正在加载视频...

视频加载失败

返回首页

This AI agent just surpassed humans for the first time ever Simular open-sourced Agent S, and scored 72.6% on OSWorld bench vs 72.36% humans, automating your desktop and complex workflows 6 wild examples + how to try: 1. Turn research paper to X thread with assets

dr_cintas's profile picture

Alvaro Cintas

130,461 subscribers

25,438 次观看 • 6 个月前 •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Today marks an important milestone in the history of Simular, the autonomous computer company. Our open source computer-use agent, 𝐀𝐠𝐞𝐧𝐭 𝐒, scored 72.6% on the OSWorld benchmark, surpassing the human baseline (72.36%) for the first time ever. This milestone matters because it shows AI can now use computers the way humans do, and, in many cases, do it better. This is a glimpse of a future where work becomes faster, more accessible, and more empowered for everyone. #AI #Automation #Simular #AgenticAI #ComputerUse
0:53

Today marks an important milestone in the history of Simular, the autonomous computer company. Our open source computer-use agent, 𝐀𝐠𝐞𝐧𝐭 𝐒, scored 72.6% on the OSWorld benchmark, surpassing the human baseline (72.36%) for the first time ever. This milestone matters because it shows AI can now use computers the way humans do, and, in many cases, do it better. This is a glimpse of a future where work becomes faster, more accessible, and more empowered for everyone. #AI #Automation #Simular #AgenticAI #ComputerUse

Simular

839,901 次观看 • 6 个月前

This new Emergent AI agent is wild. It just built me a Spotify replica with authentication using Claude 4, deployed it with 1-click, and uses real data and music. 6 crazy examples + how to try👇:
0:26

This new Emergent AI agent is wild. It just built me a Spotify replica with authentication using Claude 4, deployed it with 1-click, and uses real data and music. 6 crazy examples + how to try👇:

Alvaro Cintas

106,630 次观看 • 1 年前

It's over... for complex prompts. Pika Agent just dropped. You literally talk to your creative partner and create videos, ads, websites, decks and designs. 6 wild examples:
0:30

It's over... for complex prompts. Pika Agent just dropped. You literally talk to your creative partner and create videos, ads, websites, decks and designs. 6 wild examples:

Min Choi

101,608 次观看 • 2 个月前

introducing Agent Workflows: the first ever prompt to workflow tool build complex workflows in 1min form 1 prompt Live today on
0:29

introducing Agent Workflows: the first ever prompt to workflow tool build complex workflows in 1min form 1 prompt Live today on

arcads AI

61,822 次观看 • 2 个月前

OpenAI just released access to Computer Use Agent via an API. It combines GPT-4o vision with advanced reasoning for an AI Agent to simulate controlling computer interfaces and performing tasks just like humans. You can try it for free using this Agent Playground.
1:18

OpenAI just released access to Computer Use Agent via an API. It combines GPT-4o vision with advanced reasoning for an AI Agent to simulate controlling computer interfaces and performing tasks just like humans. You can try it for free using this Agent Playground.

Shubham Saboo

64,206 次观看 • 1 年前

Ok Gamma 3.0 is insane. This AI Agent now researches, reviews, and redesigns your content in real time. And API automates content creation at scale. Wild examples + how to try: 1. Recreate entire deck from prompt
0:49

Ok Gamma 3.0 is insane. This AI Agent now researches, reviews, and redesigns your content in real time. And API automates content creation at scale. Wild examples + how to try: 1. Recreate entire deck from prompt

Min Choi

126,946 次观看 • 9 个月前

When your tool is open source and free, your creativity has no ceiling. The ComfyUI skill in Nous Research Hermes Agent lets you compose sophisticated workflows by chatting to an agent. Try it today.
0:20

When your tool is open source and free, your creativity has no ceiling. The ComfyUI skill in Nous Research Hermes Agent lets you compose sophisticated workflows by chatting to an agent. Try it today.

