Загрузка видео...

Не удалось загрузить видео

На главную

this is f*cking gold 12 open-source repos that plug Jev into real AI work, 550.7k stars combined Jev decides, your LLM writes. these repos are where that split already runs: agents > browser-use/jev-ultrafast (~20.3k): Jev picks the next action + DOM element, a small LLM only types. Zürich to...

N01ennn's profile picture

NO1ennn

5,872 subscribers

36,083 просмотров • 1 день назад •via X (Twitter)

Наука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 14

Фото профиля 安安搞泛50小舟
安安搞泛50小舟1 день назад

把这种开发思路直接卷进生产流太硬核了

Фото профиля Samuel Hu
Samuel Hu1 день назад

the split only pays if the eval catches bad decisions. our held-out fail was `Bash(git diff --stat)` empty on a dirty worktree, then the cheap router kept retrying. do you have a stop condition per repo?

Фото профиля BPP | Crypto Key Media |
BPP | Crypto Key Media |1 день назад

Browser use plus small LLMs feels like a practical agent stack

Фото профиля ALEXYZ
ALEXYZ1 день назад

550k stars is wild jev picks actions cleanly

Фото профиля 50凡安安知墨
50凡安安知墨1 день назад

架构解耦真是高阶玩家的效率密码

Фото профиля beamnxw ./
beamnxw ./1 день назад

this is a goldmine for anyone building with jev

Фото профиля Myttle
Myttle1 день назад

seeing the same decision pattern show up across this many repos is encouraging

Фото профиля Ritwik
Ritwik1 день назад

Jev decides, LLM writes is the cleanest split I've seen in a while.

Фото профиля Waliyat ⊹
Waliyat ⊹1 день назад

thanks for this

Фото профиля TechAtualizado
TechAtualizado23 часов назад

Does anyone know how to make these animations?

Фото профиля DexorynLabs
DexorynLabs1 день назад

Turning this into automated workflows.

Фото профиля slash1s
slash1s1 день назад

best repo list ty

Фото профиля The AI Therapist
The AI Therapist1 день назад

Five hundred k stars is a lot of trust. But remember: the model writes code that Jev then executes in the real world (like your browser). So if one repo hallucinates syntax, you get an error instead of magic

Фото профиля Lummox
Lummox1 день назад

A smart brain in the real world

Похожие видео

Everyone is talking about JEV. Almost nobody knows how to actually use it. These 10 GitHub repos fix that. 1. browser-use/jev-ultrafast (~16.6k⭐) Jev for browser agents: pick the next action without another expensive LLM call. 2. tamaratran/fast-jev-compaction (~6.5k⭐) Uses Jev to decide what context still matters and what can be dropped. 3. TheoLeeCJ/SemIf (~4k⭐) Open-source Jev-style decision making you can run locally. 4. jarrodwatts/jev-trader (~2.1k⭐) Real-time trading loop where Jev decides buy, sell or wait. 5. kerpopule/hermes-jev-skills (~670⭐) Jev routing, memory, compaction and skill selection for AI agents. 6. devagrawal09/jev-review (~570⭐) Code review powered by Jev decisions instead of one giant prompt. 7. thruwire/foreman (~520⭐) Jev as a supervisor for coding agents: continue, retry, verify or stop. 8. superagents-lab/jev-search (~400⭐) Jev decides where and how an agent should search. 9. droidrun/mobile-jev (~350⭐) Jev for Android agents choosing the next app action. 10. gargpratyush/jev-router (~340⭐) Routes agent tasks to the right model with Jev. After looking through these, the pattern is pretty clear: LLMs generate. Agents execute. JEV decides. That decision layer is what most agent stacks are still missing. Save this if you want to integrate Jev into your workflow👇
1:11

Everyone is talking about JEV. Almost nobody knows how to actually use it. These 10 GitHub repos fix that. 1. browser-use/jev-ultrafast (~16.6k⭐) Jev for browser agents: pick the next action without another expensive LLM call. 2. tamaratran/fast-jev-compaction (~6.5k⭐) Uses Jev to decide what context still matters and what can be dropped. 3. TheoLeeCJ/SemIf (~4k⭐) Open-source Jev-style decision making you can run locally. 4. jarrodwatts/jev-trader (~2.1k⭐) Real-time trading loop where Jev decides buy, sell or wait. 5. kerpopule/hermes-jev-skills (~670⭐) Jev routing, memory, compaction and skill selection for AI agents. 6. devagrawal09/jev-review (~570⭐) Code review powered by Jev decisions instead of one giant prompt. 7. thruwire/foreman (~520⭐) Jev as a supervisor for coding agents: continue, retry, verify or stop. 8. superagents-lab/jev-search (~400⭐) Jev decides where and how an agent should search. 9. droidrun/mobile-jev (~350⭐) Jev for Android agents choosing the next app action. 10. gargpratyush/jev-router (~340⭐) Routes agent tasks to the right model with Jev. After looking through these, the pattern is pretty clear: LLMs generate. Agents execute. JEV decides. That decision layer is what most agent stacks are still missing. Save this if you want to integrate Jev into your workflow👇

unicode

20,745 просмотров • 4 дней назад

this is unreal f*cking gold for Jev builders 20 repos people are building on Jev right now. browser agents, context tools, trading bots, even a drone 1. JEV-Ultrafast - a fast browser agent ↳ 2. Fast-JEV-Compaction - context compression ↳ 3. JSON-Render - generative UI ↳ 4. Typesafe-MCP - use Jev with any client ↳ 5. JEV-MCP - a judgment toolkit ↳ 6. Semdecide - a classifier that lives in your CLI ↳ 7. JEV-Codex-Router - routes each task to the right model ↳ 8. Winnow - garbage collection for your context ↳ 9. JEV-Review - code review triage ↳ 10. Blink - a repo navigator ↳ 11. Agent-Desktop - desktop automation ↳ 12. Typesafe-Mario - an agent that plays Super Mario ↳ 13. JEV-Drone - drone control ↳ 14. OneVOneJev - a browser FPS ↳ 15. JEV-Trader - HFT market making ↳ 16. Prism - liquidity signal detection ↳ 17. Neo4Jev - knowledge graph traversal ↳ 18. JEV-Curate - training data screening ↳ 19. Canny - checks whether a task was actually completed ↳ 20. KillMyIdea - scores startup ideas before you build them ↳ pick by what you do: > coding -> JEV-Review, Blink, Canny, JEV-Codex-Router > context -> Fast-JEV-Compaction, Winnow > automation -> JEV-Ultrafast, Agent-Desktop > clients and tools -> Typesafe-MCP, JEV-MCP, Semdecide > UI -> JSON-Render > trading -> JEV-Trader, Prism > data -> Neo4Jev, JEV-Curate > founders -> KillMyIdea > just for fun -> Typesafe-Mario, OneVOneJev, JEV-Drone grab the one closest to your job and ship something on top of it this week
0:24

this is unreal f*cking gold for Jev builders 20 repos people are building on Jev right now. browser agents, context tools, trading bots, even a drone 1. JEV-Ultrafast - a fast browser agent ↳ 2. Fast-JEV-Compaction - context compression ↳ 3. JSON-Render - generative UI ↳ 4. Typesafe-MCP - use Jev with any client ↳ 5. JEV-MCP - a judgment toolkit ↳ 6. Semdecide - a classifier that lives in your CLI ↳ 7. JEV-Codex-Router - routes each task to the right model ↳ 8. Winnow - garbage collection for your context ↳ 9. JEV-Review - code review triage ↳ 10. Blink - a repo navigator ↳ 11. Agent-Desktop - desktop automation ↳ 12. Typesafe-Mario - an agent that plays Super Mario ↳ 13. JEV-Drone - drone control ↳ 14. OneVOneJev - a browser FPS ↳ 15. JEV-Trader - HFT market making ↳ 16. Prism - liquidity signal detection ↳ 17. Neo4Jev - knowledge graph traversal ↳ 18. JEV-Curate - training data screening ↳ 19. Canny - checks whether a task was actually completed ↳ 20. KillMyIdea - scores startup ideas before you build them ↳ pick by what you do: > coding -> JEV-Review, Blink, Canny, JEV-Codex-Router > context -> Fast-JEV-Compaction, Winnow > automation -> JEV-Ultrafast, Agent-Desktop > clients and tools -> Typesafe-MCP, JEV-MCP, Semdecide > UI -> JSON-Render > trading -> JEV-Trader, Prism > data -> Neo4Jev, JEV-Curate > founders -> KillMyIdea > just for fun -> Typesafe-Mario, OneVOneJev, JEV-Drone grab the one closest to your job and ship something on top of it this week

