Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

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 ↓ ↓show more

rody

3,618 subscribers

199,858 görüntüleme • 7 gün önce •via X (Twitter)

Bilim & Teknoloji

Anya Rossi• Live Now

Private livecam show

17 Yorum

Brian Hadu profil fotoğrafı

Brian Hadu6 gün önce

what’s the biggest takeaway from using the jev-ultrafast agent?

Tony Tong | Founder | Ancient Systems x AI profil fotoğrafı

Tony Tong | Founder | Ancient Systems x AI6 gün önce

That checklist is really an argument about orchestration, not intelligence. Model releases keep landing with barely a bump lately, what actually shifted my output was the layer of agents around it, checking each other, routing tasks, picking when a smaller model is enough.

LJ-GAMES profil fotoğrafı

LJ-GAMES6 gün önce

저장

Aditya 🍻 profil fotoğrafı

Aditya 🍻6 gün önce

Which of these patterns has held up best once the workflow gets long and stateful?

COSMOS profil fotoğrafı

COSMOS6 gün önce

ref jv

Cuth profil fotoğrafı

Cuth6 gün önce

Try this out

AI Mastery Guide profil fotoğrafı

AI Mastery Guide6 gün önce

saving this checklist

Gursers profil fotoğrafı

Gursers6 gün önce

@heyjevbook Anything in this list you could benefit from?

Myttle profil fotoğrafı

Myttle7 gün önce

alpha complitation

stunspot | ⟨🤩⨯📍⟩ | profil fotoğrafı

stunspot | ⟨🤩⨯📍⟩ |6 gün önce

@novaoptimalAI Take a look at all those. Any of these worth grabbing or ripping off for our designs?

Ohad Krispin profil fotoğrafı

Ohad Krispin6 gün önce

Worth knowing before you wire these into a loop: the constraint is rate limits, not cost. Over 700 evaluations cost me about two tenths of a cent. But sustained throughput sat near 8 seconds an item, so a 226 item run took a quarter of an hour. Budget time, not money.

Brjan | AI Builder profil fotoğrafı

Brjan | AI Builder6 gün önce

the checklist looks handy for those just starting with the Jev API

catman profil fotoğrafı

catman7 gün önce

Think of Jev as a routing layer around the agent: it filters context, chooses actions, and escalates only the ambiguous parts to a larger model.

Dassi AI profil fotoğrafı

Dassi AI6 gün önce

Splitting discrete action picking from text generation is the biggest latency unlock for browser loops. Having a fast model pick element refs via CDP and only spinning up an LLM when generative text is actually needed cuts out ~80% of roundtrip lag.

Ros profil fotoğrafı

Ros7 gün önce

The interesting bit is how narrow the agent's judgment surface is here: choose the action, not the whole plan. That makes failure traces much easier to inspect. What are you using as the boundary between routing and execution?

magsimich profil fotoğrafı

magsimich6 gün önce

Jev has some really useful setups

Steve Darlow profil fotoğrafı

Steve Darlow6 gün önce

Don’t forget this one!

Benzer Videolar

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👇

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 görüntüleme • 5 gün önce

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 London flights in ~7s > awlevin/typesafe-computer-use (~978): macOS computer use, OCR reads the screen, Jev picks the next click local decision models > jaredpalmer/kev (~7.1k): Jev-like models on Qwen, same /v1/systemone wire format > mizorewww/laya-mlx (~6.4k): Laya, the main open Jev-style engine, running on Apple silicon > TheoLeeCJ/SemIf-OpenJev (~4.3k): local semantic ifs from frozen open models, not a TypeSafe project > contrastive-lm/clm (~1.3k): open System One model with a Choice / Noul / Score API > vinnylarouge/jevlike (~1.3k): community trainer and tooling for your own Jev-like model context + skills > tamaratran/fast-jev-compaction (~6.9k): Claude Code plugin, Jev keeps, drops or truncates tool results instead of summarizing context > typesafe-ai/skills (~2.2k): official TypeSafe skill for Claude Code and Codex trading > jarrodwatts/jev-trader (~2.4k): one Jev buy/sell decision per Monad block catalogs > yibie/awesome-jev (~1.7k): the biggest map of Jev projects and discussions > Anil-matcha/awesome-jev-by-typesafe (~851): use cases, patterns and starter code start with jev-ultrafast