ComfyUI

162,951 次观看 • 1 个月前

Introducing PaperQA2, the first AI agent that conducts entire scientific literature reviews on its own. PaperQA2 is also the first agent to beat PhD and Postdoc-level biology researchers on multiple literature research tasks, as measured both by accuracy on objective benchmarks and assessments by human experts. We are publishing a paper and open-sourcing the code. This is the first example of AI agents exceeding human performance on a major portion of scientific research, and will be a game-changer for the way humans interact with the scientific literature. Paper and code are below, and congratulations in particular to Michael Skarlinski, Sam Cox, Jon Laurent, James Braza, Michaela Hinks, Michael Hammerling, Manvitha Ponnapati, Andrew White 🐦‍⬛, and others who pulled this off. 1/
0:46

Introducing PaperQA2, the first AI agent that conducts entire scientific literature reviews on its own. PaperQA2 is also the first agent to beat PhD and Postdoc-level biology researchers on multiple literature research tasks, as measured both by accuracy on objective benchmarks and assessments by human experts. We are publishing a paper and open-sourcing the code. This is the first example of AI agents exceeding human performance on a major portion of scientific research, and will be a game-changer for the way humans interact with the scientific literature. Paper and code are below, and congratulations in particular to Michael Skarlinski, Sam Cox, Jon Laurent, James Braza, Michaela Hinks, Michael Hammerling, Manvitha Ponnapati, Andrew White 🐦‍⬛, and others who pulled this off. 1/

Sam Rodriques

555,629 次观看 • 1 年前

We built the first background computer use agent for Windows Trope navigates your desktop, in the background and with multiple cursors Try today, free and open source
2:35

We built the first background computer use agent for Windows Trope navigates your desktop, in the background and with multiple cursors Try today, free and open source

Matt Chow

401,250 次观看 • 2 个月前

🚨 Breaking: Google just open-sourced the Agent Development Kit (ADK) a framework for building AI agents and multi-agent systems. - Build agents in under 100 lines. - Supports MCP More information and how to get started 👇 1/5
0:22

🚨 Breaking: Google just open-sourced the Agent Development Kit (ADK) a framework for building AI agents and multi-agent systems. - Build agents in under 100 lines. - Supports MCP More information and how to get started 👇 1/5

AshutoshShrivastava

130,272 次观看 • 1 年前

Unlock the secret to 100+ hours of productivity with AI workflows that actually work! 💻 Discover how businesses are automating complex tasks in minutes. Key AI Agent Capabilities: • Telegram-based AI communication • Personalized email generation • Intelligent content research • Calendar and email management • Dynamic web scraping Save this video - it will transform your business operations! 🤖 Want the SOP? DM me.
19:35

Unlock the secret to 100+ hours of productivity with AI workflows that actually work! 💻 Discover how businesses are automating complex tasks in minutes. Key AI Agent Capabilities: • Telegram-based AI communication • Personalized email generation • Intelligent content research • Calendar and email management • Dynamic web scraping Save this video - it will transform your business operations! 🤖 Want the SOP? DM me.

Julian Goldie SEO

15,180 次观看 • 1 年前

Unlock the power of your documents. The new Box AI Enhanced Extract Agent, running on Gemini 2.5 Pro and featuring A2A protocol, securely automates data extraction from complex files. A game-changer for automating workflows and ensuring compliance →
1:21

Unlock the power of your documents. The new Box AI Enhanced Extract Agent, running on Gemini 2.5 Pro and featuring A2A protocol, securely automates data extraction from complex files. A game-changer for automating workflows and ensuring compliance →

Google Cloud

109,204 次观看 • 1 年前

This is wild. MiniMax-M1 just dropped. This AI agent = Manus + Deep Research + Computer Use + Lovable in one. 1M token memory, open weights🤯 10 wild examples + prompts & demo: 1. Netflix clone with playable trailers
0:28

This is wild. MiniMax-M1 just dropped. This AI agent = Manus + Deep Research + Computer Use + Lovable in one. 1M token memory, open weights🤯 10 wild examples + prompts & demo: 1. Netflix clone with playable trailers

Min Choi

539,094 次观看 • 1 年前

Genspark AI agent just released AI Sheets. You can now upload any data and the agent automatically analyzes it, generates reports, and can research the web to find the data for you. 5 powerful use cases + how to try👇:
0:23

Genspark AI agent just released AI Sheets. You can now upload any data and the agent automatically analyzes it, generates reports, and can research the web to find the data for you. 5 powerful use cases + how to try👇:

Alvaro Cintas

110,569 次观看 • 1 年前

Trade research drudgery for research breakthroughs — @SciSpace_ Agent gives back an average of 1300 hours a year to researchers. SciSpace Agent is the first #AI built exclusively for the scientific research community. Learn more about your new AI co-scientist in this thread.
4:00

Trade research drudgery for research breakthroughs — @SciSpace_ Agent gives back an average of 1300 hours a year to researchers. SciSpace Agent is the first #AI built exclusively for the scientific research community. Learn more about your new AI co-scientist in this thread.

