Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

You can now use Jev right inside Claude Code 🤯 It's called jev-model-router, an early access mod built on Claude Code's new function hooks. Before every turn, it checks in with Jev and asks: > how mechanical the task is > how much reasoning it needs > whether it's...

dr_cintas's profile picture

Alvaro Cintas

132,663 subscribers

44,575 Aufrufe • vor 1 Monat •via X (Twitter)

Wissenschaft & TechnologieBildung
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

This is absolutely f*cking insane. you can put a $0.042-per-million-token model in front of Claude and let it decide what Claude ever has to see. that's Jev signal routing, and the trick is stupidly simple: Jev takes the first look at everything. Claude only gets the hard cases. instead of: data -> Claude -> tokens burnt $ it's: data -> Jev -> only the unsure ones -> Claude and here's the part people miss. every Jev answer comes with a probability. that's your router: -> Jev is sure? its answer is final -> Jev hesitates? the case goes up to Claude set the cutoff once, by testing on your own data, not by guessing. 3 repos that already do the routing for you: -> duckdb-jev: route your data. Jev labels every row straight from SQL, up to 1,000 calls in one request -> quicksilver: route your files. Jev checks all 187 files in parallel and Claude gets the 4 that matter. ~2.4k tokens instead of ~26k -> jev-router: route your models. before every message Jev decides simple or hard and sends it to the fast model or the strong one. works with your normal Claude login where this pays off right away: -> support tickets -> your inbox -> lead lists -> messy spreadsheets -> comment moderation on a public benchmark Jev labeled 1,000 rows for $0.015. Claude charged $0.80 for the same job. faster. cheaper. way fewer tokens burned. Jev sorts the mail so the genius only opens what matters. Claude thinks. Jev routes. code does the job.
0:19

This is absolutely f*cking insane. you can put a $0.042-per-million-token model in front of Claude and let it decide what Claude ever has to see. that's Jev signal routing, and the trick is stupidly simple: Jev takes the first look at everything. Claude only gets the hard cases. instead of: data -> Claude -> tokens burnt $ it's: data -> Jev -> only the unsure ones -> Claude and here's the part people miss. every Jev answer comes with a probability. that's your router: -> Jev is sure? its answer is final -> Jev hesitates? the case goes up to Claude set the cutoff once, by testing on your own data, not by guessing. 3 repos that already do the routing for you: -> duckdb-jev: route your data. Jev labels every row straight from SQL, up to 1,000 calls in one request -> quicksilver: route your files. Jev checks all 187 files in parallel and Claude gets the 4 that matter. ~2.4k tokens instead of ~26k -> jev-router: route your models. before every message Jev decides simple or hard and sends it to the fast model or the strong one. works with your normal Claude login where this pays off right away: -> support tickets -> your inbox -> lead lists -> messy spreadsheets -> comment moderation on a public benchmark Jev labeled 1,000 rows for $0.015. Claude charged $0.80 for the same job. faster. cheaper. way fewer tokens burned. Jev sorts the mail so the genius only opens what matters. Claude thinks. Jev routes. code does the job.

kiosa

11,388 Aufrufe • vor 17 Tagen

Claude Code Scheduled Tasks is now available... here's a solid idea to connect it with Telegram Save this so you don't forget to set it up! First, ask Claude to add a simple Telegram messaging module to your repo. You can use the Telegram Bot Builder Skill from Link: Install command: npx claude-code-templates@latest --skill enterprise-communication/telegram-bot-builder Once the module is in your project, grab your bot credentials from BotFather and add the bot ID to your .env file That's it! ✅ Now every Scheduled Task you create should end with an instruction for Claude to send the task result to Telegram using that module. Claude will handle the delivery automatically on every task it runs
0:18

Claude Code Scheduled Tasks is now available... here's a solid idea to connect it with Telegram Save this so you don't forget to set it up! First, ask Claude to add a simple Telegram messaging module to your repo. You can use the Telegram Bot Builder Skill from Link: Install command: npx claude-code-templates@latest --skill enterprise-communication/telegram-bot-builder Once the module is in your project, grab your bot credentials from BotFather and add the bot ID to your .env file That's it! ✅ Now every Scheduled Task you create should end with an instruction for Claude to send the task result to Telegram using that module. Claude will handle the delivery automatically on every task it runs

Daniel San

91,123 Aufrufe • vor 8 Monaten

Built a model router with Jev by TypeSafe AI. Jev decides what model fits your request best and the request is sent to that model.
0:14

Built a model router with Jev by TypeSafe AI. Jev decides what model fits your request best and the request is sent to that model.

