Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Another experiment with using Jev on two ends of an email classification system (a Jev sandwich?) to figure out what’s worth my attention based on how well I slept and my current vibes

Jack Cheng

12,033 subscribers

43,088 Aufrufe • vor 1 Monat •via X (Twitter)

Kunst Bildung Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

13 Kommentare

Profilbild von Jack Cheng

Jack Chengvor 1 Monat

This was partly inspired by @danshipper’s thought experiment on “urgency” at the top his piece on seeing like a language model. Worth a read!

Profilbild von ˗` Ronnie Higgins ˊ˗

˗` Ronnie Higgins ˊ˗vor 1 Monat

I was like “cool, cool” might try this THEN you demoed the way your health data gets used and now I’m ready to buy every biometric device to reach my potential.

Profilbild von AI News Daily

AI News Dailyvor 1 Monat

A classifier that adjusts to your sleep and vibes is either the future of inbox triage or a very polite way to let fatigue run the company. How are you evaluating false negatives?

Profilbild von Steve (Builder.io)

Steve (Builder.io)vor 1 Monat

great use case, great video Jack!

Profilbild von Jack Cheng

Jack Chengvor 1 Monat

Thanks Steve :)

Profilbild von M. Adel Alhashemi

M. Adel Alhashemivor 1 Monat

Very unique use case!!! Loved it. Especially the part where Opus generated a new set of evaluation questions against the data set based on user intent. I wonder if you have prompted it to consider the questions to be of system 1 type?

Profilbild von Jack Cheng

Jack Chengvor 1 Monat

More or less! I’ve found it helps to have typesafe’s official skill installed to help since LLMs don’t seem to have decision model best practices as part of their training data. In this case I also ran some evals to help me tune the prompt; the current one asks the reasoning model to write concrete situations for jev to evaluate instead of broad topics

Profilbild von Sofiia Matsiutsia

Sofiia Matsiutsiavor 1 Monat

Have you faced the issue that the model assigned different weights to parameters after asking the same custom question formulated differently? Ex “I need to focus on reading” vs “today I want to prioritize some reading only”. If yes, how do you handle this?

Profilbild von Jack Cheng

Jack Chengvor 1 Monat

Ah good question! I disabled caching for the purposes of the demo to show how long it actually took, but what you could do is cache the answers to the custom questions, the have jev look at whether or not the question has been answered before. Useful especially for frequent context notes like “I have 30 minutes free and want to jam on some email”

Profilbild von Sofiia Matsiutsia

Sofiia Matsiutsiavor 1 Monat

oh this makes sense! and later if you repeat the same question but in different words the system could make a shortcut for you Thanks for the explanation!

Profilbild von Samuel Snopko

Samuel Snopkovor 1 Monat

Are we watching the end of spam and email marketing in real time?

Profilbild von Jack Cheng

Jack Chengvor 1 Monat

I don’t think those will end anytime soon but imagine owning your personal algorithm instead of leaving it up to the platforms to decide for you

Profilbild von Yogi

Yogivor 1 Monat

The Jev sandwich is a nice pattern. Using a second pass to challenge the first one feels useful, but I'm curious about drift: does that second pass need retuning more often as user state changes, even if the inbox distribution stays fairly stable?

Ähnliche Videos

Choosing hotels based on reviews, using Jev to classify thousands of reviews quickly. This is only possible thanks to Jev.

Choosing hotels based on reviews, using Jev to classify thousands of reviews quickly. This is only possible thanks to Jev.

Santiago

16,364 Aufrufe • vor 29 Tagen

I updated all my workflows to use Jev. They are now faster, cheaper, and give me a ton more options because I can do things based on each prediction's confidence score. I recorded a video showing you how to start building automations with Jev.

I updated all my workflows to use Jev. They are now faster, cheaper, and give me a ton more options because I can do things based on each prediction's confidence score. I recorded a video showing you how to start building automations with Jev.