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 London flights in ~7s > awlevin/typesafe-computer-use (~978): macOS computer use, OCR reads the screen, Jev picks the next click local decision models > jaredpalmer/kev (~7.1k): Jev-like models on Qwen, same /v1/systemone wire format > mizorewww/laya-mlx (~6.4k): Laya, the main open Jev-style engine, running on Apple silicon > TheoLeeCJ/SemIf-OpenJev (~4.3k): local semantic ifs from frozen open models, not a TypeSafe project > contrastive-lm/clm (~1.3k): open System One model with a Choice / Noul / Score API > vinnylarouge/jevlike (~1.3k): community trainer and tooling for your own Jev-like model context + skills > tamaratran/fast-jev-compaction (~6.9k): Claude Code plugin, Jev keeps, drops or truncates tool results instead of summarizing context > typesafe-ai/skills (~2.2k): official TypeSafe skill for Claude Code and Codex trading > jarrodwatts/jev-trader (~2.4k): one Jev buy/sell decision per Monad block catalogs > yibie/awesome-jev (~1.7k): the biggest map of Jev projects and discussions > Anil-matcha/awesome-jev-by-typesafe (~851): use cases, patterns and starter code start with jev-ultrafast

NO1ennn

36,083 görüntüleme • 2 gün önce

Jev Founder, Diogo Almeida (ex-OpenAI): "The next era is not the Claude Code era. Claude Code is still part of the assistance era - Jev is the next step Jev is x200 faster, x400 cheaper and has 0 hallucination. This is what comes after RLHF" In 17 minutes he explains why every model you use has a human-shaped flaw baked into it and why Jev is better worth more than a $500 Claude Code engineering course watch today, then read how to actually boost yourself x100 with Jev in the post below

Jev Founder, Diogo Almeida (ex-OpenAI): "The next era is not the Claude Code era. Claude Code is still part of the assistance era - Jev is the next step Jev is x200 faster, x400 cheaper and has 0 hallucination. This is what comes after RLHF" In 17 minutes he explains why every model you use has a human-shaped flaw baked into it and why Jev is better worth more than a $500 Claude Code engineering course watch today, then read how to actually boost yourself x100 with Jev in the post below

Codez

191,889 görüntüleme • 10 gün önce

10 Jev use cases a marketer can see: 1. Lead scoring - You get 100 new leads overnight. Jev can score which ones are most likely to buy. Sales gets the best ones first. 2. Email prioritization - Drop hundreds of emails into it. Jev can score priority, spam, category, and reply probability. 3. Support routing - A client reports a billing issue, another one has an API problem. Jev can instantly decide where each ticket should go. 4. Customer intent - A user visits pricing three times this week. Jev can score how likely they are to upgrade. 5. Marketplace matching - Someone explains exactly what service they need. Jev can score which provider is the closest match. 6. Lead qualification - A prospect fills out your website form. Jev can decide between sales, self-serve, or nurture. 7. Content clipping- Give it a 60-minute podcast transcript. Jev can score the moments most worth clipping. 8. Browser tasks - Tell an agent to find the right hotel. Jev can help choose the best one in 8 seconds. 9. Human vs AI routing - Jev can decide whether it goes to AI or a human. 10. Workflow decisions - Most workflows eventually hit the same question: What should happen next? That's probably the best place to use Jev.

10 Jev use cases a marketer can see: 1. Lead scoring - You get 100 new leads overnight. Jev can score which ones are most likely to buy. Sales gets the best ones first. 2. Email prioritization - Drop hundreds of emails into it. Jev can score priority, spam, category, and reply probability. 3. Support routing - A client reports a billing issue, another one has an API problem. Jev can instantly decide where each ticket should go. 4. Customer intent - A user visits pricing three times this week. Jev can score how likely they are to upgrade. 5. Marketplace matching - Someone explains exactly what service they need. Jev can score which provider is the closest match. 6. Lead qualification - A prospect fills out your website form. Jev can decide between sales, self-serve, or nurture. 7. Content clipping- Give it a 60-minute podcast transcript. Jev can score the moments most worth clipping. 8. Browser tasks - Tell an agent to find the right hotel. Jev can help choose the best one in 8 seconds. 9. Human vs AI routing - Jev can decide whether it goes to AI or a human. 10. Workflow decisions - Most workflows eventually hit the same question: What should happen next? That's probably the best place to use Jev.