Duncan

120,065 Aufrufe • vor 1 Monat

This is f*ckin awesome. A Stanford team pairs JEV with Claude Code to sort 75 billion data points every 11 minutes. JEV runs a cheap first pass on everything. Claude only gets the hard cases. Faster, cheaper, way less compute burned.
0:19

This is f*ckin awesome. A Stanford team pairs JEV with Claude Code to sort 75 billion data points every 11 minutes. JEV runs a cheap first pass on everything. Claude only gets the hard cases. Faster, cheaper, way less compute burned.

kiosa

63,141 Aufrufe • vor 1 Monat

Opus 5.5 + GrokBot + Jev... I can't believe that I build it I packed the best of AI into ONE agent - now 99% of people’s AI agents look dumb, slow, and expensive Try here (free): prompt → GrokBot → Jev chooses LLM → Claude / GPT working on GrokBot's computer 24/7 → result → Jev sends only the tasks Grok is weak at to Opus or GPT → Jev picks the best model for each task - for example, Claude for motion design and Codex for web design → runs on the ChatGPT and Claude subscriptions you already pay for (API also work) → works on GrokBot computer while you keep chatting → checks every result against the goal before you see it → GrokBot gets smarter and cheaper at the same time → And plenty more features in a bot everyone will call "obvious" by 2030 Try Jevopus, thank me later - then read the article on the full Jev architecture ↓
0:14

Opus 5.5 + GrokBot + Jev... I can't believe that I build it I packed the best of AI into ONE agent - now 99% of people’s AI agents look dumb, slow, and expensive Try here (free): prompt → GrokBot → Jev chooses LLM → Claude / GPT working on GrokBot's computer 24/7 → result → Jev sends only the tasks Grok is weak at to Opus or GPT → Jev picks the best model for each task - for example, Claude for motion design and Codex for web design → runs on the ChatGPT and Claude subscriptions you already pay for (API also work) → works on GrokBot computer while you keep chatting → checks every result against the goal before you see it → GrokBot gets smarter and cheaper at the same time → And plenty more features in a bot everyone will call "obvious" by 2030 Try Jevopus, thank me later - then read the article on the full Jev architecture ↓

codila

274,517 Aufrufe • vor 1 Monat

it's f*cking insane.. Anthropic just dropped a Claude Code setup that makes tokens up to 97% cheaper Opus brains, Sonnet bill: > Sonnet runs your session and writes the code > Haiku subagents grab the small tasks > Opus steps in only when Sonnet gets stuck > it checks the work, digs into the problem and puts Sonnet back on track $19.50 saved on every 1M tokens a Haiku 5.5 subagent writes, compared with Opus 5.5 one command sets it up: npx claude-code-templates@latest --setting model/sonnet-opus-advisor-haiku-subagents the easiest money you'll save on Claude Code this year
0:18

it's f*cking insane.. Anthropic just dropped a Claude Code setup that makes tokens up to 97% cheaper Opus brains, Sonnet bill: > Sonnet runs your session and writes the code > Haiku subagents grab the small tasks > Opus steps in only when Sonnet gets stuck > it checks the work, digs into the problem and puts Sonnet back on track $19.50 saved on every 1M tokens a Haiku 5.5 subagent writes, compared with Opus 5.5 one command sets it up: npx claude-code-templates@latest --setting model/sonnet-opus-advisor-haiku-subagents the easiest money you'll save on Claude Code this year

Mnimiy

55,980 Aufrufe • vor 1 Monat

I built an AI trading bot with Jev + Opus 5.5, and it's probably too powerful for public use, but f*ck it... It's a high-frequency algo trading framework that prints. Open the article, copy/paste it into Claude Code. You're welcome.
0:13

I built an AI trading bot with Jev + Opus 5.5, and it's probably too powerful for public use, but f*ck it... It's a high-frequency algo trading framework that prints. Open the article, copy/paste it into Claude Code. You're welcome.

