Jev for search — a daily feed

Search tools people built with Jev: rerankers, retrieval and plain language queries.

364 builds
Sanyi@imsanyi yesterday
Telegram channel search over community channels
I built something fun using JEV I fetched the Telegram Channels in my community. You type what you are looking for. A topic, a question, or just a vibe. The channels that fit the question rise up in seconds. https://t.co/gjEdDkIsYh
Search 411 views
萩野貴拓@haginota yesterday
RAG and GraphRAG benchmarks with Jev
(続)Jev は、RAGとGraphRAGをどう変えるのか? もうちょっとだけ詳細に調べてまとめてみました。 1. リランカーとしては強い NanoHotpotQA(50問、候補100件)で、関連の薄い文書を92%除去しても正解97件はすべて保持。nDCG@10は0.833から0.975に上がりました。 2. ただし、候補にない文書は救えない 上位8件だけをJevに渡す方式では、45位にあった正解を一度も見られず、答えられませんでした。判定を磨く前に、検索の網羅性を確かめる必要があります。 3. GraphRAGでは「嘘の関係」を切れる 否定文から抽出された関係を判定して除去すると、Precisionは0.279から0.404に。Recallは変わらず、落としたのはノイズだけでした。 4. 名寄せの本当の問題は、候補づくりにあった 判定は完璧でも数値は動きませんでした。型が違うため、比較す
Search 169 views
Dr. Cheems Wang 🏡@AlbertW24045555 yesterday
Jev-LDE benchmark on TREC, DBPedia, Banking77, 44/48 wins
TREC, DBPedia & Banking77 × 4 target LLMs × 1–4 shots: ✅ best or tied-best in 44/48 settings ✅ beats its own Semantic TopK start in 46/48 📈 avg 1-shot acc 88.1 vs 81.4 (CASE) and 81.2 (Semantic TopK) Biggest gains when the demo budget is tightest. Bar chart of average 1-shot accuracy on TREC, DBPedia and Banking77 across 4 target LLMs: Jev-LDE 88.1, CASE 81.4, Semantic TopK 81.2, TopK+ConE 78.3, L
Search 29 views
Jan Kot@_JanKot yesterday
Benchmarked Jev on maze search strategies
6 search strategies competing to find hidden "reward pockets" in a randomly generated maze, with fixed budget of tries. A 60-year-old math (MCTS) crushed everyone. Qwen) did okay. Why poor new JEV kept repeating the same choice and lost even to pure random guessing. @typesafeai https://t.co/LwahJrDKV6
Search 9 views
Mohit Garg@mohitt_garg yesterday
Built Jev for text and images, ranked #1 on JevBench
@SubhadipShips Just completed Jev for both Text and Images. Ranked #1 model on JevBench and #3 on DecisionBench. https://t.co/pSmvDp1X4F
Search 7 views
Ariel@nazrielnr_ yesterday
Web agent benchmark for flight search, 7s and 3 steps
Agen web jev-ultrafast raih 21.276 star dalam 13 hari. Tolok ukur pencarian tiket maskapai tuntas dalam 7 detik dan 3 langkah. Sistem pangkas DOM 3 lapis potong 94 persen konsumsi token ke model. https://t.co/uMGOrmv05q
7 s
Search 5 views
Shanghua Gao@GaoShanghua 2 days ago
RSI-Jev v3.0 RL experiments on the 2B decision model
RSI-Jev v3.0 is out, and this is the first version where RL actually helped. Our AutoScientists loop ran 59 RL experiments on the 2B decision model. Most failed. The pattern was pretty clear: when every example already gives the model the right answer, plain supervised training is very hard to beat. What finally worked was giving RL a signal the labels didn’t contain: whether the model ranked the
60% accurate
Search 909 views
Daniel@daniel_li02 2 days ago
Open source tool to jump between Codex threads with Jev
Do you 🫵 get lost in 10 concurrent Codex threads? Using Jev from @typesafeai, I can jump instantly to an old thread when I forget it. Open source! https://t.co/faoLlPw641 https://t.co/b1HskBiFDg
Search 292 views
AmAzing-@amazing129 2 days ago
Code search benchmark against amp, 3 queries for $1.4
随便测试了一下,对比 amp 的代码搜索子代理,优势是不遗漏,但是搜索结果有点多;而且很贵啊,跑了 3 个问题花了我 1.4 刀,说好的 jev 很便宜呢。。。 https://t.co/c3MSwnwmDg
$1.4
Search 223 views
Ram Sriharsha@halfabrane 2 days ago
Jev reranker and post-filter for search
My X feed has been full of Jev as an embedder, so I got curious. Can good decisions make good coordinates for search? Turns out, they don't. That said, Jev is an outstanding reranker and post-filter. https://t.co/XtuF1FvGxU
Search 77 views
こかげ🐟@K_KOKAGE 2 days ago
Long-term memory retrieval gate cut input tokens to 1/17
Opusに感想文かいてもらいました AI エージェントの長期記憶の検索を判定モデル Jev に任せ、入力トークンを 1/17 に削るまで|こかげ https://t.co/4NgSsKpDZO #zenn
Search 39 views