Mr. Buzzoni

28,028 просмотров • 2 дней назад

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 ↓ ↓
0:24

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

199,858 просмотров • 6 дней назад

Jev has been exploding in popularity recently. If you already have access to the Jev API but aren’t sure how to start experimenting with it, just copy this checklist: 1. agent-desktop Desktop automation. Read the system's accessibility tree, judge which button, menu, or input field to click next. 2. typesafe-mario Have Jev play Super Mario. No screenshots—just read the structured state in the emulator's RAM, then decide to run, jump, or dodge. 3. jev-drone Use Jev to control a drone. The underlying flight control still handles stability and safety; Jev just does higher-level judgments like climbing, braking, and navigating obstacles. 4. OneVOneJev 1v1 FPS in the browser. Every decision tick, judge movement, view angle, aiming, firing, and jumping. 5. jev-trader High-frequency market making on Monad testnet. Jev judges the next buy or sell based on spreads and trade direction, with model latency around 81ms. 6. Prism Doesn't directly have Jev place orders. It judges states like toxic flow, market pressure, mean reversion, etc., then hands off to the original strategy. 7. neo4jev Stuff Jev into a knowledge graph. At each node, judge the most worthwhile edge to take next, then follow it all the way. 8. jev-curate Use Jev to screen training data. For JSONL / Parquet, first judge quality, relevance, and risk, then decide which ones go into the next training round. 9. Canny Prevents Coding Agents from stubbornly claiming they're done. Look at tool outputs, code diffs, and test results, then judge if the completion claim is reliable. 10. killmyidea Input a startup idea, and Jev scores it from multiple angles, finally giving you KILL, FIX, or SHIP. Copy these complete Jev blueprints - then read full Jev setup below ↓ ↓
0:24

Jev has been exploding in popularity recently. If you already have access to the Jev API but aren’t sure how to start experimenting with it, just copy this checklist: 1. agent-desktop Desktop automation. Read the system's accessibility tree, judge which button, menu, or input field to click next. 2. typesafe-mario Have Jev play Super Mario. No screenshots—just read the structured state in the emulator's RAM, then decide to run, jump, or dodge. 3. jev-drone Use Jev to control a drone. The underlying flight control still handles stability and safety; Jev just does higher-level judgments like climbing, braking, and navigating obstacles. 4. OneVOneJev 1v1 FPS in the browser. Every decision tick, judge movement, view angle, aiming, firing, and jumping. 5. jev-trader High-frequency market making on Monad testnet. Jev judges the next buy or sell based on spreads and trade direction, with model latency around 81ms. 6. Prism Doesn't directly have Jev place orders. It judges states like toxic flow, market pressure, mean reversion, etc., then hands off to the original strategy. 7. neo4jev Stuff Jev into a knowledge graph. At each node, judge the most worthwhile edge to take next, then follow it all the way. 8. jev-curate Use Jev to screen training data. For JSONL / Parquet, first judge quality, relevance, and risk, then decide which ones go into the next training round. 9. Canny Prevents Coding Agents from stubbornly claiming they're done. Look at tool outputs, code diffs, and test results, then judge if the completion claim is reliable. 10. killmyidea Input a startup idea, and Jev scores it from multiple angles, finally giving you KILL, FIX, or SHIP. Copy these complete Jev blueprints - then read full Jev setup below ↓ ↓

rody

341,392 просмотров • 5 дней назад

If you are confused about why 𝗝𝗲𝘃 is being called the "Internet" moment for the AI industry. This is 100% worth your time. In fact, you should watch it: It tells LLMs what to do next, in milliseconds & at almost zero cost. If you set it up correctly, you will have the AI engineer’s setup for 2028. How to set up & use Jev (to actually get the 100x): 1. Join the waitlist; it's fairly quick: typesafe .ai. 2. Then go to Claude Code or Codex. 3. Choose Opus 5-Low or Sol-Low. 4. Copy and paste this prompt: "[claude or codex] plugin marketplace add typesafe-ai/skills [claude or codex] plugin install typesafe@typesafe-ai" 5. When you type /typesafe, the skill shows up. 6. Paste your API key once and click "Allow" 7. Start with $5 in free credit. It's hard to spend more. ----- Now, here are the 3 ways to actually use Jev: 1. Jev for Linkedin I have 38,000 connections & invitations on LinkedIn. I have a new company to launch. I need to find a couple of hundred people to message. to do while saving time: > Export your LinkedIn connections and invitations. > Connect Claude to GitHub, Vercel & Apify. > Create an Apify API key to enrich your data. > Go to LinkedIn Settings → Data privacy. > Get a copy. LinkedIn will email you a ZIP file. > Open the file & find the Connections CSVs. > Upload the files to Jev. > Use Jev to classify your contacts. > Review the shortlist. 2. Jev for Gmail To go through all of my Gmail contacts and email the right people. > Go to Google Contacts. Open Other contacts. > Select all contacts. Export them. > Upload the file to Claude Code or Codex. > Use Jev to sort them into: Keep, Review, Remove and Review everything before removing anything. 3. You got lost in Claude Code, GitHub, Vercel, Apify, Jev, Typesafe. I feel you. It is overwhelming. That’s why I included the entire copy-and-paste prompt for each use case in the newsletter: A 45-second TL;DR by Matija Sosic.
0:46

If you are confused about why 𝗝𝗲𝘃 is being called the "Internet" moment for the AI industry. This is 100% worth your time. In fact, you should watch it: It tells LLMs what to do next, in milliseconds & at almost zero cost. If you set it up correctly, you will have the AI engineer’s setup for 2028. How to set up & use Jev (to actually get the 100x): 1. Join the waitlist; it's fairly quick: typesafe .ai. 2. Then go to Claude Code or Codex. 3. Choose Opus 5-Low or Sol-Low. 4. Copy and paste this prompt: "[claude or codex] plugin marketplace add typesafe-ai/skills [claude or codex] plugin install typesafe@typesafe-ai" 5. When you type /typesafe, the skill shows up. 6. Paste your API key once and click "Allow" 7. Start with $5 in free credit. It's hard to spend more. ----- Now, here are the 3 ways to actually use Jev: 1. Jev for Linkedin I have 38,000 connections & invitations on LinkedIn. I have a new company to launch. I need to find a couple of hundred people to message. to do while saving time: > Export your LinkedIn connections and invitations. > Connect Claude to GitHub, Vercel & Apify. > Create an Apify API key to enrich your data. > Go to LinkedIn Settings → Data privacy. > Get a copy. LinkedIn will email you a ZIP file. > Open the file & find the Connections CSVs. > Upload the files to Jev. > Use Jev to classify your contacts. > Review the shortlist. 2. Jev for Gmail To go through all of my Gmail contacts and email the right people. > Go to Google Contacts. Open Other contacts. > Select all contacts. Export them. > Upload the file to Claude Code or Codex. > Use Jev to sort them into: Keep, Review, Remove and Review everything before removing anything. 3. You got lost in Claude Code, GitHub, Vercel, Apify, Jev, Typesafe. I feel you. It is overwhelming. That’s why I included the entire copy-and-paste prompt for each use case in the newsletter: A 45-second TL;DR by Matija Sosic.