Santiago

18,086 Aufrufe • vor 1 Monat

Jev is incredibly good! If you haven't heard, Jev is a new "System One" model optimized for decision-making. For example, you can give it a set of possible choices, and Jev will classify the input text based on those choices, including a confidence score for each. Best of all: Jev is really fast and cheap, so you can use it in all sorts of applications. The first thing I built with it is a classifier to pick the hotels I want to visit. I use Apify to collect thousands of reviews, then classify them with Jev based on specific criteria I care about. You just couldn't do this reliably, but now you can. Link to the repository:

Jev is incredibly good! If you haven't heard, Jev is a new "System One" model optimized for decision-making. For example, you can give it a set of possible choices, and Jev will classify the input text based on those choices, including a confidence score for each. Best of all: Jev is really fast and cheap, so you can use it in all sorts of applications. The first thing I built with it is a classifier to pick the hotels I want to visit. I use Apify to collect thousands of reviews, then classify them with Jev based on specific criteria I care about. You just couldn't do this reliably, but now you can. Link to the repository:

Santiago

17,898 Aufrufe • vor 1 Monat

I was also looking into how we can integrate Jev into a real hardware and I built a custom firmware for my keyboard that predicts and highljghts the next key using Jev. Mostly real time. This is not a simple dummy 2kb model that lives in the board. In my project Jev gets context of the current active app on a screen so it can suggest actual vim commands completion! For real. And a real word endings or even phrases. lmao this experiments are getting out of hand this quite cool

I was also looking into how we can integrate Jev into a real hardware and I built a custom firmware for my keyboard that predicts and highljghts the next key using Jev. Mostly real time. This is not a simple dummy 2kb model that lives in the board. In my project Jev gets context of the current active app on a screen so it can suggest actual vim commands completion! For real. And a real word endings or even phrases. lmao this experiments are getting out of hand this quite cool

Dmitriy Kovalenko

56,086 Aufrufe • vor 1 Monat

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

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

vogel

450,441 Aufrufe • vor 2 Monaten

this is absolute f*cking treasure 4 GitHub business repos using Jev to save you time on sales, support and paperwork: want incoming leads sorted before sales opens the queue? -> jev-playground: experiments in lead routing, deal risk, reply triage and duplicate accounts want support tickets sent to the right team? -> jev-demo-router: Jev selects the department, judges urgency and scores customer frustration. low-confidence routing goes to a human want financial PDFs classified without opening every file? -> jev-doc-classification: invoices, receipts, bank statements and more, with probabilities for each document type want to experiment with a bookkeeping agent? -> jev-clerk: a desktop bookkeeping experiment where Jev decides the steps and a separate model updates its playbook the pattern: > give Jev the context. > define the possible decisions. > let code handle the action. > leads. tickets. documents. bookkeeping. > these are demos and experiments, not a finished > company on autopilot. API costs still apply. pick one repetitive queue. replay old cases. measure the mistakes before turning on automation. save this.

this is absolute f*cking treasure 4 GitHub business repos using Jev to save you time on sales, support and paperwork: want incoming leads sorted before sales opens the queue? -> jev-playground: experiments in lead routing, deal risk, reply triage and duplicate accounts want support tickets sent to the right team? -> jev-demo-router: Jev selects the department, judges urgency and scores customer frustration. low-confidence routing goes to a human want financial PDFs classified without opening every file? -> jev-doc-classification: invoices, receipts, bank statements and more, with probabilities for each document type want to experiment with a bookkeeping agent? -> jev-clerk: a desktop bookkeeping experiment where Jev decides the steps and a separate model updates its playbook the pattern: > give Jev the context. > define the possible decisions. > let code handle the action. > leads. tickets. documents. bookkeeping. > these are demos and experiments, not a finished > company on autopilot. API costs still apply. pick one repetitive queue. replay old cases. measure the mistakes before turning on automation. save this.

kiosa

23,740 Aufrufe • vor 1 Monat

How does Jev work? Jev takes two things: your input and an output schema. The schema gives the structure of the answer you want. I send an email. My schema asks for two fields: is spam, and a category from marketing, finance, or spam. Jev returns: - is spam: 0.90 - category: spam That is a 90% chance of spam. Jev selects the category only from the list I give it. It writes no sentences. The 0.90 is a number object, so my code can use it immediately without extra processing. Jev shows no reasoning. You get the answer and nothing more, so some people do not trust it. Use Jev for choices your code must make fast and at low cost: spam or normal, buy or no buy, reply or escalate.