📺 archie^^🪄@archieauburn 2 days ago
Free App Store app indexer built over one week with Jev
I spent a week building world’s best FREE indexer of successful AppStore apps, with Jev as the driving force behind its speed: https://t.co/fWHIEwuRpz
Search 36 views
Mori Go | Software Engineer@mori_go5 2 days ago
Topic ranking app built with Jev
最近話題のJevを使って、アプリを作ってみました。 好きなテーマで、いろいろランキングしてくれます。 よかったら遊んでみてください🙌 https://t.co/hsq4bCBjL3
Search 21 views
joão coelho@joaoac_dev 2 days ago
Tech digest app classifying article relevance with Jev
https://t.co/i9BX1Bp58b https://t.co/627YaFep3n é bem simples, fiz um app pra analisar algumas fontes que gosto e avaliar quais artigos são realmente relevantes pra mim uso o jev para classificar cada artigo em features/importância e depois para detectar se dois links cobrem a mesma cois
Search 18 views
David Arias, CFA@Davidariasfin 2 days ago
Agentic RAG for financial research, 50/50 and 100x fewer tokens
@_avichawla I've developed a Jev for agentic rag in financial research, results: 50/50 right, 100x fewer tokens, up to 18x cheaper than an agent. Tested on 4 companies and 4 LLMs, including one running locally. https://t.co/L0rXy3WVgX
50% accurate100× cheaper18× cheaper
Search 4 views
Nuri Erginer@nerginer 3 days ago
NewsWithJEV app for news-trade analysis
Çok yeni pişirdim! Haber trade yapanlar gerçekten iyi para kazanabiliyor. Özel yazılım yaptığım bir müşterim “tek bir haberle emekli olacağım” derdi. Şimdi AI haberleri analiz edebilecek kadar hızlı ve akıllı. JEV AI ile yaptığım NewsWithJEV uygulamasını ücretsiz kulüp üyeleriyle paylaşacağım. Skool: https://t.co/AZw925QLgz
Search 8k views
Alvaro@alvarombt 3 days ago
Emoji search with Jev for natural-language queries
He metido Jev en un buscador de emojis para poder escribir "lunes otra vez" en vez de buscar "cara triste" Completamente overkill pero me encanta como funciona https://t.co/mm7EpPOyWZ
Search 2k views
もりっち@企業知財@c27_gzahc 3 days ago
Patent search graphs for keyword relevance and synonym matching
複数キーワードをJevに投げれば、キーワードごとに関連度をグラフで表示できる。 キーワードの類義語もサポート可能。 棒グラフからどんな公報か理解できるため、読むべき公報、スルーできる公報が素早く判断できる。 ←左:複数搬送車無線通信制御の公報 右→:構造物の2次元地図作成システムの公報 https://t.co/VQkwCutir2
Search 285 views
Gillinghammer@gillinghammer 3 days ago
Resume upload to work-experience sizzle reel
https://t.co/PWJnXLHONg 1. upload your resume 2. get an Opus 5.5 sizzle reel of your work experience search profiles powered by Jev free while i can afford it https://t.co/mwkBZMqsbo
Search 228 views
WTome@WarlockTome 3 days ago
Jev reranker lifts answer-at-top from 7/20 to 17/20
4/ 重排,我测的: 20 道有答案的题,排第一的是答案:BM25 7 道,Jev 重排后 17 道。前 3 也是 17 道。 17 就是上限,另 3 道 BM25 前 10 段里根本没有答案。以 0.5 为线过滤,10 段平均只留 2 段给大模型。 注意 BM25 偏弱,换好的向量检索差距会变小。 https://t.co/LAHTaaceWt
Search 38 views
Kashyap Parmar@kashyaprparmar 3 days ago
TypedRank reranks tool calls, tickets, and SQL schemas
Made jev-rankkit for reranking text. Then realized: not everything is text. So I built TypedRank - rank tool calls, tickets, SQL schemas, anything. Runs on Jev + Laya, works standalone too. GitHub: https://t.co/6jWPfO1409 #BuildInPublic #OpenSource #AI
Search 31 views
Ammar Hussain@SyedAmmar69 3 days ago
Page search tool that highlights exact matches in 1.5 seconds
Right now everyone's wiring @typesafeai's Jev into chatbots. I used it to replace Ctrl+F: ask any page in plain words → the exact sentence gets highlighted. 107 passages, exactly 1 match, 1.5 seconds. Every answer quoted from the page. Open source ↓ https://t.co/vLip3lAPXw
Search 29 views
Shivam@Shivamds99 3 days ago
ProbablyThisWay trail search app with Jev routing
Introducing ProbablyThisWay 🏔️ built with @typesafeai 's Jev Model. > you can search the trails in any area on earth > find the best trail according to the Current state: temperature, wind, and every candidate route’s metadata like distance, estimated time, etc using Jev https://t.co/D6a0wh21tL
Search 24 views
Adrian Raudaschl@Raudaschl 3 days ago
