Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

introducing Jaste (beta) - TypeSafe AI jev powered copy/paste - faster than the original demo - local mode dropping soon - byok support using your computer doesn't have to be so tedious

Marcus Lowe

3,612 subscribers

116,826 views • 8 days ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

7 Comments

Noman8 days ago

@typesafeai Why did you steal my open source idea

Paul Shippy8 days ago

@typesafeai Why do you have to go to each field? Shouldn't it just fill in all the fields it can instantly?

Jatin Garg8 days ago

@typesafeai the speed claim needs numbers. "faster" could mean 2x or 20x, and that changes whether local mode is about privacy or cost.

StatysTheBaddest8 days ago

@typesafeai There should be a right click autofill button, where it tabs through the document/page, and uses computer-use to fill it in for you.

Rubs8 days ago

@typesafeai Using the form names/ids you could actually fill it all at once, you just have to read the DOM. Looks great tho

Lahfir8 days ago

@typesafeai Just curious why not autofill all the fields?

VJ8 days ago

@typesafeai paste in all fields on one CMD + V

Related Videos

Introducing jevgrep - a research agent CLI powered by jev from TypeSafe AI that reduces your coding agent cost by 40% (verified on SWE-bench) Make sure to use the built in skill so your coding agent knows to use jg for context collection

Introducing jevgrep - a research agent CLI powered by jev from TypeSafe AI that reduces your coding agent cost by 40% (verified on SWE-bench) Make sure to use the built in skill so your coding agent knows to use jg for context collection

David

409,232 views • 2 days ago

Introducing the first AI-powered scheduling software in the world. It's your more intelligent & affordable Calcom + Calendaly combined! It acts like: - Salesman (to convince your clients to book) - Support team (to answer your clients' questions & guide them) - An AI-powered booking system (to book meetings directly using AI integration) - & so much more! It will be dropping in prod in a few days :) P.S.: I used 's amazing API for scraping & web search. I also built this feature with my Co-founder in the CustomHacks hackathon hosted by Michael Magán. Get ready to transform how scheduling & AI work together! Demo 👇

Introducing the first AI-powered scheduling software in the world. It's your more intelligent & affordable Calcom + Calendaly combined! It acts like: - Salesman (to convince your clients to book) - Support team (to answer your clients' questions & guide them) - An AI-powered booking system (to book meetings directly using AI integration) - & so much more! It will be dropping in prod in a few days :) P.S.: I used 's amazing API for scraping & web search. I also built this feature with my Co-founder in the CustomHacks hackathon hosted by Michael Magán. Get ready to transform how scheduling & AI work together! Demo 👇

Bilal Bakr

275,555 views • 1 year ago

JEV MADE ME $3,031 WITH A 7-MINUTE AI AGENT SETUP Prompt → GrokBot → Jev decision → GrokBot execution → Result Jev decides what actually needs to run. GrokBot handles the execution directly on your computer. → Less wasted calls → Lower cost → Faster agent workflow Create a Typesafe API key, install typesafe-sdk and smoke test system_one. Build the usage lab with router, dry-run, config and logs. Add jev-usage-router before browser, research, retry or extra bot calls. Start in shadow mode and check the logs. Once you trust the routing, flip it to active. Now GrokBot follows the route. Jev decides what makes sense to run. You still control irreversible actions. I’ve already tested this setup on routine tasks. And the difference is crazy. → Jev decides → GrokBot executes → You stay in control Copy the setup and explore the repo below. → Full Jev deep dive ↓

JEV MADE ME $3,031 WITH A 7-MINUTE AI AGENT SETUP Prompt → GrokBot → Jev decision → GrokBot execution → Result Jev decides what actually needs to run. GrokBot handles the execution directly on your computer. → Less wasted calls → Lower cost → Faster agent workflow Create a Typesafe API key, install typesafe-sdk and smoke test system_one. Build the usage lab with router, dry-run, config and logs. Add jev-usage-router before browser, research, retry or extra bot calls. Start in shadow mode and check the logs. Once you trust the routing, flip it to active. Now GrokBot follows the route. Jev decides what makes sense to run. You still control irreversible actions. I’ve already tested this setup on routine tasks. And the difference is crazy. → Jev decides → GrokBot executes → You stay in control Copy the setup and explore the repo below. → Full Jev deep dive ↓

winkle.

