kush Bhuwalka
23h
also did anyone realize @typesafeai jev solved precision in RAG?
you can run jev on all the chunks it retrieves and delete the irrelevant ones.
Hassan El Mghari, of Together AI, with the pattern several people arrived at this week: Jev first, and anything it is unsure about goes to a bigger model. Jev classified 100 emails in 1.42 seconds, the 31 under 95% confidence went to Kimi K3, and the pair got 96 of 100 for about seven cents, of which Jev's share was a third of a cent.
Hassan El Mghari
1d
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.
Rory Garton-Smith wrote a master's thesis on classification models and built Easy-Jev so anybody can change the inputs and watch the classifications move in real time. The second half of the post is his own read of where this goes: break a statement into classifications and route each to the right kind of model.
Rory Garton-Smith
1d
I just built Easy-Jev, a Jev demo anyone can try right now!
Change the inputs and watch the classifications change in real time.
I did my master's thesis on classification models so it's fun to see a modernized version of a very useful alg
Typesafe are correct in that LLMs are just one approach to intelligence, and I think as time goes forward we’re going to see a hybrid of dif models splitting up and allocating correct parts of a problem, using less tokens overall and leaning on LLMs for less of the answer.
I’m bullish on what I call 'combination input' approaches: breaking a statement down into a series of classifications and routing each to the right type of model rather than just brute forcing the whole thing with an LLM
cc / @CompleteSkeptic @typesafeai
Link below, please enjoy
Hassan again, on a larger set: 1,018 AI papers summarised by DeepSeek V4 Flash and then filed into 24 topics by Jev for eight cents in total, at 256 ms median per paper. The result is live at 1kpapers.com.
Hassan El Mghari
1d
I used Jev to classify 1,018 AI research papers.
The result: $0.08 total cost and 256ms median end-to-end latency per paper.
The pipeline was:
1. Summarize each paper with DeepSeek V4 Flash
2. Send the title + summary + 24 possible topics to Jev
3. Use Jev to classify each paper
4. Visualize everything on http://1kpapers.com
The summaries cost $3.99 on @togethercompute. The classifications cost $0.08 on @typesafeai.
So for just over $4 of inference, I ended up with a pretty useful way to explore the top AI research papers from the past year.
I think this is where things are heading: different models for different parts of the workflow, instead of using one model for everything.
I’m running evals on the Jev classifications before replacing the current ones, but the site is already live:
Riley Brown, with the smallest possible demo of the pricing: 500 emails classified in seconds for 3.5 cents.
Riley Brown
1d
Yeah Jev by @typesafeai is very cool. It classified 500 emails in seconds. And it costed 3.5 cents.
Ryan Vogel ran it over 1,500 of his own emails the night of the launch. The film is just under two minutes.
Ryan Vogel
2d
this model is actually insane at email classification
i tested it on 1500 of my own emails to see how well it works and I am blown away