Miles Deutscher

199,310 Aufrufe • vor 1 Monat

Claude Code just reverse-engineered my Wi-Fi router... found why it was so f*cking slow and fixed it in 5 minutes check yours, here's full guide step by step: step 1 → paste prompt below into Claude Code with photo of your router and tell it what's wrong. If you just want a diagnosis, it works too step 2 → it gives you one command to save your router password to your keychain, run it - the password never touches the chat step 3 → Claude shows each fix with the old and new value, you just say yes step 4 → the rest is on Claude: it backs up every setting, finds what's killing your speed (crowded channel, wrong band, narrow width, old WI-FI mode, lag) and re-tests after every fix the result: before and after speed in one line, and a router that takes orders from chat: "who's on my WI-FI", "reboot the router" and other... p.s: works with most routers, if yours is different, just tell Claude Code and it'll find another way in Try right now, don't forget me later. Then read article below shows how to reverse-engineer anything:
0:17

Claude Code just reverse-engineered my Wi-Fi router... found why it was so f*cking slow and fixed it in 5 minutes check yours, here's full guide step by step: step 1 → paste prompt below into Claude Code with photo of your router and tell it what's wrong. If you just want a diagnosis, it works too step 2 → it gives you one command to save your router password to your keychain, run it - the password never touches the chat step 3 → Claude shows each fix with the old and new value, you just say yes step 4 → the rest is on Claude: it backs up every setting, finds what's killing your speed (crowded channel, wrong band, narrow width, old WI-FI mode, lag) and re-tests after every fix the result: before and after speed in one line, and a router that takes orders from chat: "who's on my WI-FI", "reboot the router" and other... p.s: works with most routers, if yours is different, just tell Claude Code and it'll find another way in Try right now, don't forget me later. Then read article below shows how to reverse-engineer anything:

codila

220,256 Aufrufe • vor 21 Tagen

You need to try Claude Code with CLAUDE_CODE_NO_FLICKER! I remember the early days using Claude Code in the VSCode terminal, struggling to keep the terminal from jumping around Then I switched to Ghostty and things got way better... now with tmux and NO_FLICKER it's perfect Completely clean interaction Quick test, just run: CLAUDE_CODE_NO_FLICKER=1 claude If you like it, add this to your settings.json "env": { "CLAUDE_CODE_NO_FLICKER": "1" } TIP: Add the settings.json to the .claude folder in your home directory so it applies to every session you open
0:13

You need to try Claude Code with CLAUDE_CODE_NO_FLICKER! I remember the early days using Claude Code in the VSCode terminal, struggling to keep the terminal from jumping around Then I switched to Ghostty and things got way better... now with tmux and NO_FLICKER it's perfect Completely clean interaction Quick test, just run: CLAUDE_CODE_NO_FLICKER=1 claude If you like it, add this to your settings.json "env": { "CLAUDE_CODE_NO_FLICKER": "1" } TIP: Add the settings.json to the .claude folder in your home directory so it applies to every session you open

Daniel San

43,054 Aufrufe • vor 7 Monaten

You can now run Grok inside Claude Code and Codex, using your existing subscription. it's called grok-plugin. Grok’s genuinely good right now, but if your setup lives in Claude Code and Codex, switching to use it is a pain. this solves that exact issue: > Grok in Claude Code and Codex > directly auths through X Premium or Supergrok, no api key > your workflow and subagents stay untouched free and open source. the low-friction way to test Grok in the tools you already use.
0:16

You can now run Grok inside Claude Code and Codex, using your existing subscription. it's called grok-plugin. Grok’s genuinely good right now, but if your setup lives in Claude Code and Codex, switching to use it is a pain. this solves that exact issue: > Grok in Claude Code and Codex > directly auths through X Premium or Supergrok, no api key > your workflow and subagents stay untouched free and open source. the low-friction way to test Grok in the tools you already use.

