正在加载视频...

视频加载失败

返回首页

We put jev in a claude code mod...

narsagna's profile picture

Nars

1,467 subscribers

18,011 次观看 • 9 天前 •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

20 条评论

Nars 的头像
Nars9 天前

Try for free:

Ronak 🦀 的头像
Ronak 🦀8 天前

Whoa I think that would be really interesting to see! 👀

Nars 的头像
Nars8 天前

Yeah it’s borderline addictive

Vundela Vamsi 的头像
Vundela Vamsi8 天前

@narsagna What if Claude Code itself is doing this step?

Nars 的头像
Nars8 天前

This works across your harnesses

Nachilos 的头像
Nachilos8 天前

I can see Claude skipping reasoning because of this, then making a mistake, and being like... 😂

Mahavir Agarwal 的头像
Mahavir Agarwal9 天前

benchmarks?

Nars 的头像
Nars8 天前

93% on longmemeval, still improving

Jason | Cesto 🧺 的头像
Jason | Cesto 🧺8 天前

Love to see it

psd369 的头像
psd3699 天前

I love this great idea brother keep it up I just started using this, I had made a plugin for this exact problem but I guess I don’t need that anymorree great stuffff

Nars 的头像
Nars9 天前

yess glad you're finding it useful

Akash Pavan / Chasi 的头像
Akash Pavan / Chasi8 天前

pretty cool!

Kamran 的头像
Kamran9 天前

Ok, but how’d use jev?

Nars 的头像
Nars9 天前

it makes a bunch of decisions based on each prompt - does this need referencing old sessions, which messages to pick etc, that what make this a just-in-time memory

Kamran 的头像
Kamran8 天前

Cool! But if u parse in all of the message convos at once won’t it be too much of input tok and hence price incr?

Nars 的头像
Nars8 天前

yeah which is why jev is very effective here

BreezeOg 的头像
BreezeOg8 天前

jev in claude code 😭 love it

Nars 的头像
Nars8 天前

🤣

Parth Parekh 的头像
Parth Parekh8 天前

Have you checked whether it increased token consumption while reading session transcripts everytime or does it include in cache ?

Nars 的头像
Nars8 天前

Decreased, will include analytics soon

相关视频

Jev + Vercel Sandbox Mod in Claude Code This Mod spins up a sandbox on Vercel, while Jev classifies which commands should run inside the sandbox and which ones should run locally Install: npx claude-code-templates@latest --mod security/jev-vercel-sandbox Link: Mods are a great way to customize your Claude Code workflows and connect other platforms directly into the agent loop
0:31

Jev + Vercel Sandbox Mod in Claude Code This Mod spins up a sandbox on Vercel, while Jev classifies which commands should run inside the sandbox and which ones should run locally Install: npx claude-code-templates@latest --mod security/jev-vercel-sandbox Link: Mods are a great way to customize your Claude Code workflows and connect other platforms directly into the agent loop

Daniel San

16,889 次观看 • 24 天前

Introducing Jev Model Router for Claude Code This Claude Code Mod lets you use Jev through its direct TypeSafe AI API or Vercel AI Gateway With every request you send to Claude Code, Jev classifies the subagent model, main model (only at session start to avoid breaking the cache), and effort level Install it with one command: npx claude-code-templates@latest --mod productivity/jev-model-router Full Mod details:
0:25

Introducing Jev Model Router for Claude Code This Claude Code Mod lets you use Jev through its direct TypeSafe AI API or Vercel AI Gateway With every request you send to Claude Code, Jev classifies the subagent model, main model (only at session start to avoid breaking the cache), and effort level Install it with one command: npx claude-code-templates@latest --mod productivity/jev-model-router Full Mod details:

Daniel San

206,776 次观看 • 1 个月前

Launching Jev on Command Code for free today. Jev x Command Code is super interesting. You can only use Jev in headless mode or Provider API. Also open sourced a mod "cmd-mod-jev-nudge" Use Jev for free to keep your agent running as long as the there's more work to do.
5:06

Launching Jev on Command Code for free today. Jev x Command Code is super interesting. You can only use Jev in headless mode or Provider API. Also open sourced a mod "cmd-mod-jev-nudge" Use Jev for free to keep your agent running as long as the there's more work to do.

