Загрузка видео...

Не удалось загрузить видео

На главную

FDM-1 completes complex tasks and navigates interfaces well enough to use CAD applications. Forking VMs allow us to snapshot when a successful operation completes (extrusion, selection, etc.), letting us apply test-time compute to computer use.

si_pbc's profile picture

Standard Intelligence

10,409 subscribers

59,736 просмотров • 6 месяцев назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Open Computer Agent - LLMs completing tasks using a VM. It's playground to test how well current LLM agents use a computer to solve everyday tasks. And this is just the start - very soon models will be 10x faster and 10x better at it! ❤️ built with e2b x qwen2.5-vl x smolagent
0:25

Open Computer Agent - LLMs completing tasks using a VM. It's playground to test how well current LLM agents use a computer to solve everyday tasks. And this is just the start - very soon models will be 10x faster and 10x better at it! ❤️ built with e2b x qwen2.5-vl x smolagent

Leandro von Werra

17,126 просмотров • 1 год назад

Our first short course with Anthropic! Building Towards Computer Use with Anthropic. This teaches you to build an LLM-based agent that uses a computer interface by generating mouse clicks and keystrokes. Computer Use is an important, emerging capability for LLMs that will let AI agents do many more tasks than were possible before, since it lets them interact with interfaces designed for humans to use, rather than only tools that provide explicit API access. I hope you will enjoy learning about it! This course is taught by Anthropic's Head of Curriculum, Colt_Steele. You'll learn to apply image reasoning and tool use to "use" a computer as follows: a model processes an image of the screen, analyzes it to understand what's going on, and navigates the computer via mouse clicks and keystrokes. This course goes through the key building blocks, and culminates in a demo of an AI assistant that uses a web browser to search for a research paper, downloads the PDF, and finally summarizes the paper for you. In detail, you’ll: - Learn about Anthropic's family of models, when to use which one, and make API requests to Claude - Use multi-modal prompts that combine text and image content blocks, and also work with streaming responses - Improve your prompting by using prompt templates, using XML to structure prompts, and providing examples - Implement prompt caching to reduce cost and latency - Apply tool-use to build a chatbot that can call different tools to respond to queries - See all these building blocks come together in Computer Use demo Please sign up here:
1:56

Our first short course with Anthropic! Building Towards Computer Use with Anthropic. This teaches you to build an LLM-based agent that uses a computer interface by generating mouse clicks and keystrokes. Computer Use is an important, emerging capability for LLMs that will let AI agents do many more tasks than were possible before, since it lets them interact with interfaces designed for humans to use, rather than only tools that provide explicit API access. I hope you will enjoy learning about it! This course is taught by Anthropic's Head of Curriculum, Colt_Steele. You'll learn to apply image reasoning and tool use to "use" a computer as follows: a model processes an image of the screen, analyzes it to understand what's going on, and navigates the computer via mouse clicks and keystrokes. This course goes through the key building blocks, and culminates in a demo of an AI assistant that uses a web browser to search for a research paper, downloads the PDF, and finally summarizes the paper for you. In detail, you’ll: - Learn about Anthropic's family of models, when to use which one, and make API requests to Claude - Use multi-modal prompts that combine text and image content blocks, and also work with streaming responses - Improve your prompting by using prompt templates, using XML to structure prompts, and providing examples - Implement prompt caching to reduce cost and latency - Apply tool-use to build a chatbot that can call different tools to respond to queries - See all these building blocks come together in Computer Use demo Please sign up here:

Andrew Ng

170,425 просмотров • 1 год назад

This might be the most advanced AI agent to date. It’s called Runner H by H, and it automates complex, multi-step tasks from just a prompt. You basically describe what you want and it takes over your computer to complete it. Some key features: - Outperforms competitors like Anthropic’s Computer Use on the WebVoyager benchmark. - Navigates web interfaces through pixel-level interpretation and semantic understanding. - Adapts to UI changes automatically. - Handles complex workflows like e-commerce and financial services onboarding. They have already raised $220M and looks like we are entering the agentic era! You can sign up to their waitlist now (link below).
1:04