Alvaro Cintas

26,018 Aufrufe • vor 2 Monaten

Claude Code 2.1.90 just dropped with a new /powerup command Run it and you get interactive lessons that teach you how to use Claude Code right inside the tool. It's solid and has a lot of potential for learning directly in the terminal. Curious how the UI will look in VSCode and Claude Code Desktop. Going to keep digging into this new release!
0:18

Claude Code 2.1.90 just dropped with a new /powerup command Run it and you get interactive lessons that teach you how to use Claude Code right inside the tool. It's solid and has a lot of potential for learning directly in the terminal. Curious how the UI will look in VSCode and Claude Code Desktop. Going to keep digging into this new release!

Daniel San

272,065 Aufrufe • vor 7 Monaten

Claude Code Desktop now opens a new window for each session This makes it much easier to visualize multiple Claude Code agents running in parallel My current stack depends on the task: - Ghostty: when starting a project. Bash commands, git, env variables, provider connections. All manual through the terminal with a Claude panel running alongside. - Claude Code Desktop: once everything is configured. GitHub connected, CLAUDE.md, Skills, subagents and Hooks ready. Claude Code runs on its own, no more terminal setup, just panels running and outputs to review. - VSCode: when I need to review code by hand. I use it less and less, but there are moments where I have to confirm Claude got it right. I usually open the Claude extension inside VSCode, but it lacks most of the CLI features so it's limited Solid update. Worth trying once your workflows are already set up 👇
0:16

Claude Code Desktop now opens a new window for each session This makes it much easier to visualize multiple Claude Code agents running in parallel My current stack depends on the task: - Ghostty: when starting a project. Bash commands, git, env variables, provider connections. All manual through the terminal with a Claude panel running alongside. - Claude Code Desktop: once everything is configured. GitHub connected, CLAUDE.md, Skills, subagents and Hooks ready. Claude Code runs on its own, no more terminal setup, just panels running and outputs to review. - VSCode: when I need to review code by hand. I use it less and less, but there are moments where I have to confirm Claude got it right. I usually open the Claude extension inside VSCode, but it lacks most of the CLI features so it's limited Solid update. Worth trying once your workflows are already set up 👇

Daniel San

38,982 Aufrufe • vor 5 Monaten

Sonnet as the main model, Opus as an advisor, and Haiku for subagents Save this and try it with one of your sessions Install: npx claude-code-templates@latest --setting model/sonnet-opus-advisor-haiku-subagents This command installs the settings required to configure your Claude Code sessions with this model distribution Select the appropriate configuration scope: User, Project, or Local
0:17

Sonnet as the main model, Opus as an advisor, and Haiku for subagents Save this and try it with one of your sessions Install: npx claude-code-templates@latest --setting model/sonnet-opus-advisor-haiku-subagents This command installs the settings required to configure your Claude Code sessions with this model distribution Select the appropriate configuration scope: User, Project, or Local

Daniel San

29,173 Aufrufe • vor 1 Monat

Jev + Opus 5.5 is the most underrated setup in AI right now, and i don't get why nobody's talking about it. I stopped letting Opus make every small decision in my agents. Jev makes them now. My Opus bill dropped ~500% on the same tasks, same results. Here's what Jev handles: - which files and notes to load before Opus sees anything - which effort level each task actually needs - what to do when a tool fails - which tests to run, and when to stop Opus only gets called for the hard reasoning. Every decision is a typed result the host checks before it runs. The exact prompt to set this up in your workflow is below.
0:20

Jev + Opus 5.5 is the most underrated setup in AI right now, and i don't get why nobody's talking about it. I stopped letting Opus make every small decision in my agents. Jev makes them now. My Opus bill dropped ~500% on the same tasks, same results. Here's what Jev handles: - which files and notes to load before Opus sees anything - which effort level each task actually needs - what to do when a tool fails - which tests to run, and when to stop Opus only gets called for the hard reasoning. Every decision is a typed result the host checks before it runs. The exact prompt to set this up in your workflow is below.

