Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Today Google DeepMind released a state of the art computer use model, in partnership with Browserbase. Computer use is hard to evaluate. You need reliable browser infrastructure and realistic tasks. Below, we cover how we ran these benchmarks and how you can try yourself!

browserbase's profile picture

Browserbase

21,529 subscribers

155,120 görüntüleme • 11 ay önce •via X (Twitter)

Bilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

29 Yorum

Browserbase profil fotoğrafı
Browserbase11 ay önce

Read about the evaluations:

Logan Kilpatrick profil fotoğrafı
Logan Kilpatrick11 ay önce

@GoogleDeepMind Awesome to partner with you all and excited to get this new model into the hands of more builders!!!

Paul Klein IV profil fotoğrafı
Paul Klein IV11 ay önce

@GoogleDeepMind need to buy some Google stock after this

Kyle Jeong profil fotoğrafı
Kyle Jeong11 ay önce

@GoogleDeepMind Play with the models here

Kyle Jeong profil fotoğrafı
Kyle Jeong11 ay önce

@GoogleDeepMind if you're not using Browserbase to train your computer use models, you're not doing it right

Stella Wang profil fotoğrafı
Stella Wang11 ay önce

@GoogleDeepMind 🤺

derek profil fotoğrafı
derek11 ay önce

@GoogleDeepMind google us 😎

Stella Wang profil fotoğrafı
Stella Wang11 ay önce

@GoogleDeepMind Vibe evaluating🤔🤔

Linda Chen profil fotoğrafı
Linda Chen11 ay önce

@GoogleDeepMind Sickest crossover of all time

Peyton Casper profil fotoğrafı
Peyton Casper11 ay önce

@GoogleDeepMind can't believe we built @mercor in 24hrs

Erin Goode profil fotoğrafı
Erin Goode11 ay önce

@GoogleDeepMind let's goooooo

sameel arif profil fotoğrafı
sameel arif11 ay önce

@GoogleDeepMind 🅱️ig moves

harsehaj ⋆˙⟡ profil fotoğrafı
harsehaj ⋆˙⟡11 ay önce

@GoogleDeepMind reliable browser infra !!!

alana goyal profil fotoğrafı
alana goyal11 ay önce

@GoogleDeepMind this is big

Philipp Schmid profil fotoğrafı
Philipp Schmid11 ay önce

@GoogleDeepMind Awesome work! 🚀

Filip Michalsky profil fotoğrafı
Filip Michalsky11 ay önce

@GoogleDeepMind This is HUGE

Sheing Ng profil fotoğrafı
Sheing Ng11 ay önce

@GoogleDeepMind Ping me again if it's able to solve a wordle challenge.

Stella Wang profil fotoğrafı
Stella Wang11 ay önce

@GoogleDeepMind THIS IS INSANE

⟁ndrew V profil fotoğrafı
⟁ndrew V11 ay önce

@GoogleDeepMind That’s awesome. What an epic feeling that must be to have a partnership like this announcement for y’all. Also looking forward to trying it and building something great with the potential!

Junaid profil fotoğrafı
Junaid11 ay önce

@GoogleDeepMind Amazing stuff going on at 🅱️

Aman DevX profil fotoğrafı
Aman DevX11 ay önce

@GoogleDeepMind That sounds pretty cool, Browserbase!

tim profil fotoğrafı
tim11 ay önce

@GoogleDeepMind is it just me, or is it a bit confusing on what to do after agent completes the task? I was expecting the result, but couldn't find that anywhere on the UI

parth profil fotoğrafı
parth11 ay önce

@GoogleDeepMind 🙌

Sughu profil fotoğrafı
Sughu11 ay önce

@GoogleDeepMind Please create a pay per use API tier

Nikhil Kulkarni profil fotoğrafı
Nikhil Kulkarni11 ay önce

@GoogleDeepMind lets goooo!

Turner Novak 🍌🧢 profil fotoğrafı
Turner Novak 🍌🧢11 ay önce

@GoogleDeepMind Wow

lazy_procrastinator profil fotoğrafı
lazy_procrastinator11 ay önce

@GoogleDeepMind Genuinely curious, why does one need browserbase for this? Doesn’t it work headless?

