Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

🚀 Introducing 𝐀𝐠𝐞𝐧𝐭 𝐒3, the most advanced computer-use agent, now 𝐚𝐩𝐩𝐫𝐨𝐚𝐜𝐡𝐢𝐧𝐠 𝐡𝐮𝐦𝐚𝐧-𝐥𝐞𝐯𝐞𝐥 𝐩𝐞𝐫𝐟𝐨𝐫𝐦𝐚𝐧𝐜𝐞🧠💻 Just one year ago, Agent S scored ~20% on OSWorld: SOTA then, but far from human 72%. Today, Agent S3 reaches 6̳9̳.̳9̳%̳ (⬆10% over prior SOTA), nearly matching humans on computer use. Few imagined this gap... could close so fast, but with steady progress and 𝐟𝐢𝐫𝐬𝐭-𝐩𝐫𝐢𝐧𝐜𝐢𝐩𝐥𝐞 simplicity, Simular did it in just one year. 🧪 The s̵e̵c̵r̵e̵t̵ 𝐨𝐩𝐞𝐧 𝐫𝐞𝐜𝐢𝐩𝐞: → 𝐁𝐞𝐡𝐚𝐯𝐢𝐨𝐫 𝐁𝐞𝐬𝐭-𝐨𝐟-𝐍 — scaling agents 𝘵𝘩𝘦 𝘳𝘪𝘨𝘩𝘵 𝘸𝘢𝘺 → Simpler design, stronger baseline → 100% 𝐨𝐩𝐞𝐧 𝐬𝐨𝐮𝐫𝐜𝐞 (as always) Learn more at & 👇show more

Xin Eric Wang (hiring postdoc)

20,965 subscribers

913,279 Aufrufe • vor 9 Monaten •via X (Twitter)

Gesundheit & Wellness Wissenschaft & Technologie Bildung

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Announcing Agent S3 — our most advanced computer-use agent yet — achieving 69.9% on OSWorld, just shy of the 72% human benchmark. Today also marks one year since Simular launched the first generation of Agent S. From 20% to 69.9% in just twelve months. What a year. Let that sink in. 🧠💻 🧵👇

Announcing Agent S3 — our most advanced computer-use agent yet — achieving 69.9% on OSWorld, just shy of the 72% human benchmark. Today also marks one year since Simular launched the first generation of Agent S. From 20% to 69.9% in just twelve months. What a year. Let that sink in. 🧠💻 🧵👇

Ang Li

444,496 Aufrufe • vor 9 Monaten

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

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 Aufrufe • vor 6 Monaten

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.

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 Aufrufe • vor 1 Jahr

Computer use agents are slow and brittle. The fix isn’t just stronger models, but also deploying them as multi-agent systems. MACU is a general Multi-Agent Computer Use framework that consistently lifts success rates by 3.4-25.5% and is up to 1.5x faster on long-horizon tasks.🧵

Computer use agents are slow and brittle. The fix isn’t just stronger models, but also deploying them as multi-agent systems. MACU is a general Multi-Agent Computer Use framework that consistently lifts success rates by 3.4-25.5% and is up to 1.5x faster on long-horizon tasks.🧵

Jing Yu Koh

27,760 Aufrufe • vor 27 Tagen

This AI doesn’t just automate. It uses your computer like a human clicks, types, navigates all from a simple prompt. Meet Simular Pro, the first production-grade computer-use agent. It runs thousands of steps, 24/7, so you don’t have to. How? Most agents flake. Simular Pro doesn’t. It combines two agents: 🧠 Neural (explores) ⚙️ Symbolic (executes) Every action = editable, deterministic code. Here’s how Simular works ↓

This AI doesn’t just automate. It uses your computer like a human clicks, types, navigates all from a simple prompt. Meet Simular Pro, the first production-grade computer-use agent. It runs thousands of steps, 24/7, so you don’t have to. How? Most agents flake. Simular Pro doesn’t. It combines two agents: 🧠 Neural (explores) ⚙️ Symbolic (executes) Every action = editable, deterministic code. Here’s how Simular works ↓