Anatoli Kopadze

77,128 Aufrufe • vor 1 Monat

Introducing Time Machine for Claude Code Works in both Claude Desktop and Claude Code CLI /timemachine records your session as a timeline, including prompts, tool calls, edits, Bash commands, and turn endings Pick any point and fork from there, It restores both the conversation and the code state from that moment into a separate Git worktree and branch, while your original session stays untouched Install: npx claude-code-templates@latest --mod productivity/session-time-machine Then run: /reload-plugin /timemachine
0:16

Introducing Time Machine for Claude Code Works in both Claude Desktop and Claude Code CLI /timemachine records your session as a timeline, including prompts, tool calls, edits, Bash commands, and turn endings Pick any point and fork from there, It restores both the conversation and the code state from that moment into a separate Git worktree and branch, while your original session stays untouched Install: npx claude-code-templates@latest --mod productivity/session-time-machine Then run: /reload-plugin /timemachine

Daniel San

24,097 Aufrufe • vor 1 Monat

I built a thing using Jev. Have you ever been annoyed by not finding an old Claude Code or Codex chat? => Now you can just describe what it was about and Jev finds it in milliseconds. Open Source:
0:12

I built a thing using Jev. Have you ever been annoyed by not finding an old Claude Code or Codex chat? => Now you can just describe what it was about and Jev finds it in milliseconds. Open Source:

Florian S

85,808 Aufrufe • vor 1 Monat

To make it easier to migrate your workflows, we've updated the claude-api skill in Claude Code with Opus 4.7 support. Just say "migrate to Opus 4.7" and it updates model names, prompts, and effort settings for you.
0:11

To make it easier to migrate your workflows, we've updated the claude-api skill in Claude Code with Opus 4.7 support. Just say "migrate to Opus 4.7" and it updates model names, prompts, and effort settings for you.

ClaudeDevs

362,748 Aufrufe • vor 6 Monaten

Claude Code is a mess. Until you install this. There's an official Anthropic plugin called claude-code-setup. It tells you what automations you can set up (hooks, skills, MCP servers, subagents…) and how to configure them step by step. Basically, it analyzes your project and recommends what to activate. To install it: /plugin install claude-code-setup@claude-plugins-official Save this post so you don't lose it 🔖
0:11

Claude Code is a mess. Until you install this. There's an official Anthropic plugin called claude-code-setup. It tells you what automations you can set up (hooks, skills, MCP servers, subagents…) and how to configure them step by step. Basically, it analyzes your project and recommends what to activate. To install it: /plugin install claude-code-setup@claude-plugins-official Save this post so you don't lose it 🔖

Dean W. Perkins

121,971 Aufrufe • vor 2 Tagen

Claude Code tip: if Opus 5.5 is already your main model, Fable 5.1 has been sitting idle this whole time. wire it in with /advisor start it with /advisor fable Opus 5.5 writes every line. Fable 5.1 reads the whole session, every tool call, and says nothing until one of three moments: → a plan gets proposed: is this actually the right move, or just the first one? → the same error comes back twice: is the search stuck, or is this a dead end? → the task gets marked done: what got missed while it was moving fast? Opus 5.5 ships. Fable 5.1 catches what would've shipped broken. Jev engineering makes the same move one layer down: forks that don't need a real thinker, which file, which tool, retry or give up, get routed to Jev and answered in under half a second. the expensive model only ever sees the forks that genuinely split. the tree this runs on: > Opus 5.5, high effort, owns the main session > explorer, medium effort, reads the code > worker, medium effort, edits and runs tests > researcher, medium effort, pulls the docs > Fable 5.1 outside all of it, on call, never writing a line itself drop the tree and this prompt into Claude Code: "Rebuild my Claude Code setup around this tree: 1. Look in ~/.claude/agents and .claude/agents for subagents that already cover explorer, worker and researcher. Draft new ones only for roles that are missing. Set each to model: opus, effort: medium. If an existing subagent is pinned to a different model, list it, don't touch it. 2. Set the main session's effortLevel to high in ~/.claude/settings.json, and set advisorModel to fable. 3. Check for anything disabling the advisor: CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, any variable blocking feature-flag fetches, and CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report what you find. Change nothing yet. 4. Add one line to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before marking a long task done. Show every change as a diff first. Don't touch anything until I say go."
0:19

