Jev AI examples, page 7

@rewind02 describes a production app, built with Opus 5.5 and Jev, that takes a URL, screenshots the site with Gemini Flash, has Jev score it against a fixed list of criteria, and ships a shareable report. They say a scan costs fractions of a cent.

built a full production app with opus 5.5 and jev... fed it a url, it screenshots the site, scores it against a list of known patterns, and ships a shareable re…

@miyagawa gives Jev a transcript and show notes so it can judge at what minute and second each link topic appears. They say a 3-hour episode took 0.5s and $0.003.

jev に文字起こしテキストと show notes 渡して、リンクのトピックが文字起こしの何分何秒にでてくるかを判定。3時間のエピソードで 0.5s, $0.003 でできる

@OpenRouter says Jev, TypeSafe’s System One model, launched on OpenRouter the previous week. They asked the community for innovative uses of fast, cheap decisions and had Jev pick five winners.

1/ Last week, Jev - @typesafeai's System One model, was launched on OpenRouter. The interest was massive. We asked our community to find the most innovative way…

"@motherduck ships prompt_jev() SQL powered by TypeSafe Jev: 100k-row text classification in 40s for $0.50 vs 32 min / $37 for an LLM."

Text classification in MotherDuck just got ~50x faster at ~1% of the cost. prompt_jev() is a SQL function powered by Jev, TypeSafe's new system one model. 100k…

• motherduck.com

@iNoma_main released kojev, a library for calling Jev from Kotlin with answers as user-defined enums instead of strings. Missing choice descriptions are compile errors, and it targets JVM, Android, and iOS. The package is io.github.itisnomatter:kojev:0.1.0.

Jev を Kotlin から型安全に扱うライブラリ「kojev」を公開しました！ ・答えが String ではなく自分で定義した enum で返る ・選択肢の説明は enum 定数に持たせるので、書き忘れはコンパイルエラー JVM / Android / iOS 対応 io.github.itisnomatter:k…

@Yarilo7brigada built a feed filter on Jev that asks, for each post, whether it fits their niche, has real value, what format it is, and whether it makes loud claims without proof. They report 20 of 1,000 posts kept, 97ms each, and 1.2 cents for the morning.

98% of my feed is junk. Now I don’t even see it I built a filter that reads my feed for me. It runs on Jev - a model that doesn’t generate text; it just makes b…

@TheStalwart used Jev and @eltokh7’s JSort to re-score the Fedlock corpus: 4,005 FOMC public speeches and statements since the mid-1990s.

Pretty incredible. Just used Jev + @eltokh7's JSort to re-score the entire Fedlock corpus. 4005 FOMC public speeches and statements since the mid 90s. A glimpse…

Quoted @eltokh7

@codeaholicguy built a session compact for AI DevKit with Jev labeling each message so code keeps only what the next agent needs (1.72M → 5.9K tokens).

I built a session compact for AI DevKit, using Jev to label every message, and code keeps only what the next agent needs. Tested on a real session 1.72M → 5.9K…

@mmmikhaeel built a tool powered by Jev that extracts any product’s features and business logic into a markdown repo. Enter a product URL and copy features, ICP, messaging, pricing strategy, and so on straight into an md file.

I built a tool powered by Jev that extracts any products features and business logic into a markdown repo Enter a product URL and you can copy features, ICP, me…

@kylejeong built JevSearch: a query and selection criteria go to Browserbase search for the top 25 results, then Jev scores them and returns the top 5. They say Jev often picks URLs outside the initial top 5.

I built JevSearch, search the web & validate your results with Jev. Give a query and selection criteria, use @browserbase search to get the t25 results, then Je…

Quoted @kylejeong

@yuhasbeentaken posts that they have now found the best Jev use case. The post text does not say what that use case is.

ok now I find the best Jev use case

@akshay_pachaar links an article titled “Build a Jev Judge.”