Kirk Borne

11,871 次观看 • 11 个月前

We've been using Cua-Bench internally—and with customers—for the last few months to evaluate every computer-use agent we deploy. Today it's open-source. 15 public tasks, 40 variations, adapters for OSWorld and Windows Agent Arena. One CLI, self-hostable.
0:49

We've been using Cua-Bench internally—and with customers—for the last few months to evaluate every computer-use agent we deploy. Today it's open-source. 15 public tasks, 40 variations, adapters for OSWorld and Windows Agent Arena. One CLI, self-hostable.

Cua

87,427 次观看 • 5 个月前

This is wild. Manus Agent Skills actually execute end-to-end in a secure sandbox, an executable SOPs. Sandboxed, load on-demand, and shareable across a team. Wild examples + how to try (get 1,000 credit redeem code in the comments)👇 1. Content research → Newsletter #ad
0:29

This is wild. Manus Agent Skills actually execute end-to-end in a secure sandbox, an executable SOPs. Sandboxed, load on-demand, and shareable across a team. Wild examples + how to try (get 1,000 credit redeem code in the comments)👇 1. Content research → Newsletter #ad

Min Choi

115,440 次观看 • 5 个月前

Turn your AI agent into an Elastic expert. Elastic Agent Skills puts native platform expertise in your agent, built by the engineers who develop and ship Elastic. - Accurate ES|QL. - Correct Kibana dashboards. - Security and observability workflows that run correctly, first time.
1:03

Turn your AI agent into an Elastic expert. Elastic Agent Skills puts native platform expertise in your agent, built by the engineers who develop and ship Elastic. - Accurate ES|QL. - Correct Kibana dashboards. - Security and observability workflows that run correctly, first time.

Elastic Dev

1,294,260 次观看 • 3 个月前

We just open-sourced Simulang, a JavaScript library that gives you and your coding agents the ability to fully control computers. Simulang is our scripting framework for desktop automation. It allows you to write deterministic computer use code that can be replayed dozens if not hundreds of times. Much faster and cheaper, compared to LLM agents. It ships with a skill out of the box. That means you can turn natural language prompts into Simulang code directly, and your agent can now see the screen, click, type, and navigate. It gives your AI agents eyes and hands to control the computer like humans do. Try these things with Simulang: - upload your pile of invoices to the expense platform - find 50 people with specific criteria on LinkedIn - open your calculator app and do some math - find all buttons on your favorite app using accessibility tree - or draw a bunny with MS paint 🐰 In this demo, we show how Simulang took over when the coding agent couldn’t open and click on the target LinkedIn profile page. Give it a try:
1:08

We just open-sourced Simulang, a JavaScript library that gives you and your coding agents the ability to fully control computers. Simulang is our scripting framework for desktop automation. It allows you to write deterministic computer use code that can be replayed dozens if not hundreds of times. Much faster and cheaper, compared to LLM agents. It ships with a skill out of the box. That means you can turn natural language prompts into Simulang code directly, and your agent can now see the screen, click, type, and navigate. It gives your AI agents eyes and hands to control the computer like humans do. Try these things with Simulang: - upload your pile of invoices to the expense platform - find 50 people with specific criteria on LinkedIn - open your calculator app and do some math - find all buttons on your favorite app using accessibility tree - or draw a bunny with MS paint 🐰 In this demo, we show how Simulang took over when the coding agent couldn’t open and click on the target LinkedIn profile page. Give it a try:

Simular

14,362 次观看 • 1 个月前

HERMES AGENT JUST GOT A FULL NATIVE DESKTOP APP. MULTI-AGENT MANAGEMENT, PERSISTENT MEMORY AND AUTONOMOUS WORKFLOWS ALL IN ONE PLACE. No more CLI only. Run your 24/7 self-evolving AI agent from a proper desktop UI.
0:34

HERMES AGENT JUST GOT A FULL NATIVE DESKTOP APP. MULTI-AGENT MANAGEMENT, PERSISTENT MEMORY AND AUTONOMOUS WORKFLOWS ALL IN ONE PLACE. No more CLI only. Run your 24/7 self-evolving AI agent from a proper desktop UI.

0xMarioNawfal

187,699 次观看 • 1 个月前