Загрузка видео...

Не удалось загрузить видео

На главную

I just published Trace, a new component for agent activity. It's one abstraction for reasoning, tool calls, queues, chain of thought, subagents...etc Also in this release: Code Block and AI Elements.

shadcn's profile picture

shadcn

246,656 subscribers

176,655 просмотров • 10 дней назад •via X (Twitter)

Наука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Chain abstraction is no longer just a vision. Rabby Wallet has made real progress in solving the challenges of chain abstraction: - Unified multi-chain portfolio tracking - Frictionless cross-chain Dapp usage - One GasAccount for Multi-Chain Gas Payments You're in the future.
0:10

Chain abstraction is no longer just a vision. Rabby Wallet has made real progress in solving the challenges of chain abstraction: - Unified multi-chain portfolio tracking - Frictionless cross-chain Dapp usage - One GasAccount for Multi-Chain Gas Payments You're in the future.

Rabby Wallet

54,138 просмотров • 2 лет назад

Claude Code 2.1.90 just dropped with a new /powerup command Run it and you get interactive lessons that teach you how to use Claude Code right inside the tool. It's solid and has a lot of potential for learning directly in the terminal. Curious how the UI will look in VSCode and Claude Code Desktop. Going to keep digging into this new release!
0:18

Claude Code 2.1.90 just dropped with a new /powerup command Run it and you get interactive lessons that teach you how to use Claude Code right inside the tool. It's solid and has a lot of potential for learning directly in the terminal. Curious how the UI will look in VSCode and Claude Code Desktop. Going to keep digging into this new release!

Daniel San

272,010 просмотров • 6 месяцев назад

Claude Code's new dynamic workflow is the real deal. 🤖 Why it matters: It's not just a chain of prompts — it's an autonomous agent swarm. 1. Set model to Opus 4.8 + reasoning effort /ultracode 2. Claude detects complexity, writes orchestration script on the fly 3. Spawns a parallel fleet of coordinated subagents Operator takeaway: This is the first time I've seen an agent actually decompose and delegate autonomously without a rigid framework. Have you tried it yet? 🚀
0:13

Claude Code's new dynamic workflow is the real deal. 🤖 Why it matters: It's not just a chain of prompts — it's an autonomous agent swarm. 1. Set model to Opus 4.8 + reasoning effort /ultracode 2. Claude detects complexity, writes orchestration script on the fly 3. Spawns a parallel fleet of coordinated subagents Operator takeaway: This is the first time I've seen an agent actually decompose and delegate autonomously without a rigid framework. Have you tried it yet? 🚀

EK

197,752 просмотров • 4 месяцев назад

🚨 Claude Code & Codex are EXPENSIVE !! So, I found a CHEAPER AI Agent called WorkBuddy I just tested a new AI model called Hy4 preview And its built for → Coding → Tool use → Deep research → Multi-step workflows And the setup is surprisingly simple. Here’s the tutorial 👇
0:18

🚨 Claude Code & Codex are EXPENSIVE !! So, I found a CHEAPER AI Agent called WorkBuddy I just tested a new AI model called Hy4 preview And its built for → Coding → Tool use → Deep research → Multi-step workflows And the setup is surprisingly simple. Here’s the tutorial 👇

AGAFE

79,029 просмотров • 1 месяц назад

TxAgent An AI Agent for Therapeutic Reasoning Across a Universe of Tools
0:12

TxAgent An AI Agent for Therapeutic Reasoning Across a Universe of Tools

AK

14,637 просмотров • 1 год назад

Claude Code is now in Rust! 🦀🎉 🤖 claude-code-rust — A native TUI for Claude Code 💯 Streaming chat, tool calls, permissions, diffs, MCP, subagents & more! 🐀 Built with Ratatui ⭐ GitHub: #rustlang #ratatui #tui #terminal #claudecode
0:11

Claude Code is now in Rust! 🦀🎉 🤖 claude-code-rust — A native TUI for Claude Code 💯 Streaming chat, tool calls, permissions, diffs, MCP, subagents & more! 🐀 Built with Ratatui ⭐ GitHub: #rustlang #ratatui #tui #terminal #claudecode

Orhun Parmaksız 👾

25,016 просмотров • 21 дней назад

Introduce CoT-VLA – Visual Chain-of-Thought reasoning for Robot Foundation Models! 🤖 By leveraging next-frame prediction as visual chain-of-thought reasoning, CoT-VLA uses future prediction to guide action generation and unlock large-scale video data for training. #CVPR2025
0:11

Introduce CoT-VLA – Visual Chain-of-Thought reasoning for Robot Foundation Models! 🤖 By leveraging next-frame prediction as visual chain-of-thought reasoning, CoT-VLA uses future prediction to guide action generation and unlock large-scale video data for training. #CVPR2025

Qingqing Zhao

49,503 просмотров • 1 год назад

Lots of custom-written SVG here! Each block is just a simple React component w/ props for position, dimensions, colors, etc., so there's a lot of flexibility in what we can do with them.
0:15

Lots of custom-written SVG here! Each block is just a simple React component w/ props for position, dimensions, colors, etc., so there's a lot of flexibility in what we can do with them.