How does Jev work? Jev takes two things: your input and an output schema. The schema gives the structure of the answer you want. I send an email. My schema asks for two fields: is spam, and a category from marketing, finance, or spam. Jev returns: - is spam: 0.90 - category: spam That is a 90% chance of spam. Jev selects the category only from the list I give it. It writes no sentences. The 0.90 is a number object, so my code can use it immediately without extra processing. Jev shows no reasoning. You get the answer and nothing more, so some people do not trust it. Use Jev for choices your code must make fast and at low cost: spam or normal, buy or no buy, reply or escalate.

The Startup Ideas Podcast (SIP) 🧃

12,032 Aufrufe • vor 1 Monat

I built a chat bot with jev, no LLM at all! Responses are instant, no hallucinations. I hooked it up to web search, wikipedia, weather, todoist and home assistant. Jev decides what tool to call and what args to use based on the prompt. Instant answers cite sources as well!

I built a chat bot with jev, no LLM at all! Responses are instant, no hallucinations. I hooked it up to web search, wikipedia, weather, todoist and home assistant. Jev decides what tool to call and what args to use based on the prompt. Instant answers cite sources as well!

CJ (Coding Garden)

116,124 Aufrufe • vor 1 Monat

Here's an example of stacking jev on jev inspired by Lily. Jev divides and conquers an image to find a bunch of bounding boxes. For straightforward detection it's worse/slower than SAM3 but for something intelligent - like finding all sheep who might "yee haw" - it does well.

Here's an example of stacking jev on jev inspired by Lily. Jev divides and conquers an image to find a bunch of bounding boxes. For straightforward detection it's worse/slower than SAM3 but for something intelligent - like finding all sheep who might "yee haw" - it does well.

Nathan LeClaire

19,589 Aufrufe • vor 27 Tagen

We turned Jev into a general browser skill for agents: jev-browser. Give it a website and a task. The browser opens automatically, and Jev decides every click based on what's on the screen. Here's a demo:

We turned Jev into a general browser skill for agents: jev-browser. Give it a website and a task. The browser opens automatically, and Jev decides every click based on what's on the screen. Here's a demo:

AI Builder Club

34,077 Aufrufe • vor 1 Monat

jev has made the impossible POSSIBLE. so this morning my real estate buddy asked me how to break out on instagram. I could: - ask her to scroll. - find her favorite creators - map out each hook - figure out what makes them work. - rework it in her voice - rinse & repeat every single week. Or i could have jev go through a library of 12 million shorts and do it for her.

jev has made the impossible POSSIBLE. so this morning my real estate buddy asked me how to break out on instagram. I could: - ask her to scroll. - find her favorite creators - map out each hook - figure out what makes them work. - rework it in her voice - rinse & repeat every single week. Or i could have jev go through a library of 12 million shorts and do it for her.

Matthew Berman

94,093 Aufrufe • vor 1 Monat

TyperSafe Founder, Diogo Almeida just gave the best 2-hour breakdown on how to actually master Jev, from 0% to 100%: • 10% → 21:43 - building an eval for your own workflow with JEV • 30% → 55:49 - choice, score, noul - new types of code mapping with JEV • 55% → 1:12:36 - cascade: confident answers ship, uncertain ones go to a bigger model • 80% → 1:37:12 - JEV use cases: dark data, real-time calls, verifying every LLM in your stack • 100% → 2:11:50 - building coding agents with JEV this is worth more than another $500 course on building agents with Claude watch it today - then read the full Jev playbook below