11,926 views • 6 days ago

The speed and cost is going to enable use cases that haven't been possible before. Here's a quick demo of live decisions of what slide to pull up as I'm speaking, powered by TypeSafe AI Jev. Also, sorry for the sniffling. I have a bit of a cold.

The speed and cost is going to enable use cases that haven't been possible before. Here's a quick demo of live decisions of what slide to pull up as I'm speaking, powered by TypeSafe AI Jev. Also, sorry for the sniffling. I have a bit of a cold.

Zain Hoda

59,968 views • 11 days ago

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

38,564 views • 2 days ago

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

171,725 views • 8 days ago

Okay so Jev can actually do computer use really well Without any screenshots, or LLMs and no Pixels leave my mac I dont even read the Dom elements A local CoreML model segments every button and UI element on screen. On-device OCR reads the labels. That text is all Jev gets. It returns a probability across those elements and tells me the best one to click. Then it clicks, re-runs detection, and decides again. In a loop until the goal is done. ~90ms per decision. Faster than any LLM computer use I've tried. Blazing fast computer use, without any latency TypeSafe AI is building something really interesting

Okay so Jev can actually do computer use really well Without any screenshots, or LLMs and no Pixels leave my mac I dont even read the Dom elements A local CoreML model segments every button and UI element on screen. On-device OCR reads the labels. That text is all Jev gets. It returns a probability across those elements and tells me the best one to click. Then it clicks, re-runs detection, and decides again. In a loop until the goal is done. ~90ms per decision. Faster than any LLM computer use I've tried. Blazing fast computer use, without any latency TypeSafe AI is building something really interesting

Milind S

241,887 views • 11 days ago

AI-powered Dashboards taken to the next level. Built using OpenAI and your favorite new LLMs🔥 Connect your APIs/data sources and create dynamic dashboards in *seconds* Demo with blockchain data below👇🏻 Beta:

AI-powered Dashboards taken to the next level. Built using OpenAI and your favorite new LLMs🔥 Connect your APIs/data sources and create dynamic dashboards in seconds Demo with blockchain data below👇🏻 Beta:

Aryan Sharma

66,382 views • 3 years ago

Jev by TypeSafe AI is now on the Venice API, in beta. It answers, it doesn't write. Send it your app's state and typed questions. Get back a typed answer your code can branch on: a probability, a chosen option, or a score on your rubric. No JSON to coax out of a chat model.

Jev by TypeSafe AI is now on the Venice API, in beta. It answers, it doesn't write. Send it your app's state and typed questions. Get back a typed answer your code can branch on: a probability, a chosen option, or a score on your rubric. No JSON to coax out of a chat model.

Venice

548,188 views • 10 days ago

Yesterday I demo'd how copy pasting marketing images from Notra to Figma would look like Today we added Paper support which has been a breeze thanks to Stephen Haney Soon you will be able to generate images using Notra and paste them directly in your favorite design tool!

Yesterday I demo'd how copy pasting marketing images from Notra to Figma would look like Today we added Paper support which has been a breeze thanks to Stephen Haney Soon you will be able to generate images using Notra and paste them directly in your favorite design tool!