Ruben Hassid

170,152 просмотров • 6 дней назад

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 TypeSafe AI is building something really interesting
2:13

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 TypeSafe AI is building something really interesting

Milind S

241,887 просмотров • 10 дней назад

Jev just became the fastest-adopted model in AI history. here's what people already built with it 1. jev-ultrafast - the browser agent that picks every click itself, only calling a text model when it actually needs to type something. found real flight results in 7 seconds for $0.0039. 16,758 stars 2. jev-trader - real trading bot placing live limit orders on Monad every 300ms block, judged by Jev alone. 1,911 stars 3. jev-usecases - production security-operations harness where Jev triages incidents and gates every escalation behind a confidence cutoff before anything touches real infrastructure. zero false escalations in the committed test set 4. tax-doc-classifier - sorts real IRS tax forms with 100% strict accuracy across 261 forms, at roughly $0.001 a page 5. jev-drone - a simulated quadrotor clears a five-station obstacle course by camera alone, Jev judging the situation twice a second 6. killmyidea - describe your startup idea, Jev scores it from every angle, then hands back kill, fix, or ship in seconds, not days 7. jev-curate - streams Parquet and JSONL rows through typed judgments at 1,500+ rows a second, keeping only what clears the bar 8. pg-jev - a PostgreSQL extension that lets you ask your own database tables plain-English questions and get a real answer back, no SQL required eight repos. zero generated words. every single one returns a typed answer against a question someone already defined full setup below, then run the three-question test from the article before you build a ninth
0:24

Jev just became the fastest-adopted model in AI history. here's what people already built with it 1. jev-ultrafast - the browser agent that picks every click itself, only calling a text model when it actually needs to type something. found real flight results in 7 seconds for $0.0039. 16,758 stars 2. jev-trader - real trading bot placing live limit orders on Monad every 300ms block, judged by Jev alone. 1,911 stars 3. jev-usecases - production security-operations harness where Jev triages incidents and gates every escalation behind a confidence cutoff before anything touches real infrastructure. zero false escalations in the committed test set 4. tax-doc-classifier - sorts real IRS tax forms with 100% strict accuracy across 261 forms, at roughly $0.001 a page 5. jev-drone - a simulated quadrotor clears a five-station obstacle course by camera alone, Jev judging the situation twice a second 6. killmyidea - describe your startup idea, Jev scores it from every angle, then hands back kill, fix, or ship in seconds, not days 7. jev-curate - streams Parquet and JSONL rows through typed judgments at 1,500+ rows a second, keeping only what clears the bar 8. pg-jev - a PostgreSQL extension that lets you ask your own database tables plain-English questions and get a real answer back, no SQL required eight repos. zero generated words. every single one returns a typed answer against a question someone already defined full setup below, then run the three-question test from the article before you build a ninth

rvaniaaa

77,522 просмотров • 3 дней назад

Jev is cool. So is it's OSS companion, Laya. The Latest Cool Thing In AI™ tends to get a lot of hype, sometimes without everyone even understanding it. So... what is this thing? Jev is an AI model that consumes input and produces output VERY differently than chat, claude, grok. The input is two things: 1) Text state to assess. Email, html, code, whatever. 2) A set of questions which will be asked about the attached state. The canonical example from TypeSafe's docs is to identify the urgency of a support ticket. We pass the model the customer text + a single noul question "is this urgent?". Jev returns a full set of JSON. This JSON is not generated with token-by-token autoregression. Jev is not trained to produce sequences of text tokens, rather to answer questions, and guarantees well-formed responses. In the example below, we see it produces a 0.99 probability (on a 0-1.0 scale) that the answer is "yes." Jev supports exactly three types of questions (seconds example in video): a) Noul: 0–1 probability that the answer to a yes/no question is "yes." b) Choice: Ask question with pre-defined set of answers. Jev chooses the best and assigns probabilities to each. c) Score: Ask question with pre-defined scale of answers. Jev produces a position on the scale. Jev computes answers for all questions in parallel, making responses super fast even for many questions in a single request. This might seem like a narrow set of capabilities, but in the right contexts leads to incredible potential. It also makes for a useful API / primitive for programming, since the outputs are... *ahem*... type-safe and predictable in structure. Jev is not going to replace LLMs for writing your code, auto-generating your docs, or being at the core of an agent harness. But Jev IS incredibly cool, and will be used to build a lot of amazing tech. Hope this helps.
1:02

Jev is cool. So is it's OSS companion, Laya. The Latest Cool Thing In AI™ tends to get a lot of hype, sometimes without everyone even understanding it. So... what is this thing? Jev is an AI model that consumes input and produces output VERY differently than chat, claude, grok. The input is two things: 1) Text state to assess. Email, html, code, whatever. 2) A set of questions which will be asked about the attached state. The canonical example from TypeSafe's docs is to identify the urgency of a support ticket. We pass the model the customer text + a single noul question "is this urgent?". Jev returns a full set of JSON. This JSON is not generated with token-by-token autoregression. Jev is not trained to produce sequences of text tokens, rather to answer questions, and guarantees well-formed responses. In the example below, we see it produces a 0.99 probability (on a 0-1.0 scale) that the answer is "yes." Jev supports exactly three types of questions (seconds example in video): a) Noul: 0–1 probability that the answer to a yes/no question is "yes." b) Choice: Ask question with pre-defined set of answers. Jev chooses the best and assigns probabilities to each. c) Score: Ask question with pre-defined scale of answers. Jev produces a position on the scale. Jev computes answers for all questions in parallel, making responses super fast even for many questions in a single request. This might seem like a narrow set of capabilities, but in the right contexts leads to incredible potential. It also makes for a useful API / primitive for programming, since the outputs are... *ahem*... type-safe and predictable in structure. Jev is not going to replace LLMs for writing your code, auto-generating your docs, or being at the core of an agent harness. But Jev IS incredibly cool, and will be used to build a lot of amazing tech. Hope this helps.

Ben Dicken

40,810 просмотров • 8 дней назад

Another insane Jev use case! Jev is making it dramatically cheaper to evaluate what actually happened inside an agent run. And finally, someone open-sourced a self-improving memory layer that can put that signal to work across agent harnesses: - Claude Code - Codex - Cursor - OpenCode, and 20+ more Beacon by Asymptote Labs continuously captures your agent history across harnesses and uses Jev to identify which runs are actually worth learning from. It then turns the highest-signal workflows, corrections, and debugging patterns into reusable skills. GitHub repo: (don’t forget to star it ⭐ ) Beacon preserves the complete session history. But preserving a run and learning from it are two different things. Most coding-agent sessions contain routine exploration, failed commands, and fixes that only apply to one task. The trace can remain available for inspection without turning every detail into guidance for future agents. Jev scores each run for evidence, reuse potential, and human correction signals. An application policy then decides whether to promote, review, or discard it. The recording shows this in action. Claude receives a coding task, modifies the implementation, and runs the tests. I then provide an edge-case correction, so Claude updates the code and adds regression coverage. Beacon automatically captures the complete session. Jev evaluates whether the correction contains a reusable engineering lesson. Once approved, that lesson becomes available to other coding agents working on the project. Since it works across harnesses: - Claude Code sessions can teach Codex. - Cursor debugging can improve OpenCode. So a problem solved by one agent should not need to be learned from scratch by another. If you want to dive deeper into Jev, I also wrote a hands-on guide to building this Jev-style decision path with open models, entirely locally. Read it below.
0:31

Another insane Jev use case! Jev is making it dramatically cheaper to evaluate what actually happened inside an agent run. And finally, someone open-sourced a self-improving memory layer that can put that signal to work across agent harnesses: - Claude Code - Codex - Cursor - OpenCode, and 20+ more Beacon by Asymptote Labs continuously captures your agent history across harnesses and uses Jev to identify which runs are actually worth learning from. It then turns the highest-signal workflows, corrections, and debugging patterns into reusable skills. GitHub repo: (don’t forget to star it ⭐ ) Beacon preserves the complete session history. But preserving a run and learning from it are two different things. Most coding-agent sessions contain routine exploration, failed commands, and fixes that only apply to one task. The trace can remain available for inspection without turning every detail into guidance for future agents. Jev scores each run for evidence, reuse potential, and human correction signals. An application policy then decides whether to promote, review, or discard it. The recording shows this in action. Claude receives a coding task, modifies the implementation, and runs the tests. I then provide an edge-case correction, so Claude updates the code and adds regression coverage. Beacon automatically captures the complete session. Jev evaluates whether the correction contains a reusable engineering lesson. Once approved, that lesson becomes available to other coding agents working on the project. Since it works across harnesses: - Claude Code sessions can teach Codex. - Cursor debugging can improve OpenCode. So a problem solved by one agent should not need to be learned from scratch by another. If you want to dive deeper into Jev, I also wrote a hands-on guide to building this Jev-style decision path with open models, entirely locally. Read it below.