Build a Jev Judge — https://x.com/i/article/2101635712298692608

• x.com

@idleshubh built an in-house review console with Jev to qualify 4,000+ internship applications at tryAlanAI by finding evidence of real work at scale.

JEV is INSANE. 4,000+ people applied for internship at @tryAlanAI. So we built an in house review console to find evidence of real work at scale. Every square i…

@alexchristou_ says years of hoarded Twitter bookmarks are light work for Jev to run through.

Years of twitter bookmark hoarding Light work for Jev to run through

@0xRicker describes “Jev Engineering” as turning an agent stack into a control system and moving the expensive model out of every decision loop. They cite tests up to 193x faster and 444x cheaper, and say the model should not decide everything.

Jev Engineering is what turns an agent stack into an actual control system and moves the expensive model out of every decision loop. and up to 193x faster and 4…

@kensuu was building a site that asks only questions Jev is unsure about, and says the main finding was that questions Jev is barely unsure about are hard to create. They report no other result.

Jevが迷う質問だけをするサイトを作っていたんですが、意外とギリギリ迷う質問というのは難しいという知見が得られただけで、他に何の成果も出ませんでした。

@OmiidSayfun built a Chrome extension because they could not find important unread email. Jev finds those messages and labels them by what they are about. The post links the repo at github.com/iamomiid/jev-inbox.

Couldn't find my important unread emails, so I built a Chrome extension. Jev finds them and labels them by what they're about. You can check it out here: https:…

• github.com

@LangChain says they tested Jev against LLM judges on accuracy, repeatability, latency, and cost, to see whether System One models could be a new approach to agent evaluation. They link a write-up.

We tested Jev against LLM judges on accuracy, repeatability, latency, and cost to see whether System One models could offer a new approach to agent evaluation.…

• x.com

@nailthy62 describes a Drape experiment: they talk, Jev reads the transcript plus what they are wearing, picks from the closet, and changes the outfit in real time. They report $0.0011 and about 620ms per decision.

jev is insane 🫣 it makes realtime virtual try-on hauls possible. built this experiment for Drape with @typesafeai > i talk > jev reads transcript + what i'm wea…

@markjaquith says this post is their new shortest explanation of what Jev is.

This is my new shortest “what is Jev” explanation

@akshay_pachaar explains LLMs versus Jev: the difference is not that Jev generates faster, because Jev does not generate text. A traditional LLM produces an answer one token at a time.

LLMs vs. Jev, clearly explained! TL;DR The key difference is not that Jev generates faster. Jev does not generate text at all. A traditional LLM receives contex…

@TheAIInsiderN built a system with Jev and Opus 5.5 that scores an X post before you publish it. Paste a link, press Start, and get a virality score in minutes; they say the production version took 9 minutes to build. Jev analyzes 800 viral posts as a live baseline, groups them by hook type, runs 12 checks, and finds the 5 most similar posts. Opus 5.5 explains why those posts spread. The result is a score out of 100, estimated likes and views, the share of the baseline the post beats, and a comparison with similar winners. They say it works on drafts too, and the post is tagged #JEV.

JEV + OPUS 5.5 IS INSANE. I built an AI system that analyzes an X post before you publish it. Paste any X link. Press Start. Get a virality score in minutes. Th…

@0xCodez quotes TypeSafe founder Diogo Almeida, formerly of OpenAI, saying the next era is not Claude Code or Codex with a human in the loop, and describing Jev as what comes next: about 200x faster, 400x cheaper, and, in his words, zero hallucination.

Jev Founder, Diogo Almeida (ex-OpenAI): "The next era is not the Claude Code or Codex era, they are still part of the assistance era with human in the loop - JE…

@jonymusky made a 4-minute video in Spanish explaining what Jev is, what it does not do, and why it changes where you put a model.

Hice un video de 4 min (en español) explicando qué es Jev, qué no hace, y por qué cambia dónde ponés un modelo.