Загрузка видео...

Не удалось загрузить видео

На главную

first agentic tool use demo

0xKyon's profile picture

kyon

9,085 subscribers

14,368 просмотров • 1 год назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 11

Фото профиля kyon
kyon1 год назад

no external libs for agentic behavior tool calls made on sandboxed worker with isolated perms

Фото профиля verrsane
verrsane1 год назад

Bro is putting me to shame

Фото профиля thegeneralist
thegeneralist1 год назад

this is fire kyon you are cooking

Фото профиля Kristof
Kristof1 год назад

A builder in a world of larpers

Фото профиля Miguel Ángel
Miguel Ángel1 год назад

man you really cooked here, looks amazing 🗣️

Фото профиля 🃏
🃏1 год назад

🔥

Фото профиля zan
zan1 год назад

What's tool did the programmer use

Фото профиля Himanshu Kumar
Himanshu Kumar1 год назад

Clever! Object manipulation suggests planning.

Фото профиля iMuffin
iMuffin1 год назад

Where do I signup?

Фото профиля Eriiiiiiiick
Eriiiiiiiick1 год назад

what browswer?

Фото профиля kyon
kyon1 год назад

attempting to build one

Похожие видео

Grok 4.1 Fast Reasoning outperforms every Frontier model on τ²-Bench Telecom agentic tool use and is now officially ranked #1
0:30

Grok 4.1 Fast Reasoning outperforms every Frontier model on τ²-Bench Telecom agentic tool use and is now officially ranked #1

X Freeze

7,109,789 просмотров • 7 месяцев назад

With Llama 3.2 we released our first-ever lightweight Llama models: 1B & 3B. These models empower developers to build personalized, on-device agentic applications with capabilities like summarization, tool use and RAG where data never leaves the device.
0:45

With Llama 3.2 we released our first-ever lightweight Llama models: 1B & 3B. These models empower developers to build personalized, on-device agentic applications with capabilities like summarization, tool use and RAG where data never leaves the device.

AI at Meta

153,396 просмотров • 1 год назад

Every millisecond counts for voice agents. Introducing Gemma 4 31B on LiveKit Inference! Optimized for real-time voice agents: - 354ms time to first audio - 192ms time to first token - Beats GPT-4.1 in agentic tool use (31B achieves 76.9% on tau2bench) Fast, capable, and efficient!
0:57

Every millisecond counts for voice agents. Introducing Gemma 4 31B on LiveKit Inference! Optimized for real-time voice agents: - 354ms time to first audio - 192ms time to first token - Beats GPT-4.1 in agentic tool use (31B achieves 76.9% on tau2bench) Fast, capable, and efficient!

Google Gemma

217,192 просмотров • 5 дней назад

Machine tool motor synchronization demo.
0:23

Machine tool motor synchronization demo.

MachinePix

37,244 просмотров • 5 месяцев назад

Welcome to the world, Gemini 2.0 ✨ our most capable AI model yet. We're first releasing an experimental version of 2.0 Flash ⚡ It has better performance, new multimodal output, Google tool use - and paves the way for new agentic experiences. 🧵
2:52

Welcome to the world, Gemini 2.0 ✨ our most capable AI model yet. We're first releasing an experimental version of 2.0 Flash ⚡ It has better performance, new multimodal output, Google tool use - and paves the way for new agentic experiences. 🧵

Google DeepMind

365,320 просмотров • 1 год назад

MiniMax released M2.5, and it’s clearly optimized for the agentic era: coding + tool use + research + office workflows in one model. We built a three.js demo of a coastal power and water system, featuring real-time visuals, live simulations, and integrated dashboards in a production-quality web experience. All generated from one prompt.
0:47

MiniMax released M2.5, and it’s clearly optimized for the agentic era: coding + tool use + research + office workflows in one model. We built a three.js demo of a coastal power and water system, featuring real-time visuals, live simulations, and integrated dashboards in a production-quality web experience. All generated from one prompt.

Chubby♨️

16,698 просмотров • 4 месяцев назад

First look at the tool I use to automate production for Matcherino tournaments
13:31

First look at the tool I use to automate production for Matcherino tournaments

ReddySet

41,848 просмотров • 10 месяцев назад

GPT-5.4 is here. Native computer-use capabilities. Up to 1M tokens of context in Codex and the API. Best-in-class agentic coding for complex tasks. Scalable tool search across larger ecosystems. More efficient reasoning for long, tool-heavy workflows.
3:02

GPT-5.4 is here. Native computer-use capabilities. Up to 1M tokens of context in Codex and the API. Best-in-class agentic coding for complex tasks. Scalable tool search across larger ecosystems. More efficient reasoning for long, tool-heavy workflows.

OpenAI Developers

1,074,161 просмотров • 4 месяцев назад

A new study shows a wild wolf appearing to use a tool for the first time The unexpected discovery could potentially represent the first known example of tool use in wild wolves, scientists reported today in Ecology and Evolution.
1:35

A new study shows a wild wolf appearing to use a tool for the first time The unexpected discovery could potentially represent the first known example of tool use in wild wolves, scientists reported today in Ecology and Evolution.