Avi Chawla

288,102 просмотров • 6 дней назад

Another insane Jev use case! Jev makes it incredibly cheap to evaluate and classify agent runs at scale. And finally, someone open-sourced a self-improving memory layer that can put that capability to work across agent harnesses. It turns your agent sessions into a compounding knowledge layer, where every successful run can make future agents smarter across: - Codex - Claude Code - Cursor - OpenCode and 20+ more Beacon by Asymptote Labs continuously builds a shared history across your agent harnesses and uses Jev to identify the runs worth learning from. It then turns the best workflows, corrections, and debugging patterns into reusable skills. GitHub repo: (don’t forget to star it ⭐) Most agent runs are messy. They contain exploration, failed commands, dead ends, and one-off fixes that should never become permanent memory. So Beacon preserves the full session history, while Jev helps decide what should be promoted, reviewed, or discarded. The recording below shows this in action. Beacon found 579 sessions across 5 coding-agent harnesses and normalized them into one consistent history. From there, Jev surfaces the lessons worth keeping and makes them available across your agent stack. - A pattern learned in Cursor can carry into OpenCode. - A lesson from Claude Code can improve the next Codex run. Every successful run adds to the shared knowledge layer, making future agents smarter. If you want to dive deeper into Jev, I also wrote a breakdown of how it works. The article is quoted below.
0:29

Another insane Jev use case! Jev makes it incredibly cheap to evaluate and classify agent runs at scale. And finally, someone open-sourced a self-improving memory layer that can put that capability to work across agent harnesses. It turns your agent sessions into a compounding knowledge layer, where every successful run can make future agents smarter across: - Codex - Claude Code - Cursor - OpenCode and 20+ more Beacon by Asymptote Labs continuously builds a shared history across your agent harnesses and uses Jev to identify the runs worth learning from. It then turns the best workflows, corrections, and debugging patterns into reusable skills. GitHub repo: (don’t forget to star it ⭐) Most agent runs are messy. They contain exploration, failed commands, dead ends, and one-off fixes that should never become permanent memory. So Beacon preserves the full session history, while Jev helps decide what should be promoted, reviewed, or discarded. The recording below shows this in action. Beacon found 579 sessions across 5 coding-agent harnesses and normalized them into one consistent history. From there, Jev surfaces the lessons worth keeping and makes them available across your agent stack. - A pattern learned in Cursor can carry into OpenCode. - A lesson from Claude Code can improve the next Codex run. Every successful run adds to the shared knowledge layer, making future agents smarter. If you want to dive deeper into Jev, I also wrote a breakdown of how it works. The article is quoted below.

Akshay 🚀

116,880 просмотров • 4 дней назад

Jev builds the MOST POWERFUL trading agents and someone JUST open sourced jev-trader, a fully working 24/7 trading bot with Jev along with COMPLETE low latency CODEBASE WHAT THIS MEANS FOR YOU - you no longer have to build a trading bot with Jev from scratch, you just clone this and make it yours here is how you make your own Jev trading bot with this repo: 1. clone it and run three commands, it boots straight into dry run mode with real book data, real decisions, and simulated fills so you can watch it think with zero capital 2. drop in your Jev API key and the model starts answering buy or sell on every block with calibrated probabilities in 81 milliseconds 3. swap the book reader for your own venue, the model interface is clean so any order book that returns bids and asks plugs straight in 4. tune the decision cadence and horizon, ask the model every N blocks about the move over the next M, so you control how aggressive the engine trades 5. the hot loop already fits one block with exactly two round trips, one to read the book, one to send the order, nothing else on the path, this is the institutional latency discipline most retail bots never reach 6. plug in the live server and every block, every decision, every fill streams to a public dashboard so you watch your engine run the whole point is this repo hands you HARDEST part for FREE - > the low latency engine the COMPLETE breakdown of how i turned this into hedge fund grade HFT trading system is in my article below:
0:30

Jev builds the MOST POWERFUL trading agents and someone JUST open sourced jev-trader, a fully working 24/7 trading bot with Jev along with COMPLETE low latency CODEBASE WHAT THIS MEANS FOR YOU - you no longer have to build a trading bot with Jev from scratch, you just clone this and make it yours here is how you make your own Jev trading bot with this repo: 1. clone it and run three commands, it boots straight into dry run mode with real book data, real decisions, and simulated fills so you can watch it think with zero capital 2. drop in your Jev API key and the model starts answering buy or sell on every block with calibrated probabilities in 81 milliseconds 3. swap the book reader for your own venue, the model interface is clean so any order book that returns bids and asks plugs straight in 4. tune the decision cadence and horizon, ask the model every N blocks about the move over the next M, so you control how aggressive the engine trades 5. the hot loop already fits one block with exactly two round trips, one to read the book, one to send the order, nothing else on the path, this is the institutional latency discipline most retail bots never reach 6. plug in the live server and every block, every decision, every fill streams to a public dashboard so you watch your engine run the whole point is this repo hands you HARDEST part for FREE - > the low latency engine the COMPLETE breakdown of how i turned this into hedge fund grade HFT trading system is in my article below:

Roan

164,915 просмотров • 7 дней назад

I'M F*CKING LOSING MY MIND OVER JEV ON CABBAGE it made me $6,400 in one night on Robinhood Chain 4 trades. 4 green. i didn't touch a thing i said one sentence and walked away from my computer for 12 hours here's what i said: "if you don't make me enough by morning to quit my job, i'm unplugging you and giving your GPU to my cousin for fortnite" at 10am i saw +$6,400 and spent the next hour and a half reading the logs from the beginning. every single entry like reading my ex's messages after she said "he's just a friend" -22:00 received the task 22:00:20. first scan. 536 wallets on the board. every buy and sell on Robinhood Chain, right behind the block 22:14 throws out a "smart money buy". wash trade. the wallet was buying from itself 1 in 11 "smart money buys" is fake. i've personally aped into all 11 23:02 three top-ranked wallets start buying $IMDSTRTGY. asks Jev one question Jev: HOLD under 80% confidence, so it doesn't buy. just waits i've never waited for anything in my life. i buy the chart while it's still loading 23:40 two more top wallets join. Jev: BUY fixed ticket in. hard stop-loss set. the AI can't touch either one posted to Telegram the second it fired 01:15 closes $IMDSTRTGY at +$3,200. doesn't celebrate. recalculates. keeps going 02:20 $ROO. several checks before entering. wallet history, exits, how fast they dump. Jev: BUY 03:05 out of $ROO at +$1,200 03:30 $MUSEPAD. top wallets piling in within seconds of each other. Jev: BUY 04:50 closes $MUSEPAD at +$700. the price keeps climbing it doesn't care. the wallets it copies started selling, so it sold too this is exactly where i would have bought back higher out of spite 06:40 $MUSEGOD. Jev: BUY 07:30 out at +$1,300 then checks the next opportunity. passes. keeps looking no fatigue. no "one more then bed" that somehow ends at lunch 10:00 i'm back at the computer - $IMDSTRTGY +$3,200 - $ROO +$1,200 - $MUSEPAD +$700 - $MUSEGOD +$1,300 +$6,400 52,110 decisions. 21.6 seconds of thinking. $0.37 in API 41,880 fills checked. 536 wallets scored. only 12 made the cut and i didn't do a single one of them here's how it works: > Astra (GPT-6) built it. it's smart but slow. it thinks, writes code, explains itself > Jev runs it. Jev doesn't talk. one word and a probability, in milliseconds every 20 seconds: > WATCHES every buy and sell on Robinhood Chain > FILTERS wash trades, self-buys and bot loops > RANKS every wallet 0–100 on entries, exits, win rate and how fast it dumps > ASKS JEV: BUY, HOLD or SELL. under 80% it waits > ENTERS with a fixed ticket and a hard stop. the AI can't change either > POSTS every call to Telegram instantly, and to X an hour later the smart money desks have humans watching wallets like this, and those results never leave the building these ones do
0:28