This might be the most advanced AI agent to date. It’s called Runner H by H, and it automates complex, multi-step tasks from just a prompt. You basically describe what you want and it takes over your computer to complete it. Some key features: - Outperforms competitors like Anthropic’s Computer Use on the WebVoyager benchmark. - Navigates web interfaces through pixel-level interpretation and semantic understanding. - Adapts to UI changes automatically. - Handles complex workflows like e-commerce and financial services onboarding. They have already raised $220M and looks like we are entering the agentic era! You can sign up to their waitlist now (link below).

Alvaro Cintas

86,907 просмотров • 1 год назад

Internet Computer's Caffeine is Now Available in Claude Internet Computer (DFINITY Foundation)'s Caffeine launches a direct integration with Anthropic’s Claude, enabling the instantaneous generation of production-ready applications through natural language interfaces. This deployment enables "vibe coders" and enterprise teams to use caffeine’s modular frameworks to build, iterate on, and deploy complex software without leaving the LLM environment.
0:30

Internet Computer's Caffeine is Now Available in Claude Internet Computer (DFINITY Foundation)'s Caffeine launches a direct integration with Anthropic’s Claude, enabling the instantaneous generation of production-ready applications through natural language interfaces. This deployment enables "vibe coders" and enterprise teams to use caffeine’s modular frameworks to build, iterate on, and deploy complex software without leaving the LLM environment.

BSCN

31,877 просмотров • 2 месяцев назад

🎮 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

93,200 просмотров • 1 год назад

1/ Today was the first time offline computer use felt real to us. We ran Muse Glimmer 30B from AI at Meta locally and watched it operate Notes and Reminders on macOS through Cua Driver We didn’t expect a 30B local model to get this far 🧵
0:26

1/ Today was the first time offline computer use felt real to us. We ran Muse Glimmer 30B from AI at Meta locally and watched it operate Notes and Reminders on macOS through Cua Driver We didn’t expect a 30B local model to get this far 🧵

Francesco

30,326 просмотров • 20 дней назад

“We don’t allow our artists to grow, and we criticize them when they do,” ashy daddy says. He told us about the value of letting artists evolve and change over time, adding, “We need to carry our artists in a different way.”
0:41

“We don’t allow our artists to grow, and we criticize them when they do,” ashy daddy says. He told us about the value of letting artists evolve and change over time, adding, “We need to carry our artists in a different way.”

Pigeons & Planes

21,565 просмотров • 5 месяцев назад

“… When the time is right, and it won't be that far away, when we'll use the US Navy to escort ships through the Straits of Hormuz […] … Fortunately , we have the world just massively well-supplied […] I’ll be a bump in the road…”
1:44

“… When the time is right, and it won't be that far away, when we'll use the US Navy to escort ships through the Straits of Hormuz […] … Fortunately , we have the world just massively well-supplied […] I’ll be a bump in the road…”

Javier Blas

61,579 просмотров • 5 месяцев назад

Perhaps the most well known abductee on the planet discussing the aliens using us as a FOOD SOURCE from time to time, and while they're looking for companions, if they can't get companions they'll STEAL OUR SOULS and use us as slaves. And these are the good guys?
1:04

Perhaps the most well known abductee on the planet discussing the aliens using us as a FOOD SOURCE from time to time, and while they're looking for companions, if they can't get companions they'll STEAL OUR SOULS and use us as slaves. And these are the good guys?