Dominik Koch

12,636 views • 4 months ago

Also have been playing with TypeSafe AI Jev, insane! So many immediate use cases and new apps are possible. What a time to be a builder! Sharing some experiments here starting with: Keystroke oracle / predictive launcher: Your launcher ranks by aliases, fuzzy match, and habit. Jev reads intent: type "the pdf I just downloaded" and the newest PDF is already the top hit with a full confidence on every keystroke, in ~100 ms

Also have been playing with TypeSafe AI Jev, insane! So many immediate use cases and new apps are possible. What a time to be a builder! Sharing some experiments here starting with: Keystroke oracle / predictive launcher: Your launcher ranks by aliases, fuzzy match, and habit. Jev reads intent: type "the pdf I just downloaded" and the newest PDF is already the top hit with a full confidence on every keystroke, in ~100 ms

nader dabit

431,716 views • 11 days ago

It's BAGS Bags Hackathon demo day so here's a little preview of the soon to be released $GSD Cloud app I'm building for GSD. Manage AI agents on your home computer from ANY device with internet access. Lots of very cool new features to share in the coming 2 weeks.

It's BAGS Bags Hackathon demo day so here's a little preview of the soon to be released $GSD Cloud app I'm building for GSD. Manage AI agents on your home computer from ANY device with internet access. Lots of very cool new features to share in the coming 2 weeks.

Lex Christopherson

16,161 views • 5 months ago

Make's AI era is coming. Discover how soon, you’ll be able to transform your ideas into scenarios faster than ever. And learn more about the AI resources already in the Make ecosystem. Sign up now! 👉🏽

Make's AI era is coming. Discover how soon, you’ll be able to transform your ideas into scenarios faster than ever. And learn more about the AI resources already in the Make ecosystem. Sign up now! 👉🏽

Make

58,600 views • 3 years ago

BETA Coming Soon!! 🔥 Keep your eyes out, no dates for you just yet, but it's sooner than you think, and it's going to be so much cooler than what you have in mind. 🚀👩‍🚀

BETA Coming Soon!! 🔥 Keep your eyes out, no dates for you just yet, but it's sooner than you think, and it's going to be so much cooler than what you have in mind. 🚀👩‍🚀

SUBBD

59,180 views • 2 years ago

Listen to James Murdza's demo of a 100% open-source Computer Use. The agent is using 3 different LLMs: 🔸Llama 3.2 (AI at Meta) 🔸Llama 3.3 🔸OS-Atlas (Qwen, Junyang Lin) This example is using @e2b_dev's Desktop Sandbox as a virtual computer. It's completely open-source too, so go build your own agent.

Listen to James Murdza's demo of a 100% open-source Computer Use. The agent is using 3 different LLMs: 🔸Llama 3.2 (AI at Meta) 🔸Llama 3.3 🔸OS-Atlas (Qwen, Junyang Lin) This example is using @e2b_dev's Desktop Sandbox as a virtual computer. It's completely open-source too, so go build your own agent.

Tereza Tizkova, 🌁 at AI Engineer 06/29-07/02

71,412 views • 1 year ago

Waymo’s Co-CEO was asked to respond to Tesla using strictly Computer Vision & AI rather than LiDAR: “You have to be able to see at night. You have to have this vision that is better than humans. What we’re doing is replacing humans. We’re not asking you to sit behind the wheel and take over the vehicle at a very vulnerable moment.” The Tesla Robotaxi network can’t come soon enough. Good luck to Waymo.

Waymo’s Co-CEO was asked to respond to Tesla using strictly Computer Vision & AI rather than LiDAR: “You have to be able to see at night. You have to have this vision that is better than humans. What we’re doing is replacing humans. We’re not asking you to sit behind the wheel and take over the vehicle at a very vulnerable moment.” The Tesla Robotaxi network can’t come soon enough. Good luck to Waymo.

Nic Cruz Patane

759,260 views • 1 year ago

I came across this video of Justin Bieber using a full orchestra to turn the rhythms in his mind into music. Soon, anyone will be able to hum a tune, describe the vibe you’re aiming for, and have an AI-powered producer turn your ideas into reality.

I came across this video of Justin Bieber using a full orchestra to turn the rhythms in his mind into music. Soon, anyone will be able to hum a tune, describe the vibe you’re aiming for, and have an AI-powered producer turn your ideas into reality.

Reid Hoffman

262,348 views • 1 year ago