Ahmad Awais

34,780 次观看 • 1 个月前

Introducing Jev Skill Suggestion for Claude Code Now you can keep your skills completely out of the context window until they’re actually needed Set your skills as user invocable only, and the Mod sends the available skill list to Jev For every request, Jev classifies which skill best matches the task, then injects only that skill into Claude’s context Works with both the TypeSafe AI API and Vercel AI Gateway Install it with one command: npx claude-code-templates@latest --mod productivity/jev-skill-suggestion Full implementation details on the Mod page at
0:34

Introducing Jev Skill Suggestion for Claude Code Now you can keep your skills completely out of the context window until they’re actually needed Set your skills as user invocable only, and the Mod sends the available skill list to Jev For every request, Jev classifies which skill best matches the task, then injects only that skill into Claude’s context Works with both the TypeSafe AI API and Vercel AI Gateway Install it with one command: npx claude-code-templates@latest --mod productivity/jev-skill-suggestion Full implementation details on the Mod page at

Daniel San

81,381 次观看 • 1 个月前

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
17:33

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

193,792 次观看 • 1 个月前

This is absolutely f*cking insane. A Stanford AI research group joints JEV with Claude Code to sort 100+ billion data points every 15 minutes. the trick is stupidly simple: JEV runs a cheap first pass on everything. Claude only gets the hard cases. so instead of: everything -> Claude -> $$$ it’s: everything -> JEV filters -> hard stuff -> Claude thinks the boring stuff never touches the expensive model. Claude gets a tiny pile that actually deserves deeper analysis. faster. cheaper. way less compute burned. basically, JEV sorts the mail so the genius only opens what matters. LLMs think. JEV decides. code does.
0:32

This is absolutely f*cking insane. A Stanford AI research group joints JEV with Claude Code to sort 100+ billion data points every 15 minutes. the trick is stupidly simple: JEV runs a cheap first pass on everything. Claude only gets the hard cases. so instead of: everything -> Claude -> $$$ it’s: everything -> JEV filters -> hard stuff -> Claude thinks the boring stuff never touches the expensive model. Claude gets a tiny pile that actually deserves deeper analysis. faster. cheaper. way less compute burned. basically, JEV sorts the mail so the genius only opens what matters. LLMs think. JEV decides. code does.

kiosa

116,185 次观看 • 29 天前

This is absolutely insane. A Stanford AI research group joints JEV with Claude Code to sort 100+ billion data points every 15 minutes. the trick is stupidly simple: JEV runs a cheap first pass on everything. Claude only gets the hard cases. so instead of: everything -> Claude -> $$$ it’s: everything -> JEV filters -> hard stuff -> Claude thinks the boring stuff never touches the expensive model. Claude gets a tiny pile that actually deserves deeper analysis. faster. cheaper. way less compute burned. basically, JEV sorts the mail so the genius only opens what matters. LLMs think, JEV decides Read the full Jev setup guide in the article below:
0:24

This is absolutely insane. A Stanford AI research group joints JEV with Claude Code to sort 100+ billion data points every 15 minutes. the trick is stupidly simple: JEV runs a cheap first pass on everything. Claude only gets the hard cases. so instead of: everything -> Claude -> $$$ it’s: everything -> JEV filters -> hard stuff -> Claude thinks the boring stuff never touches the expensive model. Claude gets a tiny pile that actually deserves deeper analysis. faster. cheaper. way less compute burned. basically, JEV sorts the mail so the genius only opens what matters. LLMs think, JEV decides Read the full Jev setup guide in the article below:

rody

114,820 次观看 • 28 天前

You can mod Claude Code now, so I did the obvious
0:27

You can mod Claude Code now, so I did the obvious

Adam Holter

32,591 次观看 • 23 天前

We’ve been building this in secret for a while. We love Claude Code, and we’ve reimplemented “Claude Code” in Genspark. Introducing Genspark AI Developer - “Claude Code” in the browser - “Claude Code” on mobile - Everyone can build, no coding experience required - Supports multiple frontier models: Claude Sonnet 4, Claude Opus 4.1, GPT‑5, Kimi + Groq 1/4
3:24

We’ve been building this in secret for a while. We love Claude Code, and we’ve reimplemented “Claude Code” in Genspark. Introducing Genspark AI Developer - “Claude Code” in the browser - “Claude Code” on mobile - Everyone can build, no coding experience required - Supports multiple frontier models: Claude Sonnet 4, Claude Opus 4.1, GPT‑5, Kimi + Groq 1/4