FELIX

76,011 Aufrufe • vor 11 Monaten

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

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

Alvaro Cintas

25,438 Aufrufe • vor 6 Monaten

Two years ago, we built OSWorld 1.0 — the benchmark that became the standard for computer-use agents. Agents now score 83.5% on it. Problem solved? Not even close. 🚀Today we introduce OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks. What's new: 🎯 108 real-world workflows, each ~1.6 hours ⏱️ for a skilled human ⚙️ ~318 tool calls/task vs. ~30 in OSWorld 1.0 🌍 Grounded in authentic artifacts & stateful user profiles ⚡ Captures real phenomena: dynamic environments, streaming interaction, cross-source reasoning, implicit-state inference & more 📊 Best results: Claude Opus 4.8 reaches the highest accuracy at 20.6%, while GPT-5.5 is far more token-efficient but plateaus near 13%. No one is close to solving real computer use. 🏠 Homepage: 📄 Paper: 💻 Code: 🤗 Dataset: 🧵 [1/8]

Two years ago, we built OSWorld 1.0 — the benchmark that became the standard for computer-use agents. Agents now score 83.5% on it. Problem solved? Not even close. 🚀Today we introduce OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks. What's new: 🎯 108 real-world workflows, each ~1.6 hours ⏱️ for a skilled human ⚙️ ~318 tool calls/task vs. ~30 in OSWorld 1.0 🌍 Grounded in authentic artifacts & stateful user profiles ⚡ Captures real phenomena: dynamic environments, streaming interaction, cross-source reasoning, implicit-state inference & more 📊 Best results: Claude Opus 4.8 reaches the highest accuracy at 20.6%, while GPT-5.5 is far more token-efficient but plateaus near 13%. No one is close to solving real computer use. 🏠 Homepage: 📄 Paper: 💻 Code: 🤗 Dataset: 🧵 [1/8]

XLANG NLP Lab

140,789 Aufrufe • vor 4 Tagen

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.

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 Aufrufe • vor 5 Monaten

one year later: ryOS can now run classic Mac OS (System 1 – 10.4) with a full computer-use agent and it all started from one tiny soundboard app...

one year later: ryOS can now run classic Mac OS (System 1 – 10.4) with a full computer-use agent and it all started from one tiny soundboard app...

Ryo Lu

38,685 Aufrufe • vor 5 Monaten

1/ Introducing Agent Protocol: the payment stack for AI agents AI agents don’t have a SSN. They can’t use our human banking system. AI agents will use crypto. Agent Protocol provides the infra and token ($AGENT) that the AI agent economy will run on.

1/ Introducing Agent Protocol: the payment stack for AI agents AI agents don’t have a SSN. They can’t use our human banking system. AI agents will use crypto. Agent Protocol provides the infra and token ($AGENT) that the AI agent economy will run on.

Samuel Spitz

21,629 Aufrufe • vor 1 Jahr

Announcing a new chapter for AI agents: Lindy 3.0. Our vision has always been the "Al employee": as capable as humans (can do anything on a computer) and as easy to use (just ask). 3.0 takes 3 giant steps in this direction, with Agent Builder, Autopilot, and Team Collaboration.

Announcing a new chapter for AI agents: Lindy 3.0. Our vision has always been the "Al employee": as capable as humans (can do anything on a computer) and as easy to use (just ask). 3.0 takes 3 giant steps in this direction, with Agent Builder, Autopilot, and Team Collaboration.

Flo Crivello

644,547 Aufrufe • vor 11 Monaten

🚨 BREAKING: Hugging Face just dropped a free AI agent that uses a computer like a human. It’s called Open Computer Agent, and it mimics real computer use. You can run it in your browser no install required. Here's everything you need to know:

🚨 BREAKING: Hugging Face just dropped a free AI agent that uses a computer like a human. It’s called Open Computer Agent, and it mimics real computer use. You can run it in your browser no install required. Here's everything you need to know:

Ihtesham Haider

245,607 Aufrufe • vor 1 Jahr

🚀 We just shipped a major update to LangSmith Agent Builder: • New agent chat: One always-available agent with access to all your workspace tools • Chat → Agent: Turn any conversation into a specialized agent with one click • File uploads: Attach files directly to Agent Builder • Tool registry: Add, authenticate, and manage your tools in one place Try it now: Learn more:

🚀 We just shipped a major update to LangSmith Agent Builder: • New agent chat: One always-available agent with access to all your workspace tools • Chat → Agent: Turn any conversation into a specialized agent with one click • File uploads: Attach files directly to Agent Builder • Tool registry: Add, authenticate, and manage your tools in one place Try it now: Learn more:

LangChain

24,885,978 Aufrufe • vor 4 Monaten

so Lightcone is the fastest computer use agent in the world and watching it do the boring stuff this fast is genuinely kind of insane. and it's only getting faster and more reliable.