Collin Shill profil fotoğrafı
Collin Shill11 ay önce

@GoogleDeepMind LFG

Ethan profil fotoğrafı
Ethan11 ay önce

@GoogleDeepMind Nice

Benzer Videolar

Computer use is finally reliable. It just needed a real harness. Now there is one. Starting today, anyone can ship a SOTA browser agent, batteries included. Introducing Browserbase Agents: one prompt and one API call is all you need to automate the whole web.
0:29

Computer use is finally reliable. It just needed a real harness. Now there is one. Starting today, anyone can ship a SOTA browser agent, batteries included. Introducing Browserbase Agents: one prompt and one API call is all you need to automate the whole web.

Browserbase

96,484 görüntüleme • 3 ay önce

We've partnered with OpenAI as one of their early research preview partners for the new computer use model. With this model, AI can control a browser better than ever before 👀 Of course, we had to launch a free hosted version + open source implementation. Check it out!
0:53

We've partnered with OpenAI as one of their early research preview partners for the new computer use model. With this model, AI can control a browser better than ever before 👀 Of course, we had to launch a free hosted version + open source implementation. Check it out!

Browserbase

40,232 görüntüleme • 1 yıl önce

A look at computer use and the built-in browser in the new ChatGPT app 👀 dominik kundel walks through how ChatGPT can work with apps on your computer and browse the web to research, navigate websites, and complete tasks with you.
1:19

A look at computer use and the built-in browser in the new ChatGPT app 👀 dominik kundel walks through how ChatGPT can work with apps on your computer and browse the web to research, navigate websites, and complete tasks with you.

ChatGPT

128,615 görüntüleme • 2 ay önce

You've probably heard of us before, but what exactly is Browserbase? Here's everything you need to know about how we can help you automate the web, in 90 seconds.
1:37

You've probably heard of us before, but what exactly is Browserbase? Here's everything you need to know about how we can help you automate the web, in 90 seconds.

Browserbase

39,801 görüntüleme • 9 ay önce

Forgot to make dinner plans? No worries, you can now use the Browserbase MCP Server with Raycast to book a fancy place in no time. The everything MCP. Try it out now! Config below.
0:31

Forgot to make dinner plans? No worries, you can now use the Browserbase MCP Server with Raycast to book a fancy place in no time. The everything MCP. Try it out now! Config below.

Browserbase

34,963 görüntüleme • 1 yıl önce

HoloTab is officially live. 🚀 14 days ago, we released Holo3. It proved you can hit state-of-the-art computer-use performance, outperforming the biggest models in the world at 1/10th of the cost. Now, we are moving that power out of the research labs and into your browser tabs. Don't trust the benchmarks. Trust your own experience! #AI #AgenticAI #HoloTab #ComputerUse #Innovation #HCompany
1:37

HoloTab is officially live. 🚀 14 days ago, we released Holo3. It proved you can hit state-of-the-art computer-use performance, outperforming the biggest models in the world at 1/10th of the cost. Now, we are moving that power out of the research labs and into your browser tabs. Don't trust the benchmarks. Trust your own experience! #AI #AgenticAI #HoloTab #ComputerUse #Innovation #HCompany

H

25,183 görüntüleme • 5 ay önce

Your agents should use a remote browser built specifically for them, We revamped our Browser Skill to use our custom Stagehand CLI, It's faster than MCP tools and each run uses a new browser context, avoiding prompt injection. npx skills add browserbase/skills —skill browser
0:22

Your agents should use a remote browser built specifically for them, We revamped our Browser Skill to use our custom Stagehand CLI, It's faster than MCP tools and each run uses a new browser context, avoiding prompt injection. npx skills add browserbase/skills —skill browser

Browserbase

41,144 görüntüleme • 6 ay önce

Google just unveiled a new project that shows how AI Agents are coming for full browser and computer use. This opens up AI to any of the laborious knowledge tasks that we do today. Most importantly, it lets us automate work that we never had even contemplated before.
1:27

Google just unveiled a new project that shows how AI Agents are coming for full browser and computer use. This opens up AI to any of the laborious knowledge tasks that we do today. Most importantly, it lets us automate work that we never had even contemplated before.

Aaron Levie

145,442 görüntüleme • 1 yıl önce

OpenClaw is all the rage and skills are a huge reason why. We've revamped ours to make it easier for Claude to go from local to prod. Check out how you can use Claude, Skills, and GitHub Actions to automatically self-heal browser automation scripts.
0:49

OpenClaw is all the rage and skills are a huge reason why. We've revamped ours to make it easier for Claude to go from local to prod. Check out how you can use Claude, Skills, and GitHub Actions to automatically self-heal browser automation scripts.