Eric Jing

23,246,376 次观看 • 1 年前

A conversation with cat on: - some tips for using Claude Code - how we prototype new features - customizing Claude Code - how we think about the Claude Code SDK and agents
14:03

A conversation with cat on: - some tips for using Claude Code - how we prototype new features - customizing Claude Code - how we think about the Claude Code SDK and agents

Alex Albert

147,262 次观看 • 1 年前

I created a course to learn Claude Code in Claude Code.
0:36

I created a course to learn Claude Code in Claude Code.

Delba

110,891 次观看 • 8 个月前

15 MINUTES OF JEV REPOS THAT WILL INCREASE YOUR CLAUDE CODE PRODUCTIVITY FEED THIS TRANSCRIPT TO YOUR AGENTS
15:33

15 MINUTES OF JEV REPOS THAT WILL INCREASE YOUR CLAUDE CODE PRODUCTIVITY FEED THIS TRANSCRIPT TO YOUR AGENTS

0xMarioNawfal

56,187 次观看 • 25 天前

Stop using your most expensive model for every decision. In our Minesweeper experiment (open-source code below), JEV crushed every other model we tested on speed and cost. JEV: 8s / ~$0.003 Fable 5.1: 100s / ~$2.41 Astra: 128s / ~$8.75 Grok 4.6: 158s / ~$0.55 Where would you put JEV to work in your company?
0:28

Stop using your most expensive model for every decision. In our Minesweeper experiment (open-source code below), JEV crushed every other model we tested on speed and cost. JEV: 8s / ~$0.003 Fable 5.1: 100s / ~$2.41 Astra: 128s / ~$8.75 Grok 4.6: 158s / ~$0.55 Where would you put JEV to work in your company?

Buddy Works

171,528 次观看 • 1 个月前

This Polymarket Trading Bot has never lost (thanks claude code) + i put all the code in the video
12:47

This Polymarket Trading Bot has never lost (thanks claude code) + i put all the code in the video

Moon Dev

15,291 次观看 • 4 个月前

Why settle for one Claude Code when you can run ten in parallel? We built Claude Squad — a manager for Claude Code & Aider tasks: • Supervise multiple agents in one place • Isolated git workspaces Free + open-source:
0:32

Why settle for one Claude Code when you can run ten in parallel? We built Claude Squad — a manager for Claude Code & Aider tasks: • Supervise multiple agents in one place • Isolated git workspaces Free + open-source:

mufeez

120,932 次观看 • 1 年前

If you use Claude Code, be careful what you put in your commit messages...
34:38

If you use Claude Code, be careful what you put in your commit messages...

Theo - t3.gg

87,914 次观看 • 5 个月前

New Claude Code Mod… it keeps getting more hackable and customizable This Mod lets you see every subagent running in your session You won’t lose track of them anymore... they stay visible in the sidebar, where you can review what each one has done and how much context it has used Install it with one command: npx claude-code-templates@latest --mod ui/agent-flow Link:
0:26

New Claude Code Mod… it keeps getting more hackable and customizable This Mod lets you see every subagent running in your session You won’t lose track of them anymore... they stay visible in the sidebar, where you can review what each one has done and how much context it has used Install it with one command: npx claude-code-templates@latest --mod ui/agent-flow Link:

Daniel San

22,324 次观看 • 1 个月前

We ran Claude code in a while loop and it ported Browser Use to Typescript
1:54

We ran Claude code in a while loop and it ported Browser Use to Typescript

Simon Farshid

93,683 次观看 • 1 年前

Can Jev Nav? We put Jev, Astra, Fable, Dimcode, and other models + harnesses to the test on 2000+ navigation tasks in 133 real and simulated environments How far are LMs from zero-shotting complex real-time control tasks? Full dataset and code open source ⤵️
0:24

Can Jev Nav? We put Jev, Astra, Fable, Dimcode, and other models + harnesses to the test on 2000+ navigation tasks in 133 real and simulated environments How far are LMs from zero-shotting complex real-time control tasks? Full dataset and code open source ⤵️

stash

20,409 次观看 • 27 天前

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

204,901 次观看 • 1 个月前