200-query NFCorpus reranking test of Jev with RAG Fusion
I expected a better reranker to make RAG-Fusion redundant. So I tested Jev as the reranker on 200 NFCorpus queries, and got the opposite: fusion's lift doubled (+0.050 NDCG@10, against +0.025 with bge-large). https://t.co/QiGPhWZLJj https://t.co/QdfVcDvNbo
Search 17 views
📺 archie^^🪄@archieauburn 3 days ago
Free Jev-powered App Store indexing tool
We’re finally live! Check out this free Jev-powered AppStore indexing tool: https://t.co/wW8vdTrDWC
Search 16 views
Pranab Sarkar | YantrikDB | YantrikOS@developerpranab 3 days ago
Story slicing and prioritization added to the dev loop
Added Jev in the development loop for slicing stories and prioritizing https://t.co/7BFeF0buHu
Search 15 views
knaka Tech-Blog@k_nakashima 3 days ago
Added a Jev ranking article to Zenn
* LLM概要生成なし。Jevランキング記事 追加しました。 https://t.co/LWo6YlpkDx
Search 7 views
mazrean@mazrean22 4 days ago
Go Proposal Weekly Digest search with Jev
Go Proposal Weekly Digest に Jev 使って検索機能つけたので、その解説記事です。 https://t.co/QXUgchOQtR
Search 6k views
Sankalp Sinha (Left $15K+ MRR job to indiehack)@sankalpdomore 4 days ago
Open search history for Jev.Store
Added an open search history to the https://t.co/6rvbCXTB3W site so everyone can see what others are searching with Jev. Pretty fun to see who's searching "what" from "where". https://t.co/QOl9Jqbz2x
Search 1k views
monokern@monokern 4 days ago
3-hour stream VOD cut to 5 minutes for under $1
jev + opus 5.5 on stream clips is insane still can't believe every streamer isn't running this already on a 3-hour vod it turned an evening of scrubbing into about 5 minutes, and the bill came out under a dollar. easily the best use i've found for it so far → jev looks at each frame and just says if something's actually happening → if it's a real moment, the clip gets cut right there → long boring
Search 1k views
もりっち@企業知財@c27_gzahc 4 days ago
Pre-IP analysis app with Jev reclassification, 700 items for $0.0457
Jevを活用した「プレ知財分析アプリ」を作ってみました。 使い方はシンプルに。 1. ざっくりとした母集団データをアップロード 2. 知りたいことを自然言語で入力 (例:走行安定性に関する制御) 3.Jevが情報を整理して再分析 700件のJev再分類で$0.0457 7円程の額でした! ※5$で100回強 本格的な知財分析の前に分析イメージができます。 知らない技術の分析時にFIやキーワードのアタリを付けることにも役立つかもしれませんね。 #知財分析 #Jev #Opus55
$0.0457
Search 549 views
Tân Tân@premiumtantan 4 days ago
Visual search cost model at $0.00023 per search
Visual search with Jev. $0.00023/search -> $0.23 for 1,000 searches -> 10m searches for 1m user ~= $2300 total 🤔
$0.0002
Search 482 views
LoucB@LoicBerthelot 4 days ago
Shopify and Meta ads product research tool built with Jev
We just fixed product research with JEV I was tired of seeing JEV slop so I built something useful Tech part JEV + Shopify UCP + Meta ads lib RT + comment "JEVSLOP" and I'll send it to you rn https://t.co/ke11tLbufi
Search 312 views
Satoshi Nagayasu 🧠🤖@snaga 4 days ago
Weekly arXiv funnel using Jev and social signals
TypeSafe Jevとソーシャルシグナル(Hugging Face)による週次arXiv多段階ファンネル選別の実践とアーキテクチャ https://t.co/jHYuWlrjd6 Jev楽しいねぇ。Jev-as-a-JudgeをarXivの週次キャッチアップのワークフローに組み込んでみた。
Search 115 views
Ethan Abimelech@Ethan_Abimelech 4 days ago
X scanner for AI posts that are taking off
Jev changed how I keep up with AI news. I used it to build a tool that scans every new AI post on X and quickly surfaces the ones taking off across the industry. So you can spot what’s breaking through and join the conversation early. Repo : https://t.co/Lzvgmh7ql2 https://t.co/VXLWcCnTka
Search 93 views
Abhishek Gupta@nitmonk 4 days ago
AI agent for market research with Jev and LangGraph
Must Watch - https://t.co/9lCMFx5I2C Lots of things I talked about and complete end to end build I Built an AI Agent That Does Market Research — Jev + LangGraph + https://t.co/17JP6wMCkc https://t.co/DRxpHgfEz5
Search 52 views
328 more below

Submit a build

Paste the link to your post on X about something you built with Jev. We check the link right away. The next update, within about 4 hours, adds the card if the post shows your build.