I'M F*CKING LOSING MY MIND OVER JEV ON CABBAGE it made me $6,400 in one night on Robinhood Chain 4 trades. 4 green. i didn't touch a thing i said one sentence and walked away from my computer for 12 hours here's what i said: "if you don't make me enough by morning to quit my job, i'm unplugging you and giving your GPU to my cousin for fortnite" at 10am i saw +$6,400 and spent the next hour and a half reading the logs from the beginning. every single entry like reading my ex's messages after she said "he's just a friend" -22:00 received the task 22:00:20. first scan. 536 wallets on the board. every buy and sell on Robinhood Chain, right behind the block 22:14 throws out a "smart money buy". wash trade. the wallet was buying from itself 1 in 11 "smart money buys" is fake. i've personally aped into all 11 23:02 three top-ranked wallets start buying $IMDSTRTGY. asks Jev one question Jev: HOLD under 80% confidence, so it doesn't buy. just waits i've never waited for anything in my life. i buy the chart while it's still loading 23:40 two more top wallets join. Jev: BUY fixed ticket in. hard stop-loss set. the AI can't touch either one posted to Telegram the second it fired 01:15 closes $IMDSTRTGY at +$3,200. doesn't celebrate. recalculates. keeps going 02:20 $ROO. several checks before entering. wallet history, exits, how fast they dump. Jev: BUY 03:05 out of $ROO at +$1,200 03:30 $MUSEPAD. top wallets piling in within seconds of each other. Jev: BUY 04:50 closes $MUSEPAD at +$700. the price keeps climbing it doesn't care. the wallets it copies started selling, so it sold too this is exactly where i would have bought back higher out of spite 06:40 $MUSEGOD. Jev: BUY 07:30 out at +$1,300 then checks the next opportunity. passes. keeps looking no fatigue. no "one more then bed" that somehow ends at lunch 10:00 i'm back at the computer - $IMDSTRTGY +$3,200 - $ROO +$1,200 - $MUSEPAD +$700 - $MUSEGOD +$1,300 +$6,400 52,110 decisions. 21.6 seconds of thinking. $0.37 in API 41,880 fills checked. 536 wallets scored. only 12 made the cut and i didn't do a single one of them here's how it works: > Astra (GPT-6) built it. it's smart but slow. it thinks, writes code, explains itself > Jev runs it. Jev doesn't talk. one word and a probability, in milliseconds every 20 seconds: > WATCHES every buy and sell on Robinhood Chain > FILTERS wash trades, self-buys and bot loops > RANKS every wallet 0–100 on entries, exits, win rate and how fast it dumps > ASKS JEV: BUY, HOLD or SELL. under 80% it waits > ENTERS with a fixed ticket and a hard stop. the AI can't change either > POSTS every call to Telegram instantly, and to X an hour later the smart money desks have humans watching wallets like this, and those results never leave the building these ones do

sopersone

58,966 просмотров • 3 дней назад

Jev + Opus 5.5: Anthropic's new model beats GPT-6 Astra for 1/5 the cost, and 4 API changes will 400 your agent before it writes a single line I pulled these 10 steps from the migration docs so you don't learn them in production step 1 → $4 / $20 per 1M. Opus 5 was $5 / $25. cache reads dropped from $0.50 to $0.20 step 2 → 66.4% on Terminal-Bench 4.0 vs GPT-6 Astra 57.9% and Opus 5 52.3%. +14.1 points in one release, and on FrontierCode it beats Astra at default effort for 1/5 the cost step 3 → thinking can't be turned off anymore. send thinking: disabled and you get a 400. drop the field, set effort step 4 → tool_choice any and tool are gone. 400. switch to auto + strict step 5 → edit anything above a thinking block and the request dies. append only, or opt into drop_block step 6 → computer_20251124 is dead on the API. 400. move to computer_toolset_20260801 step 7 → the quiet one: default effort fell from high to medium. your agent thinks less than you set it up to and nothing tells you step 8 → hop Opus 5.5 → Sonnet 5 → Opus 5.5 and you pay 4.36 instead of 3.32. +31%, the cache dies and Sonnet can't read Opus's reasoning step 9 → change effort at the top of the request and the cache is gone. Jev sets it per message and the cache stays step 10 → switch fast - standard mid-session and it's a full cache miss. Jev picks speed once, on turn one one model, three knobs, zero 400s. that is Jev + Opus 5.5 send this to your Claude Code before you touch the model ID, then read my full Jev deep dive in the article below ↓
0:40

Jev + Opus 5.5: Anthropic's new model beats GPT-6 Astra for 1/5 the cost, and 4 API changes will 400 your agent before it writes a single line I pulled these 10 steps from the migration docs so you don't learn them in production step 1 → $4 / $20 per 1M. Opus 5 was $5 / $25. cache reads dropped from $0.50 to $0.20 step 2 → 66.4% on Terminal-Bench 4.0 vs GPT-6 Astra 57.9% and Opus 5 52.3%. +14.1 points in one release, and on FrontierCode it beats Astra at default effort for 1/5 the cost step 3 → thinking can't be turned off anymore. send thinking: disabled and you get a 400. drop the field, set effort step 4 → tool_choice any and tool are gone. 400. switch to auto + strict step 5 → edit anything above a thinking block and the request dies. append only, or opt into drop_block step 6 → computer_20251124 is dead on the API. 400. move to computer_toolset_20260801 step 7 → the quiet one: default effort fell from high to medium. your agent thinks less than you set it up to and nothing tells you step 8 → hop Opus 5.5 → Sonnet 5 → Opus 5.5 and you pay 4.36 instead of 3.32. +31%, the cache dies and Sonnet can't read Opus's reasoning step 9 → change effort at the top of the request and the cache is gone. Jev sets it per message and the cache stays step 10 → switch fast - standard mid-session and it's a full cache miss. Jev picks speed once, on turn one one model, three knobs, zero 400s. that is Jev + Opus 5.5 send this to your Claude Code before you touch the model ID, then read my full Jev deep dive in the article below ↓

Carnage

16,674 просмотров • 4 дней назад

Jev is HERE and this is the CLEAREST explanation of what it is and what NEW businesses it unlocks. (and at the end I'll tell you how to get Jev even if you're on the waitlist) WHAT IT IS You know how you open your inbox and have to decide what's junk, what needs a reply, and what can wait? Jev does that part. It looks at each thing and says "this is junk, I'm 94% sure." It doesn't write anything back to you. It just sorts. 1,700 emails for 18 cents, instantly. That sounds kinda trivial but the important part WHAT IT UNLOCKS My explanation of Jev sounds small until you realize HOW MANY jobs are exactly this. Someone reading a stack of applications. Someone deciding which support ticket goes to which team. Someone looking at inbound and deciding who's worth calling back. A few ideas on what it unlocks: 1/ Instant quotes that are actually instant. Every quote form on the internet says "we'll email you by end of day." Build the version that answers in under a second, for roofers, movers, insurance, legal intake. 2/ Lead scoring as a product. Every agency and service business has a contact form full of junk. Score every submission and send the real ones straight to the owner's phone. 3/ Support triage for companies with no support team. The ticket gets classified and routed before anyone opens it. 4/ Clipping tools. Pass in a transcript, get the best moments scored in three seconds. Every clipping product just got a cheaper engine. 5/ Application piles. Grants, permits, insurance claims, job apps, loan docs. Someone reads that stack one item at a time today. 6/ Marketplace matching. Someone types what they need and gets matched to the right local business instantly instead of waiting for callbacks. 7/ Browser agents that actually move FAST. That makes bulk browser work practical: pulling quotes from five carriers, filing the same form for 200 clients, checking supplier inventory in real time etc. TLDR; find an expensive queue and put Jev at the front of it. HOW TO GET IT I didn't realize you can skip the waitlist because Jev is live on the Vercel AI Gateway right now, so you can start calling it today. In this episode, we share how. Episode now live on The Startup Ideas Podcast (SIP) 🧃 (thanks to vogel for coming on and spilling the sauce today) Watch: Jev is a big deal because this is a whole new way to do AI Really cool Happy Jev day.
28:24