Massimo

113,053 просмотров • 8 месяцев назад

Anthropic just dropped Claude Opus 4.1 It outperforms OpenAI o3, Gemini 2.5 Pro and Qwen-3 Coder on agentic coding and tool use. Claude Code is going to get incredibly better.
0:26

Anthropic just dropped Claude Opus 4.1 It outperforms OpenAI o3, Gemini 2.5 Pro and Qwen-3 Coder on agentic coding and tool use. Claude Code is going to get incredibly better.

Shubham Saboo

26,252 просмотров • 11 месяцев назад

This AIST humanoid demo is worth studying. The robot handles a large construction panel keeps balance aligns the sheet against the wall frame and uses a power tool in a real workspace setup. Slow movement. Controlled demo. Still a serious look at where humanoid robots could matter first. Construction tasks need reach force control balance tool use and recovery when the object shifts. That is exactly why humanoids are hard.
0:34

This AIST humanoid demo is worth studying. The robot handles a large construction panel keeps balance aligns the sheet against the wall frame and uses a power tool in a real workspace setup. Slow movement. Controlled demo. Still a serious look at where humanoid robots could matter first. Construction tasks need reach force control balance tool use and recovery when the object shifts. That is exactly why humanoids are hard.

TechniaHQ | humanoid robots

556,153 просмотров • 22 дней назад

Five years ago I created TabNine, the first commercial code completion tool to use deep learning. Today I'm releasing Supermaven, the first code completion tool with a context window exceeding 100,000 tokens.
0:45

Five years ago I created TabNine, the first commercial code completion tool to use deep learning. Today I'm releasing Supermaven, the first code completion tool with a context window exceeding 100,000 tokens.

Jacob Jackson

496,035 просмотров • 2 лет назад

Goodbye NotebookLM. Introducing the World’s First Full Agentic AI Pods - Generate Any Professional Podcasts with One Prompt! Free to Use for Everyone!
2:16

Goodbye NotebookLM. Introducing the World’s First Full Agentic AI Pods - Generate Any Professional Podcasts with One Prompt! Free to Use for Everyone!

Eric Jing

8,093,558 просмотров • 1 год назад

Build anything in the terminal with improved agentic coding in Gemini 3 Flash! Watch this demo to see how a rapid prototyping tool doesn't have to compromise code quality. Learn more about using Gemini 3 Flash with Gemini CLI →
0:52

Build anything in the terminal with improved agentic coding in Gemini 3 Flash! Watch this demo to see how a rapid prototyping tool doesn't have to compromise code quality. Learn more about using Gemini 3 Flash with Gemini CLI →

Google Cloud Tech

38,036 просмотров • 6 месяцев назад

Our new LFM2.5-350M brings tool calling and agentic AI to Raspberry Pi level hardware
3:14

Our new LFM2.5-350M brings tool calling and agentic AI to Raspberry Pi level hardware

Mathias Lechner

13,398 просмотров • 3 месяцев назад

🤖 AI Agents vs Agentic AI: What’s the difference? We broke down the latest research paper on the conceptual taxonomy, use cases, and challenges of both. 🧠 AI Agents = simple automation ⚙️ Agentic AI = complex, collaborative goal-seeking 🎥 Watch the demo 📚 Get the TL;DR below 👇
0:28

🤖 AI Agents vs Agentic AI: What’s the difference? We broke down the latest research paper on the conceptual taxonomy, use cases, and challenges of both. 🧠 AI Agents = simple automation ⚙️ Agentic AI = complex, collaborative goal-seeking 🎥 Watch the demo 📚 Get the TL;DR below 👇

Masa

14,391 просмотров • 1 год назад

Use the right tool for the job 🖊️ Explore Q's wide array of gadgets in 007 First Light
0:42

Use the right tool for the job 🖊️ Explore Q's wide array of gadgets in 007 First Light

PlayStation

332,899 просмотров • 1 месяц назад

Use the right tool for the job 🖊️ Explore Q's wide array of gadgets in 007 First Light.
0:42

Use the right tool for the job 🖊️ Explore Q's wide array of gadgets in 007 First Light.

PlayStation Europe

16,131 просмотров • 1 месяц назад

the world’s first agentic brokerage Public
0:33

the world’s first agentic brokerage Public

Manz🌪

13,873 просмотров • 29 дней назад

Smaller models with agentic workflows outperform giants. His 4 design patterns change everything: • Reflection (AI critiques itself) • Tool use (connects to APIs) • Planning (breaks complex tasks) • Multi-agent collaboration JPMorgan already cut costs 30% using this.
0:33

Smaller models with agentic workflows outperform giants. His 4 design patterns change everything: • Reflection (AI critiques itself) • Tool use (connects to APIs) • Planning (breaks complex tasks) • Multi-agent collaboration JPMorgan already cut costs 30% using this.

Karl Mehta

132,729 просмотров • 11 месяцев назад