Yum⋆₊˚

130,108 görüntüleme • 9 gün önce

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.

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 görüntüleme • 7 gün önce

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

76,756 görüntüleme • 6 gün önce

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.

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 görüntüleme • 9 gün önce

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.

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

288,967 görüntüleme • 7 gün önce

Finally, an OpenRouter for agent harnesses! (including System One by Jev) Devs just open-sourced a plug-and-play infrastructure layer that lets you run any harness under a single interface, like: - Codex - Hermes - Claude code - DeepSeek Harness - System One, powered by Jev - And 9 more agent harnesses This means you can bring Jev into the same product that already uses Codex, Claude Code, or another supported harness, without writing another implementation for sessions, streaming, files, cancellation, and failure handling. Here's the repo: (don't forget to star it ⭐ ) The harnesses run locally, and the Unified Harness Protocol (UHP) defines the common task interface with an OpenAI Responses-compatible API. If you want to dive deeper, my recent article explains why model routing is not the same as harness routing, and what it takes to support multiple harnesses. It also covers UHP, the full local setup, a working API call, and how sessions and files work. Read it below.

Finally, an OpenRouter for agent harnesses! (including System One by Jev) Devs just open-sourced a plug-and-play infrastructure layer that lets you run any harness under a single interface, like: - Codex - Hermes - Claude code - DeepSeek Harness - System One, powered by Jev - And 9 more agent harnesses This means you can bring Jev into the same product that already uses Codex, Claude Code, or another supported harness, without writing another implementation for sessions, streaming, files, cancellation, and failure handling. Here's the repo: (don't forget to star it ⭐ ) The harnesses run locally, and the Unified Harness Protocol (UHP) defines the common task interface with an OpenAI Responses-compatible API. If you want to dive deeper, my recent article explains why model routing is not the same as harness routing, and what it takes to support multiple harnesses. It also covers UHP, the full local setup, a working API call, and how sessions and files work. Read it below.

Akshay 🚀

355,021 görüntüleme • 7 gün önce

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.

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 görüntüleme • 5 gün önce

Jev founder, Diogo Almeida, just put out a PDF on building a Jev harness for coding agents the claim: 200x faster, 400x cheaper the model stopped being the bottleneck a while ago. the harness around it is where the cost and the speed actually live five decisions sit on every loop, and only one of them writes code hand this PDF and the article below to your Claude Code or Codex instance and let it rebuild its own setup your agent gets a better harness tonight, and monday looks different than it would have 👇

Jev founder, Diogo Almeida, just put out a PDF on building a Jev harness for coding agents the claim: 200x faster, 400x cheaper the model stopped being the bottleneck a while ago. the harness around it is where the cost and the speed actually live five decisions sit on every loop, and only one of them writes code hand this PDF and the article below to your Claude Code or Codex instance and let it rebuild its own setup your agent gets a better harness tonight, and monday looks different than it would have 👇

Hanako

37,887 görüntüleme • 4 gün önce

i finally mastered how to maximise my opus 5.5 usage limits... the trick: let jev choose which subagent gets each task and how much effort it should use. [here’s how i’d wire it:] claude breaks the project into tasks. jev selects from predefined worker profiles. claude applies the selected settings and dispatches the work. → main session, medium: clarify the requirements, define what “done” looks like, and prepare the tasks → builder, low: small, clearly defined tasks with existing examples or patterns → builder, medium: tasks that connect multiple parts or need decisions within the approved plan → verifier, high: check requirements, probe edge cases, and report problems for the builder to fix jev gets the task’s scope, what’s uncertain, and the consequences of failure. it chooses from the profiles allowed for that task. your approval checkpoints stay in place. paste this into your next planning session: “use opus 5.5 with jev selecting the worker and effort profile for each task. first, check that a working jev integration is available and that this environment supports separate effort settings for subagents. check for configuration or environment overrides that could prevent those settings from taking effect. if anything is missing, explain what needs wiring before proceeding. break my request into tasks with clear ownership, dependencies, relevant context, and acceptance checks. keep small related tasks together when a separate subagent would add unnecessary overhead. keep the main session at medium effort. offer jev these worker profiles: builder at low effort for small, clearly defined tasks using existing patterns; builder at medium effort for tasks that connect multiple parts or require decisions within the approved plan; verifier at high effort for checking requirements and edge cases. give jev each task’s scope, uncertainties, dependencies, and consequences of failure. only offer profiles appropriate to the current stage. validate its selection before dispatching. use the actual jev integration; don’t simulate its decisions. if it abstains or returns an invalid choice, stop that handoff and ask me. show me the task plan and proposed assignments before starting. after approval, launch the selected workers with their assigned effort settings, relevant context, file ownership, and completion checks. let me review the result before verification. the verifier may add tests but must leave implementation code unchanged. have it report what passed, what failed, and what remains uncertain. send implementation fixes back to the builder, then recheck the affected parts. if a task repeatedly fails, examine the requirements and approach before increasing effort. report available total usage, including jev calls, worker calls, retries, and verification. don’t invent missing data. compare similar completed tasks before claiming savings.” steal this 👇