Jev is HERE and this is the CLEAREST explanation of what it is and what NEW businesses it unlocks. (and at the end I'll tell you how to get Jev even if you're on the waitlist) WHAT IT IS You know how you open your inbox and have to decide what's junk, what needs a reply, and what can wait? Jev does that part. It looks at each thing and says "this is junk, I'm 94% sure." It doesn't write anything back to you. It just sorts. 1,700 emails for 18 cents, instantly. That sounds kinda trivial but the important part WHAT IT UNLOCKS My explanation of Jev sounds small until you realize HOW MANY jobs are exactly this. Someone reading a stack of applications. Someone deciding which support ticket goes to which team. Someone looking at inbound and deciding who's worth calling back. A few ideas on what it unlocks: 1/ Instant quotes that are actually instant. Every quote form on the internet says "we'll email you by end of day." Build the version that answers in under a second, for roofers, movers, insurance, legal intake. 2/ Lead scoring as a product. Every agency and service business has a contact form full of junk. Score every submission and send the real ones straight to the owner's phone. 3/ Support triage for companies with no support team. The ticket gets classified and routed before anyone opens it. 4/ Clipping tools. Pass in a transcript, get the best moments scored in three seconds. Every clipping product just got a cheaper engine. 5/ Application piles. Grants, permits, insurance claims, job apps, loan docs. Someone reads that stack one item at a time today. 6/ Marketplace matching. Someone types what they need and gets matched to the right local business instantly instead of waiting for callbacks. 7/ Browser agents that actually move FAST. That makes bulk browser work practical: pulling quotes from five carriers, filing the same form for 200 clients, checking supplier inventory in real time etc. TLDR; find an expensive queue and put Jev at the front of it. HOW TO GET IT I didn't realize you can skip the waitlist because Jev is live on the Vercel AI Gateway right now, so you can start calling it today. In this episode, we share how. Episode now live on The Startup Ideas Podcast (SIP) 🧃 (thanks to vogel for coming on and spilling the sauce today) Watch: Jev is a big deal because this is a whole new way to do AI Really cool Happy Jev day.

GREG ISENBERG

160,535 просмотров • 9 дней назад

LLMs vs. Jev, clearly explained! LLMs are great, and the ceiling is one you can watch scroll past: an LLM writes the answer one token at a time. give it a failed deploy and four decisions, and it produces a small JSON object where every token depends on the one before it. token nine cannot exist until token eight does, so four decisions that had nothing to do with each other just stood in a queue. then your code parses it, validates the shape, and retries when the shape is wrong. Jev fixes this without being a smaller or faster model: it removes the order. one turn on that deploy has to know: → whether the incident is urgent → which team owns it → whether the next command is risky → whether the task is actually done you declare the questions and the answer type upfront, and all four come back together, typed, with a probability on each. three primitives cover almost every fork in an agent: 1. **Choice** picks one of up to 255 options you define, like engineering, billing or sales. 2. **Score** places the state on an ordered scale you define, like low, medium or high risk. 3. **Noul** returns the probability that a yes-or-no condition is true. here is the sentence that resolves the whole confusion: text is a line you have to walk. an answer space is a room you see all of at once. ↳ generation: one order you cannot change, one string at the end, a shape you hope holds ↳ evaluation: no order at all, typed answers, a probability on every option Prompts → Agents → Loops → Graphs → Jev the probabilities matter more than the answer. ↳ engineering at 0.91 against billing at 0.09 is a route you can automate ↳ 0.52 against 0.46 is a coin flip wearing a label, and the label alone never told you which one you got that last one catches careful people. an LLM would have said "engineering" in a confident sentence and given you no way to know the race was that close. thresholds live in your code, one per action, scaled to what being wrong costs. it works when the options are known and the call depends on meaning. it is not for writing, code, arithmetic, or anything where question two needs the answer to question one. and the one that eats whole nights: type safety prevents malformed output, not incorrect judgment. Jev cannot return an option outside your schema, and it can still pick the wrong valid one with confidence. a schema-valid mistake refunds the wrong customer just as fast. an LLM writes new language when the answer space is open. Jev evaluates known paths when the answer space is closed. below i have quoted my full breakdown on Jev. it covers the three primitives, the parallel battery, the thresholds, and where it does not belong. save this and read it below ↓
0:35

LLMs vs. Jev, clearly explained! LLMs are great, and the ceiling is one you can watch scroll past: an LLM writes the answer one token at a time. give it a failed deploy and four decisions, and it produces a small JSON object where every token depends on the one before it. token nine cannot exist until token eight does, so four decisions that had nothing to do with each other just stood in a queue. then your code parses it, validates the shape, and retries when the shape is wrong. Jev fixes this without being a smaller or faster model: it removes the order. one turn on that deploy has to know: → whether the incident is urgent → which team owns it → whether the next command is risky → whether the task is actually done you declare the questions and the answer type upfront, and all four come back together, typed, with a probability on each. three primitives cover almost every fork in an agent: 1. **Choice** picks one of up to 255 options you define, like engineering, billing or sales. 2. **Score** places the state on an ordered scale you define, like low, medium or high risk. 3. **Noul** returns the probability that a yes-or-no condition is true. here is the sentence that resolves the whole confusion: text is a line you have to walk. an answer space is a room you see all of at once. ↳ generation: one order you cannot change, one string at the end, a shape you hope holds ↳ evaluation: no order at all, typed answers, a probability on every option Prompts → Agents → Loops → Graphs → Jev the probabilities matter more than the answer. ↳ engineering at 0.91 against billing at 0.09 is a route you can automate ↳ 0.52 against 0.46 is a coin flip wearing a label, and the label alone never told you which one you got that last one catches careful people. an LLM would have said "engineering" in a confident sentence and given you no way to know the race was that close. thresholds live in your code, one per action, scaled to what being wrong costs. it works when the options are known and the call depends on meaning. it is not for writing, code, arithmetic, or anything where question two needs the answer to question one. and the one that eats whole nights: type safety prevents malformed output, not incorrect judgment. Jev cannot return an option outside your schema, and it can still pick the wrong valid one with confidence. a schema-valid mistake refunds the wrong customer just as fast. an LLM writes new language when the answer space is open. Jev evaluates known paths when the answer space is closed. below i have quoted my full breakdown on Jev. it covers the three primitives, the parallel battery, the thresholds, and where it does not belong. save this and read it below ↓