Claude Code tip: if Opus 5.5 is already your main model, Fable 5.1 has been sitting idle this whole time. wire it in with /advisor start it with /advisor fable Opus 5.5 writes every line. Fable 5.1 reads the whole session, every tool call, and says nothing until one of three moments: → a plan gets proposed: is this actually the right move, or just the first one? → the same error comes back twice: is the search stuck, or is this a dead end? → the task gets marked done: what got missed while it was moving fast? Opus 5.5 ships. Fable 5.1 catches what would've shipped broken. Jev engineering makes the same move one layer down: forks that don't need a real thinker, which file, which tool, retry or give up, get routed to Jev and answered in under half a second. the expensive model only ever sees the forks that genuinely split. the tree this runs on: > Opus 5.5, high effort, owns the main session > explorer, medium effort, reads the code > worker, medium effort, edits and runs tests > researcher, medium effort, pulls the docs > Fable 5.1 outside all of it, on call, never writing a line itself drop the tree and this prompt into Claude Code: "Rebuild my Claude Code setup around this tree: 1. Look in ~/.claude/agents and .claude/agents for subagents that already cover explorer, worker and researcher. Draft new ones only for roles that are missing. Set each to model: opus, effort: medium. If an existing subagent is pinned to a different model, list it, don't touch it. 2. Set the main session's effortLevel to high in ~/.claude/settings.json, and set advisorModel to fable. 3. Check for anything disabling the advisor: CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, any variable blocking feature-flag fetches, and CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report what you find. Change nothing yet. 4. Add one line to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before marking a long task done. Show every change as a diff first. Don't touch anything until I say go."

Ryven

36,283 Aufrufe • vor 1 Monat

jev + sonnet 5.5 is f**king insane. my entire workflow got 4x faster after adding these 6 lines to CLAUDE.md. [with jev connected, paste this👇] 1. Before you start a Claude worker, ask Jev once to select a host-approved profile with one or two sessions. The profile must specify each session’s model and effort level. If Jev makes no selection, use the host default. 2. The host must check Jev’s selection. The host must set the model and effort before each session starts. Keep these settings fixed during the session. The host controls permissions and approvals. 3. Use Sonnet 5.5 at medium effort for clear coding tasks. Use higher effort for complex reasoning or JSON tasks. Use a second Claude only for independent research or a review that the user requested. 4. Give the second Claude the task, applicable files, limits, and completion requirements. Return its findings and evidence to the lead. 5. Complete the requested work. Ask the user only when you cannot continue without input or before an action that needs approval. Do not add features, tests, files, documentation, refactors, or review rounds that the user did not request. When the work is complete and checked, stop. Report the result. 6. Before you report completion, run a test, build, type check, or command that checks the code change. If no check can run, identify the missing check. Explain why it cannot run. same task. two timers. watch the difference.
0:18

jev + sonnet 5.5 is f**king insane. my entire workflow got 4x faster after adding these 6 lines to CLAUDE.md. [with jev connected, paste this👇] 1. Before you start a Claude worker, ask Jev once to select a host-approved profile with one or two sessions. The profile must specify each session’s model and effort level. If Jev makes no selection, use the host default. 2. The host must check Jev’s selection. The host must set the model and effort before each session starts. Keep these settings fixed during the session. The host controls permissions and approvals. 3. Use Sonnet 5.5 at medium effort for clear coding tasks. Use higher effort for complex reasoning or JSON tasks. Use a second Claude only for independent research or a review that the user requested. 4. Give the second Claude the task, applicable files, limits, and completion requirements. Return its findings and evidence to the lead. 5. Complete the requested work. Ask the user only when you cannot continue without input or before an action that needs approval. Do not add features, tests, files, documentation, refactors, or review rounds that the user did not request. When the work is complete and checked, stop. Report the result. 6. Before you report completion, run a test, build, type check, or command that checks the code change. If no check can run, identify the missing check. Explain why it cannot run. same task. two timers. watch the difference.

Avid

177,825 Aufrufe • vor 1 Monat