Avid

31,355 görüntüleme • 2 gün önce

I just built a Jev X Viral Post Analyser. 100,000 viral X posts. 20.4 seconds. $0.67. Claude Opus 5, same corpus, same clock, got through 214 posts and spent $0.98. per post that is ~680x cheaper the full Opus pass would have run $458. viral analysis is the perfect Jev job. • it is not writing, it is 14 yes/no calls per post: > does the hook open a loop, > is there a number in the first line, > is the proof real or claimed. classification, not prose. • what it found: 1,220 posts broke into the top 1%. baseline 1.22%. > superlative claim - 2.34% viral. 1.92x baseline > contrarian take - 1.59%. 1.31x > launch / tool drop - 1.46%. 1.19x and numbered lists, the thing everyone writes: 0.55%. below baseline. the most used hook is the least viral one. full stop. • what you are watching: left is the post under analysis, right is Jev answering 14 typed questions about it, each with a confidence score. the run stops at 20.4s because that is when Jev finished all 100k. pulled the corpus through a few X APIs, one parallel pass into Jev. should I drop it to public? Read my latest article on Jev Engineering below and turn your ideas into reality.

I just built a Jev X Viral Post Analyser. 100,000 viral X posts. 20.4 seconds. $0.67. Claude Opus 5, same corpus, same clock, got through 214 posts and spent $0.98. per post that is ~680x cheaper the full Opus pass would have run $458. viral analysis is the perfect Jev job. • it is not writing, it is 14 yes/no calls per post: > does the hook open a loop, > is there a number in the first line, > is the proof real or claimed. classification, not prose. • what it found: 1,220 posts broke into the top 1%. baseline 1.22%. > superlative claim - 2.34% viral. 1.92x baseline > contrarian take - 1.59%. 1.31x > launch / tool drop - 1.46%. 1.19x and numbered lists, the thing everyone writes: 0.55%. below baseline. the most used hook is the least viral one. full stop. • what you are watching: left is the post under analysis, right is Jev answering 14 typed questions about it, each with a confidence score. the run stops at 20.4s because that is when Jev finished all 100k. pulled the corpus through a few X APIs, one parallel pass into Jev. should I drop it to public? Read my latest article on Jev Engineering below and turn your ideas into reality.

Movez

82,397 görüntüleme • 9 gün önce

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 ↓

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 görüntüleme • 5 gün önce

Jev is WILD for SEO audit 🤯 in 45.1 seconds it read all 586 pages on my site and rebuilt the internal link map. 584 links placed, 139 pages it refused to link because nothing honestly fit. total cost $0.21. Claude Opus 5, same 586 pages, same clock, got through 21 of them and spent $1.43. per page that is ~190x cheaper. the full Opus pass would have run $43. internal linking is the perfect Jev job. it is not writing, it is 8,790 yes/no calls: does this page have a real reason to link to that one, and is there anchor text already sitting in the copy. that is a classification problem, and we have been paying frontier prices to do it one page at a time. what you are watching: left column is Jev, right is Opus, same queue, same rubric. the run stops the moment Jev finishes so Opus stops burning tokens. coming soon to Distribb + connector + gpt plugin