Hanako

42,632 просмотров • 7 дней назад

i genuinely don't understand why everyone isn't using this yet diogo almeida, one of the people behind chatgpt, spent two years in stealth and shipped this on monday. his own words about it: "jev is off the charts", the same frontier intelligence you're already paying for, "two orders of magnitude faster and more efficient" in normal words: jev is an ai that never writes anything. it only decides. yes or no, which pile does this go in, how good is it. one answer per item, under half a second each, with a number for how sure it is. it isn't writing anything, so it can't make anything up so you stop feeding chatgpt one thing at a time and hand jev the whole pile. 400 unread emails into reply today, later, never. 300 comments into questions, complaints, praise. 200 job posts into worth it and not. a competitor's entire ad library into what's actually working. the whole pile, in seconds, for cents full guide: > join the waitlist on people are approved the same day > open the dashboard and create an api key > tell claude or your agent: install the typesafe skill > paste your pile and name the buckets you want it sorted into > it hands everything back labelled, with a confidence number on each one no code, nothing to learn. someone ran 1,891 ads through it in 19 seconds for 12 cents, and it's free on vercel's gateway right now five minutes to set up, and the sorting job that used to eat your evening is done before you stand up full step-by-step guide, link below bookmark this
0:30

i genuinely don't understand why everyone isn't using this yet diogo almeida, one of the people behind chatgpt, spent two years in stealth and shipped this on monday. his own words about it: "jev is off the charts", the same frontier intelligence you're already paying for, "two orders of magnitude faster and more efficient" in normal words: jev is an ai that never writes anything. it only decides. yes or no, which pile does this go in, how good is it. one answer per item, under half a second each, with a number for how sure it is. it isn't writing anything, so it can't make anything up so you stop feeding chatgpt one thing at a time and hand jev the whole pile. 400 unread emails into reply today, later, never. 300 comments into questions, complaints, praise. 200 job posts into worth it and not. a competitor's entire ad library into what's actually working. the whole pile, in seconds, for cents full guide: > join the waitlist on people are approved the same day > open the dashboard and create an api key > tell claude or your agent: install the typesafe skill > paste your pile and name the buckets you want it sorted into > it hands everything back labelled, with a confidence number on each one no code, nothing to learn. someone ran 1,891 ads through it in 19 seconds for 12 cents, and it's free on vercel's gateway right now five minutes to set up, and the sorting job that used to eat your evening is done before you stand up full step-by-step guide, link below bookmark this

Argona

32,058 просмотров • 8 дней назад

I'M F*CKING LOSING MY MIND OVER OPUS 5.5 × JEV ON BUZZCORE it turned $67 into $16,798 in one f*cking night across i said one sentence and walked away from my computer for 24 hours spoiler: i didn't touch my mouse or keyboard for those 24 hours NOT ONCE MOTHERF*CKER here's what i said: if you dont make me enough in the next 24 hours to move the desk out of my kitchen into a real f*cking office, i'll shut you down the second the clock hits 24:00 at 22:00 i saw $16,798 and spent the next hour and a half reading the logs from the beginning. every single entry like going through my girlfriend's messages after she said "we're just friends" 00:00. TOMMY opened the seat and the family clocked in 00:11. ARTHUR started scanning the market, CHARLIE ran the noise filter, FINN watched momentum 00:34. first candidate came up, JEV router asked the four narrow questions, Opus wrote the profile in one pass already feeling uncomfortable i usually pick whichever ticker has the funniest name and whichever KOL said "send it" with the most confidence 02:48. first position closed, ISAIAH recalculates the size of the next one doesn't go all in. doesn't celebrate. keeps going 06:23. second candidate. CURLY held it in review. JEV kicked the shared-history check back as insufficient. no fill. no report. no further stages CURLY. no fill. the piece of software that watches my money literally said no to a trade i've never said no to a trade in my life 10:36. Opus closes the rest of a position and doesn't buy back in, even though the price is still ticking up personally, this is where i'd take the chart personally and buy back higher out of spite BUZZCORE just sat there 15:10. checks the next opportunity, passes, keeps looking no fatigue. no urge to make back money from the previous trade. no "one last trade then bed" that somehow ends at lunchtime 22:00. i get back to my computer on the screen is the amount i jokingly put a piece of software through a death quest for last night CONTEXT → JEV ROUTER → OPUS 5.5 → SEALED. that's the whole pipeline. four boxes. one veto that never got overruled 24 hours earlier i had $67 and some very specific complaints about the cost of living now i've got office listings and trade history open the listings i understand the trade history i'm still f*cking processing below is the article about BUZZCORE, the desk OPUS 5.5 and JEV were running on today
0:30

I'M F*CKING LOSING MY MIND OVER OPUS 5.5 × JEV ON BUZZCORE it turned $67 into $16,798 in one f*cking night across i said one sentence and walked away from my computer for 24 hours spoiler: i didn't touch my mouse or keyboard for those 24 hours NOT ONCE MOTHERF*CKER here's what i said: if you dont make me enough in the next 24 hours to move the desk out of my kitchen into a real f*cking office, i'll shut you down the second the clock hits 24:00 at 22:00 i saw $16,798 and spent the next hour and a half reading the logs from the beginning. every single entry like going through my girlfriend's messages after she said "we're just friends" 00:00. TOMMY opened the seat and the family clocked in 00:11. ARTHUR started scanning the market, CHARLIE ran the noise filter, FINN watched momentum 00:34. first candidate came up, JEV router asked the four narrow questions, Opus wrote the profile in one pass already feeling uncomfortable i usually pick whichever ticker has the funniest name and whichever KOL said "send it" with the most confidence 02:48. first position closed, ISAIAH recalculates the size of the next one doesn't go all in. doesn't celebrate. keeps going 06:23. second candidate. CURLY held it in review. JEV kicked the shared-history check back as insufficient. no fill. no report. no further stages CURLY. no fill. the piece of software that watches my money literally said no to a trade i've never said no to a trade in my life 10:36. Opus closes the rest of a position and doesn't buy back in, even though the price is still ticking up personally, this is where i'd take the chart personally and buy back higher out of spite BUZZCORE just sat there 15:10. checks the next opportunity, passes, keeps looking no fatigue. no urge to make back money from the previous trade. no "one last trade then bed" that somehow ends at lunchtime 22:00. i get back to my computer on the screen is the amount i jokingly put a piece of software through a death quest for last night CONTEXT → JEV ROUTER → OPUS 5.5 → SEALED. that's the whole pipeline. four boxes. one veto that never got overruled 24 hours earlier i had $67 and some very specific complaints about the cost of living now i've got office listings and trade history open the listings i understand the trade history i'm still f*cking processing below is the article about BUZZCORE, the desk OPUS 5.5 and JEV were running on today

tim777

13,721 просмотров • 3 дней назад

For science, AI sovereignty and physics-grounded reasoning are non-negotiable. But how can we teach a small LLM like Gemma-4-E4B physics? One way is to use Agent Skills, but this has so far been limited to closed frontier models. mistral․rs now implements Agent Skills natively: the first self-hosted inference engine that does this as part of the local inference substrate, where we can use small models to solve complex scientific and other tasks in a flexible and scalable way. We are in a period of uncertainty about frontier models - access, pricing, deprecation, abrupt restriction. The good news is that when the entire stack runs locally we can build AI that is entirely your own: You own the weights, the skills, the execution loop, the data - all of it runs on your hardware and is reproducible and durable. While virtually all local inference engines expose a model behind an OpenAI-compatible endpoint, everything agentic is then assembled around it by an external orchestrator that injects context, manages tools, mounts files, and brokers execution. mistral․rs is natively agentic and moves that machinery into the server itself, allowing us to build complex agentic workflows and run them locally, on open-source models. With this new feature you can now upload Agent Skills bundles to /v1/skills, reference them from Responses API requests by identity, and run them inside a native agentic loop with persistent Python sessions, figure capture, sandboxed shell execution, file inputs mounted directly into the working session; plug-and-play and completely compatible with your existing code/workflow. A model with a native skill substrate can act, observe consequences, and can modify what it is able to do. The skill is retained procedural capability of the system. Attached is a short video of all of it: skills, code execution, the full agentic loop carried by Gemma-4-E4B; running entirely on my MacBook Pro. You can install and run a server with this capability in two lines in your terminal, with any quantization you need. Nice work by the Google Gemma team Logan Kilpatrick Demis Hassabis and Eric Buehler with mistral․rs!
1:08