Fringe

83,671 просмотров • 1 год назад

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 просмотров • 1 год назад

Putin says Russia test-fired a new ballistic missile at the Yuzhmash factory in Ukraine. This is his response to the US and UK letting Ukraine hit targets in Russia with advanced weapons. He says Russia has the right to target countries that let Ukraine use their weapons.
7:45

Putin says Russia test-fired a new ballistic missile at the Yuzhmash factory in Ukraine. This is his response to the US and UK letting Ukraine hit targets in Russia with advanced weapons. He says Russia has the right to target countries that let Ukraine use their weapons.

max seddon

232,225 просмотров • 1 год назад

I believe a big part of "The Plan" is awakening people to not only the corruption, but also to our true nature which has been hidden from us. WE CREATE THIS REALITY WITH OUR CONSCIOUSNESS. When enough of us understand this and use our FOCUS to do that, we will enter the highest timeline.
4:23

I believe a big part of "The Plan" is awakening people to not only the corruption, but also to our true nature which has been hidden from us. WE CREATE THIS REALITY WITH OUR CONSCIOUSNESS. When enough of us understand this and use our FOCUS to do that, we will enter the highest timeline.

Sanders Parker

11,491 просмотров • 2 месяцев назад

Local Autonomous Agent for All of Us Browser-Use Web UI is a gradio app that uses LLMs to automatically surf the web to achieve tasks. All you need to do is just tell it what to do. It works like magic. And now anyone can run it locally with 1 click.
0:31

Local Autonomous Agent for All of Us Browser-Use Web UI is a gradio app that uses LLMs to automatically surf the web to achieve tasks. All you need to do is just tell it what to do. It works like magic. And now anyone can run it locally with 1 click.

cocktail peanut

40,782 просмотров • 1 год назад

Fun Fact: The Declaration of Independence explicitly enshrines the right of the people to overthrow a despotic government. Americans today have been conditioned to think revolution is “radical” when it is a right and duty our founders gave us. It’s time to use it!
0:45

Fun Fact: The Declaration of Independence explicitly enshrines the right of the people to overthrow a despotic government. Americans today have been conditioned to think revolution is “radical” when it is a right and duty our founders gave us. It’s time to use it!

Power to the People ☭🕊

14,449 просмотров • 3 месяцев назад

Zack Polanski, "Why does it seem that our government is incapable of standing up to a US president?" Jeremy Corbyn, "It's in the psychology of the Ministry of Defence, the Foreign Office, a pro-US position" "There's this assumption that we will always be close to the US, whatever it does" "So when the US comes along with something utterly absurd and bizarre, like the bombing of Iran. For what?" "They can't actually give a rational reason for bombing Iran" "On one side they say to get rid of Iran's nuclear weapons, when they knew full well that Iran doesn't have any nuclear weapons" "They then said we have to bomb Iran and the British government said they are not involved in this. Yet, at the same time allow US forces to use British bases" "More specifically, Trump goes onto Andy Burnham the day after he's become Prime Minister and says, can we use RAF bases for US planes to take off and bomb Iran, but don't worry its only defensive" "What was Burnham doing agreeing to that?"
2:13

Zack Polanski, "Why does it seem that our government is incapable of standing up to a US president?" Jeremy Corbyn, "It's in the psychology of the Ministry of Defence, the Foreign Office, a pro-US position" "There's this assumption that we will always be close to the US, whatever it does" "So when the US comes along with something utterly absurd and bizarre, like the bombing of Iran. For what?" "They can't actually give a rational reason for bombing Iran" "On one side they say to get rid of Iran's nuclear weapons, when they knew full well that Iran doesn't have any nuclear weapons" "They then said we have to bomb Iran and the British government said they are not involved in this. Yet, at the same time allow US forces to use British bases" "More specifically, Trump goes onto Andy Burnham the day after he's become Prime Minister and says, can we use RAF bases for US planes to take off and bomb Iran, but don't worry its only defensive" "What was Burnham doing agreeing to that?"

Farrukh

18,391 просмотров • 3 дней назад

🚨BREAKING NEWS Iranian Parliament member Boroujerdi: "We are not pursuing a nuclear bomb. But when they come and bomb us and threaten to use nuclear bombs against us, we will not abide by the rules of the game. To summarize in one sentence, the time has come to withdraw from the Nuclear Non-Proliferation Treaty."
2:32

🚨BREAKING NEWS Iranian Parliament member Boroujerdi: "We are not pursuing a nuclear bomb. But when they come and bomb us and threaten to use nuclear bombs against us, we will not abide by the rules of the game. To summarize in one sentence, the time has come to withdraw from the Nuclear Non-Proliferation Treaty."