TyperSafe Founder, Diogo Almeida just gave the best 2-hour breakdown on how to actually master Jev, from 0% to 100%: • 10% → 21:43 - building an eval for your own workflow with JEV • 30% → 55:49 - choice, score, noul - new types of code mapping with JEV • 55% → 1:12:36 - cascade: confident answers ship, uncertain ones go to a bigger model • 80% → 1:37:12 - JEV use cases: dark data, real-time calls, verifying every LLM in your stack • 100% → 2:11:50 - building coding agents with JEV this is worth more than another $500 course on building agents with Claude watch it today - then read the full Jev playbook below

Codez

78,034 Aufrufe • vor 1 Monat

i built a codebase classifier with Jev and this might be the solution to overengineered code that agents create what should I test Jev on next?

i built a codebase classifier with Jev and this might be the solution to overengineered code that agents create what should I test Jev on next?

vogel

99,501 Aufrufe • vor 2 Monaten

I trust Jev with my life

I trust Jev with my life

Alex

1,061,937 Aufrufe • vor 1 Monat

Next week is JEV WEEK on the How I AI podcast - a double header of episodes with yours truly and John Lindquist about what Jev is, why we love it, and what we're each using it for. If you like nools, you'll love these episodes. Drops starting Monday on YT:

Next week is JEV WEEK on the How I AI podcast - a double header of episodes with yours truly and John Lindquist about what Jev is, why we love it, and what we're each using it for. If you like nools, you'll love these episodes. Drops starting Monday on YT:

claire vo 🖤

25,956 Aufrufe • vor 1 Monat

I've built an open-source workflow builder for Jev! Experiment using a UI—classify inputs using choices, scores, booleans; wire results into other prompts; and return a set of custom outputs. Below I've set up a support system that can help with various queries. Features ↓

I've built an open-source workflow builder for Jev! Experiment using a UI—classify inputs using choices, scores, booleans; wire results into other prompts; and return a set of custom outputs. Below I've set up a support system that can help with various queries. Features ↓

Chris Nicholas

38,613 Aufrufe • vor 1 Monat

a Stanford professor used JEV to build a data science system that analyzes 40.000.000.000 data points every 15 min his system can process massive datasets and automatically decide which results deserve deeper analysis. the professor spent more than a year developing the system with his research team. the first version relied heavily on LLMs to interpret every result. it worked, but analyzing millions of records created unnecessary latency and huge inference costs. then they redesigned the decision layer around Jev. instead of generating explanations for every data point, Jev evaluates the results and decides what the system should investigate next. I found a breakdown of the pipeline they used and the way Jev filters the data is surprisingly clever. I’ll show you how it works next so stay tuned if you want to see what Jev Engineering looks like inside a real data science system. would you let an AI decide which patterns in your data are worth investigating?

a Stanford professor used JEV to build a data science system that analyzes 40.000.000.000 data points every 15 min his system can process massive datasets and automatically decide which results deserve deeper analysis. the professor spent more than a year developing the system with his research team. the first version relied heavily on LLMs to interpret every result. it worked, but analyzing millions of records created unnecessary latency and huge inference costs. then they redesigned the decision layer around Jev. instead of generating explanations for every data point, Jev evaluates the results and decides what the system should investigate next. I found a breakdown of the pipeline they used and the way Jev filters the data is surprisingly clever. I’ll show you how it works next so stay tuned if you want to see what Jev Engineering looks like inside a real data science system. would you let an AI decide which patterns in your data are worth investigating?

deezzex

175,697 Aufrufe • vor 1 Monat

Jev is cool, but like any foundation model it needs to be calibrated to your decision criteria. We launched jev-align: an open-source CLI to quickly teach Jev what good and bad looks like using GEPA. Try it out!

Jev is cool, but like any foundation model it needs to be calibrated to your decision criteria. We launched jev-align: an open-source CLI to quickly teach Jev what good and bad looks like using GEPA. Try it out!

Seth Kimmel

129,932 Aufrufe • vor 1 Monat

I GAVE JEV $500 AND LET IT TRADE ON ITS OWN Built JEV to find trades and execute them without me sitting there watching it. → Scans live markets → Tracks sentiment → Filters bad setups → Trades when it finds something worth taking The run started with $500. Eventually it crossed $13K. By the time I recorded this: $13,213 → $13,710 → $14,202 Same system. Same account. I just kept it running. $500 to $14,202. How far can JEV take it?