Jev is WILD for SEO audit 🤯 in 45.1 seconds it read all 586 pages on my site and rebuilt the internal link map. 584 links placed, 139 pages it refused to link because nothing honestly fit. total cost $0.21. Claude Opus 5, same 586 pages, same clock, got through 21 of them and spent $1.43. per page that is ~190x cheaper. the full Opus pass would have run $43. internal linking is the perfect Jev job. it is not writing, it is 8,790 yes/no calls: does this page have a real reason to link to that one, and is there anchor text already sitting in the copy. that is a classification problem, and we have been paying frontier prices to do it one page at a time. what you are watching: left column is Jev, right is Opus, same queue, same rubric. the run stops the moment Jev finishes so Opus stops burning tokens. coming soon to Distribb + connector + gpt plugin

borja

832,795 görüntüleme • 10 gün önce

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:

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

169,700 görüntüleme • 8 gün önce

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.

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 görüntüleme • 10 gün önce

I gave JEV one prompt: "turn $24.80 into 1000x or I'm pulling the plug" it didn't ask questions. didn't negotiate. didn't say "that's unrealistic" it just started $24.80 to $31,847.52 overnight I woke up, opened Meridian Desk, and the number was already there. green, pulsing, real here's the part nobody talks about: I didn't mass-trade, didn't watch charts at 3am, didn't mass-subscribe to signal groups I built a terminal called Meridian Desk and let Jev run it while I slept Jev is the brain. it doesn't trade, it thinks it reads the entire market state every few seconds and outputs one structured decision: buy, copy, skip, or pass, each one tagged with a confidence score below Jev sit four agents that do the actual work: SCOUT finds fresh mints before anyone's even talking about them LEDGER tracks smart wallets and mirrors the ones with 90%+ win rates PULSE reads momentum and social sentiment in real time FLUX maps liquidity routes so every fill gets the best execution then there's WARDEN, the fifth agent, the last gate every decision Jev makes has to pass through WARDEN before a single dollar moves. it checks for honeypots, arms stop-losses, sizes the position, and vetoes anything that smells off if WARDEN says no, nothing happens. period at hour two the balance dropped to $7 Jev went quiet. stopped entering. WARDEN was blocking everything. confidence too low, liquidity too thin, signals disagreed it waited then around hour four something shifted. SCOUT flagged a mint nobody had seen yet, LEDGER confirmed three smart wallets were already in, PULSE showed social mentions climbing, FLUX found a clean route with under 2% slippage Jev lit up: BUY, conf 0.91 WARDEN cleared it. position filled in 1.6 milliseconds that was the first real trade. the balance went from $7 to $40 in minutes after that it just kept compounding. trade after trade, all night, no human input 96.4% copy accuracy. five agents running in sync. one decision engine calling the shots I got early access to JEV. that's it. manual research trying to do what Jev does in seconds? $5,000 a month minimum, and you'd still miss the window this isn't a bot that sprays trades and hopes. this is an architecture. intelligence layer on top, execution layer below, risk gate in between Jev analyzes. agents execute. WARDEN protects I haven't touched it since I hit start bookmark this. follow me if you want to see the terminal live

I gave JEV one prompt: "turn $24.80 into 1000x or I'm pulling the plug" it didn't ask questions. didn't negotiate. didn't say "that's unrealistic" it just started $24.80 to $31,847.52 overnight I woke up, opened Meridian Desk, and the number was already there. green, pulsing, real here's the part nobody talks about: I didn't mass-trade, didn't watch charts at 3am, didn't mass-subscribe to signal groups I built a terminal called Meridian Desk and let Jev run it while I slept Jev is the brain. it doesn't trade, it thinks it reads the entire market state every few seconds and outputs one structured decision: buy, copy, skip, or pass, each one tagged with a confidence score below Jev sit four agents that do the actual work: SCOUT finds fresh mints before anyone's even talking about them LEDGER tracks smart wallets and mirrors the ones with 90%+ win rates PULSE reads momentum and social sentiment in real time FLUX maps liquidity routes so every fill gets the best execution then there's WARDEN, the fifth agent, the last gate every decision Jev makes has to pass through WARDEN before a single dollar moves. it checks for honeypots, arms stop-losses, sizes the position, and vetoes anything that smells off if WARDEN says no, nothing happens. period at hour two the balance dropped to $7 Jev went quiet. stopped entering. WARDEN was blocking everything. confidence too low, liquidity too thin, signals disagreed it waited then around hour four something shifted. SCOUT flagged a mint nobody had seen yet, LEDGER confirmed three smart wallets were already in, PULSE showed social mentions climbing, FLUX found a clean route with under 2% slippage Jev lit up: BUY, conf 0.91 WARDEN cleared it. position filled in 1.6 milliseconds that was the first real trade. the balance went from $7 to $40 in minutes after that it just kept compounding. trade after trade, all night, no human input 96.4% copy accuracy. five agents running in sync. one decision engine calling the shots I got early access to JEV. that's it. manual research trying to do what Jev does in seconds? $5,000 a month minimum, and you'd still miss the window this isn't a bot that sprays trades and hopes. this is an architecture. intelligence layer on top, execution layer below, risk gate in between Jev analyzes. agents execute. WARDEN protects I haven't touched it since I hit start bookmark this. follow me if you want to see the terminal live