Aleksey The Great 🇷🇺🎖

142,330 просмотров • 5 месяцев назад

OpenAI just announced API access to o1 (advanced reasoning model) yesterday. I'm delighted to announce today a new short course, Reasoning with o1, built with OpenAI, and taught by Colin Jarvis, Head of AI Solutions at OpenAI, to show you how to use this effectively! Unlike previous language models which generate output directly, o1 “thinks before it responds,” and generates many reasoning tokens before returning a more thoughtful and accurate response. It is great at complex reasoning -- including planning for agentic workflows, coding, and domain-specific reasoning in STEM fields like law. But how you should use it is quite different from other LLMs. I think o1 will be a game changer for many AI applications; and in this course, you'll learn how to use it effectively. In detail, you’ll: - Learn to recognize what tasks o1 is suited for, and when to use a smaller model, or combine o1 with a smaller model - Understand the new principles of prompting reasoning models: Be simple and direct; no explicit chain-of-thought required; use structure; show rather than tell - Implement multi-step orchestration in which o1 plans, and hands tasks over to gpt-4o-mini to execute specific steps; this illustrates a design pattern to optimize intelligence (accuracy) and cost - Use o1 for a coding task to build a new application, edit existing code, and test performance by running a coding competition between o1-mini and GPT 4o - Use o1 for image understanding and learn how it performs better with a "hierarchy of reasoning," in which it incurs the latency and cost upfront, preprocessing the image and indexing it with rich details so it can be used for Q&A later - Learn a technique called meta-prompting, in which you use o1 to improve your prompts. Using a customer support evaluation set, you'll iteratively use o1 to modify a prompt to improve performance You'll also learn about how OpenAI used reinforcement learning to produce a model that uses "test-time compute" to improve performance. I think you'll find this course enjoyable and valuable. Please sign up for it here:
3:07

OpenAI just announced API access to o1 (advanced reasoning model) yesterday. I'm delighted to announce today a new short course, Reasoning with o1, built with OpenAI, and taught by Colin Jarvis, Head of AI Solutions at OpenAI, to show you how to use this effectively! Unlike previous language models which generate output directly, o1 “thinks before it responds,” and generates many reasoning tokens before returning a more thoughtful and accurate response. It is great at complex reasoning -- including planning for agentic workflows, coding, and domain-specific reasoning in STEM fields like law. But how you should use it is quite different from other LLMs. I think o1 will be a game changer for many AI applications; and in this course, you'll learn how to use it effectively. In detail, you’ll: - Learn to recognize what tasks o1 is suited for, and when to use a smaller model, or combine o1 with a smaller model - Understand the new principles of prompting reasoning models: Be simple and direct; no explicit chain-of-thought required; use structure; show rather than tell - Implement multi-step orchestration in which o1 plans, and hands tasks over to gpt-4o-mini to execute specific steps; this illustrates a design pattern to optimize intelligence (accuracy) and cost - Use o1 for a coding task to build a new application, edit existing code, and test performance by running a coding competition between o1-mini and GPT 4o - Use o1 for image understanding and learn how it performs better with a "hierarchy of reasoning," in which it incurs the latency and cost upfront, preprocessing the image and indexing it with rich details so it can be used for Q&A later - Learn a technique called meta-prompting, in which you use o1 to improve your prompts. Using a customer support evaluation set, you'll iteratively use o1 to modify a prompt to improve performance You'll also learn about how OpenAI used reinforcement learning to produce a model that uses "test-time compute" to improve performance. I think you'll find this course enjoyable and valuable. Please sign up for it here:

Andrew Ng

357,661 просмотров • 1 год назад