For science, AI sovereignty and physics-grounded reasoning are non-negotiable. But how can we teach a small LLM like Gemma-4-E4B physics? One way is to use Agent Skills, but this has so far been limited to closed frontier models. mistral․rs now implements Agent Skills natively: the first self-hosted inference engine that does this as part of the local inference substrate, where we can use small models to solve complex scientific and other tasks in a flexible and scalable way. We are in a period of uncertainty about frontier models - access, pricing, deprecation, abrupt restriction. The good news is that when the entire stack runs locally we can build AI that is entirely your own: You own the weights, the skills, the execution loop, the data - all of it runs on your hardware and is reproducible and durable. While virtually all local inference engines expose a model behind an OpenAI-compatible endpoint, everything agentic is then assembled around it by an external orchestrator that injects context, manages tools, mounts files, and brokers execution. mistral․rs is natively agentic and moves that machinery into the server itself, allowing us to build complex agentic workflows and run them locally, on open-source models. With this new feature you can now upload Agent Skills bundles to /v1/skills, reference them from Responses API requests by identity, and run them inside a native agentic loop with persistent Python sessions, figure capture, sandboxed shell execution, file inputs mounted directly into the working session; plug-and-play and completely compatible with your existing code/workflow. A model with a native skill substrate can act, observe consequences, and can modify what it is able to do. The skill is retained procedural capability of the system. Attached is a short video of all of it: skills, code execution, the full agentic loop carried by Gemma-4-E4B; running entirely on my MacBook Pro. You can install and run a server with this capability in two lines in your terminal, with any quantization you need. Nice work by the Google Gemma team Logan Kilpatrick Demis Hassabis and Eric Buehler with mistral․rs!

Markus J. Buehler

10,229 просмотров • 3 месяцев назад

this is free f*cking gold a second brain article hit 8 million views, so the guy behind it put the entire setup in one place the repo, the guide, the tools, the learning path. all of it, free • the guide > 10 sections, 65 pages, concept through troubleshooting > 5 tracks on top, 44 pages, 15 of them build guides with code that runs • the machine (.claude/) > 18 agent skills, one per workflow > 72 slash commands - /ingest-pdf, /ingest-youtube, /ingest-voice, /backfill > 6 subagents - curator, linker, researcher, reviewer, ingestor, graph-analyst > 4 of them read only, so nothing rewrites your vault behind your back • the scripts (plain Python, zero dependencies) > graph export, link checker, vault stats, chat converter, site builder • the starter vault > its own CLAUDE.md with page contracts and linking rules > raw/ never edited after it lands, wiki/ is what the agent maintains > log.md - one line per run, so the whole thing stays auditable • 87 vetted resources > 28 tools, 26 Obsidian plugins, 15 repos, 12 skills, papers and articles five tracks to pick from: > knowledge graphs > Jev engineering > agent harnesses > loop engineering > eval engineering start with the second brain guide if you're new. go straight to the tracks if you already live in this stuff a consultant charges four figures to build you a research system. this one sits in a public repo under MIT ↳
0:24

this is free f*cking gold a second brain article hit 8 million views, so the guy behind it put the entire setup in one place the repo, the guide, the tools, the learning path. all of it, free • the guide > 10 sections, 65 pages, concept through troubleshooting > 5 tracks on top, 44 pages, 15 of them build guides with code that runs • the machine (.claude/) > 18 agent skills, one per workflow > 72 slash commands - /ingest-pdf, /ingest-youtube, /ingest-voice, /backfill > 6 subagents - curator, linker, researcher, reviewer, ingestor, graph-analyst > 4 of them read only, so nothing rewrites your vault behind your back • the scripts (plain Python, zero dependencies) > graph export, link checker, vault stats, chat converter, site builder • the starter vault > its own CLAUDE.md with page contracts and linking rules > raw/ never edited after it lands, wiki/ is what the agent maintains > log.md - one line per run, so the whole thing stays auditable • 87 vetted resources > 28 tools, 26 Obsidian plugins, 15 repos, 12 skills, papers and articles five tracks to pick from: > knowledge graphs > Jev engineering > agent harnesses > loop engineering > eval engineering start with the second brain guide if you're new. go straight to the tracks if you already live in this stuff a consultant charges four figures to build you a research system. this one sits in a public repo under MIT ↳

Annatar.md

193,376 просмотров • 3 дней назад

Introducing Workshop: cloud + on-device agentic AI. And to celebrate, we're giving away $250k in Google Gemini AI credits. (details below). The future of AI work is neither cloud-based nor local. It's both. In Workshop Cloud, you can use agents powered by frontier models like Claude and/or open source models like Z.ai's GLM-5 to build internal tools, dashboards, and AI web apps. Or, breeze through tasks like managing your Google and Meta Ads. In Workshop Desktop, you can do all the same right on your computer, plus make desktop apps, mobile apps, and 3D creations. Our favorite part? You can power the full agent experience with local models like Qwen 3.5 family on your computer. Fully offline. 2026 is the year in which local models for agentic tasks will become viable for mainstream use. But the setup for tools like OpenClaw is like setting up Linux from scratch on your computer. Workshop Desktop is one-click to install on Windows, Mac, and Linux. It recommends which open source model you should use for your hardware and lets you download and run it right in the app. And its agent harness allows you to chat, create websites, build personal utilities, and analyze data. 100% offline. Or multitask with AI models in the cloud while running other agent threads locally. Start in Workshop Cloud when you want flexibility and speed. Download your project and continue in Workshop Desktop when you want local files, privacy, and/or better performance on large code bases. Publish from either. The agent tooling space is maturing and discerning users have come to expect a lot from their tools. We've packed Workshop with features to help you 10x your productivity. - Native support for skills - Autocompaction for seamless context management - Built-in AI for your apps - Dozens of connectors, like Google Drive, Big Query, and Supabase - dbt integration to ground your dashboards in your semantic layer - Native Github integration - Private app deployment - ... and more (+ we're shipping super fast) To access the free credit offer, RT this post and reply with "Workshop". Make sure you are following us so we can DM you the instructions to redeem. - First 100 to RT + comment get $500 in credits. - Everyone else gets up to $250 And thanks to our partners Modal, Google Gemini, and Z.ai!
3:50

Introducing Workshop: cloud + on-device agentic AI. And to celebrate, we're giving away $250k in Google Gemini AI credits. (details below). The future of AI work is neither cloud-based nor local. It's both. In Workshop Cloud, you can use agents powered by frontier models like Claude and/or open source models like Z.ai's GLM-5 to build internal tools, dashboards, and AI web apps. Or, breeze through tasks like managing your Google and Meta Ads. In Workshop Desktop, you can do all the same right on your computer, plus make desktop apps, mobile apps, and 3D creations. Our favorite part? You can power the full agent experience with local models like Qwen 3.5 family on your computer. Fully offline. 2026 is the year in which local models for agentic tasks will become viable for mainstream use. But the setup for tools like OpenClaw is like setting up Linux from scratch on your computer. Workshop Desktop is one-click to install on Windows, Mac, and Linux. It recommends which open source model you should use for your hardware and lets you download and run it right in the app. And its agent harness allows you to chat, create websites, build personal utilities, and analyze data. 100% offline. Or multitask with AI models in the cloud while running other agent threads locally. Start in Workshop Cloud when you want flexibility and speed. Download your project and continue in Workshop Desktop when you want local files, privacy, and/or better performance on large code bases. Publish from either. The agent tooling space is maturing and discerning users have come to expect a lot from their tools. We've packed Workshop with features to help you 10x your productivity. - Native support for skills - Autocompaction for seamless context management - Built-in AI for your apps - Dozens of connectors, like Google Drive, Big Query, and Supabase - dbt integration to ground your dashboards in your semantic layer - Native Github integration - Private app deployment - ... and more (+ we're shipping super fast) To access the free credit offer, RT this post and reply with "Workshop". Make sure you are following us so we can DM you the instructions to redeem. - First 100 to RT + comment get $500 in credits. - Everyone else gets up to $250 And thanks to our partners Modal, Google Gemini, and Z.ai!

Workshop AI

29,445 просмотров • 6 месяцев назад