Browserbase

27,910 görüntüleme • 7 ay önce

Today we're excited to introduce Vy, our AI that sees and acts on your computer. At Vercept, our mission is to reinvent how humans use computers–enabling you to accomplish orders of magnitude more than what you can do today. Vy is a first glimpse at AI that sees and uses your computer just like you do. It runs natively on your computer, with access to all your applications and accounts that you’re already signed into. It is available for download starting today! As part of the release, we’ve built VyUI, an AI model bridging the gap between language and your screen. It sets a new state-of-the-art on UI grounding benchmarks like ScreenSpot v1, ScreenSpot v2, and GroundUI Web–beating leading models from OpenAI, Google, and Anthropic. Check out what Vy can do in the thread below: 🧵👇
1:41

Today we're excited to introduce Vy, our AI that sees and acts on your computer. At Vercept, our mission is to reinvent how humans use computers–enabling you to accomplish orders of magnitude more than what you can do today. Vy is a first glimpse at AI that sees and uses your computer just like you do. It runs natively on your computer, with access to all your applications and accounts that you’re already signed into. It is available for download starting today! As part of the release, we’ve built VyUI, an AI model bridging the gap between language and your screen. It sets a new state-of-the-art on UI grounding benchmarks like ScreenSpot v1, ScreenSpot v2, and GroundUI Web–beating leading models from OpenAI, Google, and Anthropic. Check out what Vy can do in the thread below: 🧵👇

Vercept

123,859 görüntüleme • 1 yıl önce

Just found an open-source tool that lets you see how well an AI can actually use a computer. it’s called OSWorld 2.0. you give the AI a real task on a computer, then watch to see if it can figure everything out and finish it. it gives you: → real computer tasks, not simple questions → tasks that can take many steps to finish → the same computer setup for every AI → websites made for testing → all the files and tasks for free this is also the environment used to test computer-use systems from OpenAI and Anthropic. so if you’re building AI agents, researching computer use, or just want to see what these models can actually do, you can run the same tests yourself instead of relying only on benchmark scores. the labs publish the scores. this repo is where the actual tests come from. bookmark this.
0:25

Just found an open-source tool that lets you see how well an AI can actually use a computer. it’s called OSWorld 2.0. you give the AI a real task on a computer, then watch to see if it can figure everything out and finish it. it gives you: → real computer tasks, not simple questions → tasks that can take many steps to finish → the same computer setup for every AI → websites made for testing → all the files and tasks for free this is also the environment used to test computer-use systems from OpenAI and Anthropic. so if you’re building AI agents, researching computer use, or just want to see what these models can actually do, you can run the same tests yourself instead of relying only on benchmark scores. the labs publish the scores. this repo is where the actual tests come from. bookmark this.

MIKE

14,387 görüntüleme • 16 gün önce

We're excited to announce our partnership with Prime Intellect to allow anyone to train browser agents. General-purpose models aren't optimized for your browser workflows, BrowserEnv lets you train one that is. Checkout and train your own custom model in a few hours.
0:29

We're excited to announce our partnership with Prime Intellect to allow anyone to train browser agents. General-purpose models aren't optimized for your browser workflows, BrowserEnv lets you train one that is. Checkout and train your own custom model in a few hours.

Browserbase

191,891 görüntüleme • 6 ay önce

We just built AWS Lambda with a browser built-in. Introducing Functions, a new compute paradigm that co-locates your code and browsers to build faster browser agents. Functions lets your team focus on the product, while we handle the infrastructure.
0:53

We just built AWS Lambda with a browser built-in. Introducing Functions, a new compute paradigm that co-locates your code and browsers to build faster browser agents. Functions lets your team focus on the product, while we handle the infrastructure.

Browserbase

63,284 görüntüleme • 7 ay önce

After coding is solved, the next frontier is computer use. Today, we are launching Use Computer, the infra for evaluating and training models to use all kinds of computers 👇
0:25

After coding is solved, the next frontier is computer use. Today, we are launching Use Computer, the infra for evaluating and training models to use all kinds of computers 👇

Marco Mascorro

44,641 görüntüleme • 3 ay önce

Claude Fable 5 is now available in Computer as an orchestrator model. This is Anthropic's state-of-the-art model for long, complex tasks. Available only to Pro and Max subscribers in Computer.
0:20

Claude Fable 5 is now available in Computer as an orchestrator model. This is Anthropic's state-of-the-art model for long, complex tasks. Available only to Pro and Max subscribers in Computer.