I GAVE JEV $500 AND LET IT TRADE ON ITS OWN Built JEV to find trades and execute them without me sitting there watching it. → Scans live markets → Tracks sentiment → Filters bad setups → Trades when it finds something worth taking The run started with $500. Eventually it crossed $13K. By the time I recorded this: $13,213 → $13,710 → $14,202 Same system. Same account. I just kept it running. $500 to $14,202. How far can JEV take it?

winkle.

16,013 Aufrufe • vor 1 Monat

Jev has been blowing up lately. If you've got the Jev API but don't know how to play around with it yet, you can just copy this checklist. 1. jev-ultrafast A high-speed browser Agent built with Browser Use. Jev only judges "what to do, which element to click" at each step, and only calls the small model when typing is needed. Searching for a flight on Google Flights takes about 7 seconds. 2. fast-jev-compaction Context compression for Claude Code. Before each tool call, have Jev judge if there's anything still useful; delete the useless stuff, and keep the original text without rewriting it. 3. json-render Vercel Labs' generative UI framework. In experiments, Jev doesn't write JSON token by token; it just handles selecting components, properties, and layouts. 4. typesafe-mcp Best for people who just got the API. Plug Jev into Claude Code, Claude Desktop, Codex, and Pi, and do Choice / Score / Noul anytime. 5. jev-mcp Ready-made Agent judgment toolkit: fact-checking, content screening, semantic ranking, classification, and information extraction. 6. SemDecide Turn Jev into a command-line tool. Directly classify, score, and filter in the Shell—great for hooking up to crawlers, CI, and data pipelines. 7. jev-codex-router First have Jev judge how hard this round of programming tasks is, then decide the model tier, reasoning depth, and speed mode. 8. Winnow Context garbage collection for Claude Code. When Read / Bash / Grep spits out a ton of stuff, Jev first judges which parts are really relevant to the current task. 9. jev-review Before code review, run it through Jev first to pick out high-risk changes, then hand them off to a pricier big model or a human. Comes with a local dashboard. 10. Blink Use Jev as a code repository navigator. At each directory level, judge which files are most relevant to the current issue, then keep digging down. Copy these complete Jev blueprints - then read full Jev setup below ↓ ↓

Jev has been blowing up lately. If you've got the Jev API but don't know how to play around with it yet, you can just copy this checklist. 1. jev-ultrafast A high-speed browser Agent built with Browser Use. Jev only judges "what to do, which element to click" at each step, and only calls the small model when typing is needed. Searching for a flight on Google Flights takes about 7 seconds. 2. fast-jev-compaction Context compression for Claude Code. Before each tool call, have Jev judge if there's anything still useful; delete the useless stuff, and keep the original text without rewriting it. 3. json-render Vercel Labs' generative UI framework. In experiments, Jev doesn't write JSON token by token; it just handles selecting components, properties, and layouts. 4. typesafe-mcp Best for people who just got the API. Plug Jev into Claude Code, Claude Desktop, Codex, and Pi, and do Choice / Score / Noul anytime. 5. jev-mcp Ready-made Agent judgment toolkit: fact-checking, content screening, semantic ranking, classification, and information extraction. 6. SemDecide Turn Jev into a command-line tool. Directly classify, score, and filter in the Shell—great for hooking up to crawlers, CI, and data pipelines. 7. jev-codex-router First have Jev judge how hard this round of programming tasks is, then decide the model tier, reasoning depth, and speed mode. 8. Winnow Context garbage collection for Claude Code. When Read / Bash / Grep spits out a ton of stuff, Jev first judges which parts are really relevant to the current task. 9. jev-review Before code review, run it through Jev first to pick out high-risk changes, then hand them off to a pricier big model or a human. Comes with a local dashboard. 10. Blink Use Jev as a code repository navigator. At each directory level, judge which files are most relevant to the current issue, then keep digging down. Copy these complete Jev blueprints - then read full Jev setup below ↓ ↓

rody

204,901 Aufrufe • vor 1 Monat