so Lightcone is the fastest computer use agent in the world and watching it do the boring stuff this fast is genuinely kind of insane. and it's only getting faster and more reliable.

noah

48,414 Aufrufe • vor 1 Monat

working with cloud agents in cursor feels the same as local, but the fact that i can shut down my computer and still have it running is amazing. one of my favorite use cases is planning in cursor, then send off to cloud agent for impl. here's a short demo

working with cloud agents in cursor feels the same as local, but the fact that i can shut down my computer and still have it running is amazing. one of my favorite use cases is planning in cursor, then send off to cloud agent for impl. here's a short demo

eric zakariasson

61,940 Aufrufe • vor 8 Monaten

Our latest LangChain Academy course – Building Ambient Agents with LangGraph – is now available! Most agents today handle one request at a time through chat interfaces. But as models have improved, agents can now run in the background – and take on long-running, complex tasks. LangGraph is built for these “ambient agents,” with support for human-in-the-loop workflows and memory. LangGraph Platform provides the infrastructure to run these agents at scale, and LangSmith helps you observe, evaluate, and improve your agents. Together, they make it easier to build reliable, production-ready agents. In this course, you’ll: 📩 Learn the fundamentals of LangGraph and how to build your own email agent 📊 Evaluate your agent using LangSmith ✅ Add human-in-the-loop for reviews, and memory so your agent adapts over time 🚀 Deploy your agent with LangGraph Platform and connect it to Gmail

Our latest LangChain Academy course – Building Ambient Agents with LangGraph – is now available! Most agents today handle one request at a time through chat interfaces. But as models have improved, agents can now run in the background – and take on long-running, complex tasks. LangGraph is built for these “ambient agents,” with support for human-in-the-loop workflows and memory. LangGraph Platform provides the infrastructure to run these agents at scale, and LangSmith helps you observe, evaluate, and improve your agents. Together, they make it easier to build reliable, production-ready agents. In this course, you’ll: 📩 Learn the fundamentals of LangGraph and how to build your own email agent 📊 Evaluate your agent using LangSmith ✅ Add human-in-the-loop for reviews, and memory so your agent adapts over time 🚀 Deploy your agent with LangGraph Platform and connect it to Gmail

LangChain

33,192 Aufrufe • vor 1 Jahr

We’ve been working with OpenAI for the past few weeks to test their latest Computer-using Agent model. On our evals, CUA has set a new SOTA. Once integrated with an agent, it can complete long-horizon tasks previously impossible. Try CUA on our playground and Act SDK for free!

We’ve been working with OpenAI for the past few weeks to test their latest Computer-using Agent model. On our evals, CUA has set a new SOTA. Once integrated with an agent, it can complete long-horizon tasks previously impossible. Try CUA on our playground and Act SDK for free!

Scrapybara

89,458 Aufrufe • vor 1 Jahr

Flowith just dropped Agent Neo and the gap between human jobs and AI just narrowed dramatically. Been using it for a week now and it's freaking nuts. - UNLIMITED workflow steps, can runs for hours - Cloud execution for intensive tasks - Nested agent hierarchies with sub-agents - Knowledge marketplace to monetize expertise I built this entire game design document in one prompt. More details below: 👇

Flowith just dropped Agent Neo and the gap between human jobs and AI just narrowed dramatically. Been using it for a week now and it's freaking nuts. - UNLIMITED workflow steps, can runs for hours - Cloud execution for intensive tasks - Nested agent hierarchies with sub-agents - Knowledge marketplace to monetize expertise I built this entire game design document in one prompt. More details below: 👇

AshutoshShrivastava

81,440 Aufrufe • vor 1 Jahr

Computer use with any model Hermes Agent × Cua

Computer use with any model Hermes Agent × Cua

Nous Research

1,090,607 Aufrufe • vor 1 Monat

I can't tell you the last time I was so excited to see a new AI capability in action. We plugged in Claude computer use in Replit ⠕ Agent as a human feedback replacement. And… it just works! I feel it won't take long until our agent will become fully autonomous.

I can't tell you the last time I was so excited to see a new AI capability in action. We plugged in Claude computer use in Replit ⠕ Agent as a human feedback replacement. And… it just works! I feel it won't take long until our agent will become fully autonomous.

Michele Catasta

185,920 Aufrufe • vor 1 Jahr