Perplexity

139,671 görüntüleme • 3 ay önce

For our European friends 🎉 we are rolling out this week Codex for Chrome, Computer Use, Memories, and Chronicle in EU, EEA and UK. Here's a recap on how you can use Codex with Chrome and some more tips below 🧵
2:34

For our European friends 🎉 we are rolling out this week Codex for Chrome, Computer Use, Memories, and Chronicle in EU, EEA and UK. Here's a recap on how you can use Codex with Chrome and some more tips below 🧵

dominik kundel

25,555 görüntüleme • 3 ay önce

Papers With Code SOTA is back 🚀 We used Gemini 3 to process millions of charts and tables across arXiv + the web to surface state-of-the-art AI research in reasoning, computer-use, OCR, and more Track the best-performing methods and see which benchmarks are getting adopted
0:36

Papers With Code SOTA is back 🚀 We used Gemini 3 to process millions of charts and tables across arXiv + the web to surface state-of-the-art AI research in reasoning, computer-use, OCR, and more Track the best-performing methods and see which benchmarks are getting adopted

alphaXiv

17,856 görüntüleme • 10 ay önce

🎮 Computer Use Agent Arena is LIVE! 🚀 🔥 Easiest way to test computer-use agents in the wild without any setup 🌟 Compare top VLMs: OpenAI Operator, Claude 3.7, Gemini 2.5 Pro, Qwen 2.5 vl and more 🕹️ Test agents on 100+ real apps & webs with one-click config 🔒 Safe & free access on cloud-hosted machines Page: Leaderboard (tentative): Blog: Data & Code (coming soon): ⭐️Why Computer Agent Arena? 1️⃣Beyond Static Benchmarks: We use computers to perform enormous tasks and workflows every day, and AI agents have the potential to automate these tasks. However, existing benchmarks are very limited (e.g., only 369 tasks in OSWorld and 812 tasks in WebArena). To better measure their capabilities, we introduce Computer Agent Arena for users to easily compare & test AI agents on all kinds of crowdsourced real-world computer use tasks. 2️⃣Cloud Testing, Simplified: As agents like OpenAI’s Operator and Claude 3.7 sonnet release, users face configuration challenges and privacy hurdles to deploy on their own computers. Our platform integrates these agents with cloud-hosted machines, providing users with quick and secure access. 3️⃣Unified Embodied Digital Environment: Unlike Chatbot Arena, we provide users with a real embodied environment—computers—where all agents are grounded in real computer tasks and environments. Led by @XLANG_Lab [1/🧵]
0:32

🎮 Computer Use Agent Arena is LIVE! 🚀 🔥 Easiest way to test computer-use agents in the wild without any setup 🌟 Compare top VLMs: OpenAI Operator, Claude 3.7, Gemini 2.5 Pro, Qwen 2.5 vl and more 🕹️ Test agents on 100+ real apps & webs with one-click config 🔒 Safe & free access on cloud-hosted machines Page: Leaderboard (tentative): Blog: Data & Code (coming soon): ⭐️Why Computer Agent Arena? 1️⃣Beyond Static Benchmarks: We use computers to perform enormous tasks and workflows every day, and AI agents have the potential to automate these tasks. However, existing benchmarks are very limited (e.g., only 369 tasks in OSWorld and 812 tasks in WebArena). To better measure their capabilities, we introduce Computer Agent Arena for users to easily compare & test AI agents on all kinds of crowdsourced real-world computer use tasks. 2️⃣Cloud Testing, Simplified: As agents like OpenAI’s Operator and Claude 3.7 sonnet release, users face configuration challenges and privacy hurdles to deploy on their own computers. Our platform integrates these agents with cloud-hosted machines, providing users with quick and secure access. 3️⃣Unified Embodied Digital Environment: Unlike Chatbot Arena, we provide users with a real embodied environment—computers—where all agents are grounded in real computer tasks and environments. Led by @XLANG_Lab [1/🧵]

Bowen Wang

93,273 görüntüleme • 1 yıl önce