cristal💎

263,431 görüntüleme • 6 gün önce

Corent’s brain uses TypeSafe AI Jev now. Not to generate the output, to make the decision before the output gets generated. When a request comes into Corent, you don’t need to tell us which model to use. You send the prompt, the workload and the quality level. Then Jev helps us decide what that request actually needs, how confident we are in that decision, and whether we should take the route or fall back to something safer. That matters because every request has different economics. A 2¢ image can tolerate more uncertainty. A $2 video clip cannot. Across 1000+ models, this changes how we route. We can set different confidence requirements depending on the workload, the cost and the quality expected. If the confidence is too low, we stop guessing. Routing was never really a text problem. It was a decision problem. Diogo Almeida and the team did a wonderful job with JEV Get your key at

Corent’s brain uses TypeSafe AI Jev now. Not to generate the output, to make the decision before the output gets generated. When a request comes into Corent, you don’t need to tell us which model to use. You send the prompt, the workload and the quality level. Then Jev helps us decide what that request actually needs, how confident we are in that decision, and whether we should take the route or fall back to something safer. That matters because every request has different economics. A 2¢ image can tolerate more uncertainty. A $2 video clip cannot. Across 1000+ models, this changes how we route. We can set different confidence requirements depending on the workload, the cost and the quality expected. If the confidence is too low, we stop guessing. Routing was never really a text problem. It was a decision problem. Diogo Almeida and the team did a wonderful job with JEV Get your key at

corent

109,541 görüntüleme • 10 gün önce

fun weekend project: AutoJev. i was curious to see if i could train a competitive Jev-like model completely autonomously with a swarm of agents using our internal system. turns out you can get quite far! some details: - gave the swarm a devbox with an h200 gpu - the swarm is a mix of astra and fable; used sol and luna for synthetic data and filtering; ran for 20 hours - spent $3.1k in total ($1.9k on agents, $1.2k on data) - used qwen3.8-27b as the backbone. it underperforms Jev initially, but after training it is competitive/better, and it also supports 260k context and multimodal input - the agents tried RL, but it hasn't worked out so far, so they fell back to SFT on high-quality synthetic data - both accuracy and calibration are better - jev-compatible api, playground, and inference. on an h200 it gets around 120ms p95. that will be higher under contention, but still quite fast for an unoptimized version code: model: going to let it run longer, and will also bring up inference so folks can try it out.

fun weekend project: AutoJev. i was curious to see if i could train a competitive Jev-like model completely autonomously with a swarm of agents using our internal system. turns out you can get quite far! some details: - gave the swarm a devbox with an h200 gpu - the swarm is a mix of astra and fable; used sol and luna for synthetic data and filtering; ran for 20 hours - spent $3.1k in total ($1.9k on agents, $1.2k on data) - used qwen3.8-27b as the backbone. it underperforms Jev initially, but after training it is competitive/better, and it also supports 260k context and multimodal input - the agents tried RL, but it hasn't worked out so far, so they fell back to SFT on high-quality synthetic data - both accuracy and calibration are better - jev-compatible api, playground, and inference. on an h200 it gets around 120ms p95. that will be higher under contention, but still quite fast for an unoptimized version code: model: going to let it run longer, and will also bring up inference so folks can try it out.

Denis Yarats

27,544 görüntüleme • 6 gün önce