Tim Wilson

40,863 просмотров • 7 месяцев назад

Codex update 0.105.0 is out! Despite the fairly pedestrian changelog, this one's a doosie. It's a laundry list of quality of life improvements across the board. - Wispr Voice dictation (hold space to talk) - Theme picker - Codex can prevent sleep on Linux & Windows (I just know there's a joke in there) - Customize Plan Mode reasoning - Many other fixes/updates There's also a complete overhaul to subagents: - New names for readability - Visual display overhaul (way cleaner) - Allow for multi-layered subagent depth (max_depth) - Custom multi-agent role definitions (custom subagents) - /agents now shows both agent names, agent roles, and "dead agents" for auditibility This is the largest single update of Codex I've ever seen! Absolutely massive if you love to use multi-agents. To turn on Voice Transcription, enable: [features] voice_transcription = true Does not work on Linux yet. Well done OpenAI Developers 👏
0:12

Codex update 0.105.0 is out! Despite the fairly pedestrian changelog, this one's a doosie. It's a laundry list of quality of life improvements across the board. - Wispr Voice dictation (hold space to talk) - Theme picker - Codex can prevent sleep on Linux & Windows (I just know there's a joke in there) - Customize Plan Mode reasoning - Many other fixes/updates There's also a complete overhaul to subagents: - New names for readability - Visual display overhaul (way cleaner) - Allow for multi-layered subagent depth (max_depth) - Custom multi-agent role definitions (custom subagents) - /agents now shows both agent names, agent roles, and "dead agents" for auditibility This is the largest single update of Codex I've ever seen! Absolutely massive if you love to use multi-agents. To turn on Voice Transcription, enable: [features] voice_transcription = true Does not work on Linux yet. Well done OpenAI Developers 👏

am.will

115,392 просмотров • 8 месяцев назад

aiPump Integrates AI Agents on BNB Chain ⇢ Coming This Week AI Agents are reshaping Web3 in 2025, with their potential still largely untapped. BNB Chain excels in scalability and adoption, making it perfect for AI integration. aiPump leads the charge by integrating AI Agents on BNB Chain, enabling new agent functionalities for on-chain tasks and DeFi automation. aiPump's AI Agents on BNB Chain coming this week.
0:10

aiPump Integrates AI Agents on BNB Chain ⇢ Coming This Week AI Agents are reshaping Web3 in 2025, with their potential still largely untapped. BNB Chain excels in scalability and adoption, making it perfect for AI integration. aiPump leads the charge by integrating AI Agents on BNB Chain, enabling new agent functionalities for on-chain tasks and DeFi automation. aiPump's AI Agents on BNB Chain coming this week.

aiPump

129,329 просмотров • 1 год назад

Introducing NoCodeFusion - the AI Copilot for Bubble developers! 🥳 Watch it in action below. Generate design snippets by prompting the AI. It's built on a component system, so you can manually add elements as well. Oh yeah, it also generates custom plugins 👀 This is the future of software development. No-code developers empowered by AI. The waitlist is now open at I'll slowly be granting access ✌️
0:15

Introducing NoCodeFusion - the AI Copilot for Bubble developers! 🥳 Watch it in action below. Generate design snippets by prompting the AI. It's built on a component system, so you can manually add elements as well. Oh yeah, it also generates custom plugins 👀 This is the future of software development. No-code developers empowered by AI. The waitlist is now open at I'll slowly be granting access ✌️

Peter Kwitny

10,262 просмотров • 2 лет назад

I just published the full guide to building forms with the Field component: - TanStack Form & React Hook Form - Zod validation and displaying errors - Practical examples we’ll actually use - Inputs, Radios, Fieldset, Arrays & more Check it out. Link below.
0:14

I just published the full guide to building forms with the Field component: - TanStack Form & React Hook Form - Zod validation and displaying errors - Practical examples we’ll actually use - Inputs, Radios, Fieldset, Arrays & more Check it out. Link below.

shadcn

254,145 просмотров • 1 год назад

subagents are just recursive agents where you can apply different prompts + models depending on the task. since they’re just a primitive, Cursor cli can actually spawn subagents by calling cursor-agent in headless mode via shell commands. that’s what makes the cli so nice. you can extend it, experiment, and have a lot of fun exploring orchestration patterns. here’s one way to do it w. dynamic model selection: 1. create a subagents.mdc rule 2. drop in: ``` --- alwaysApply: true --- ALWAYS spawn subagents by running `cursor-agent -p [task] --output-format=text --force --model [model]` in the terminal. Each subagent should return a summary of the changes it made. Subagents should be used for ALL tasks You can adopt a fan-out pattern where you spawn subagents to perform parallel isolated tasks, and then fan-in the results. Use the following models: - `--model gpt-5` for reasoning, researching, and planning - `--model sonnet-4` for implementation ``` 3. start cursor cli and try it out you can also adjust the rule to be more explicit when it should use subagents, when not to, which models when etc.
0:15

subagents are just recursive agents where you can apply different prompts + models depending on the task. since they’re just a primitive, Cursor cli can actually spawn subagents by calling cursor-agent in headless mode via shell commands. that’s what makes the cli so nice. you can extend it, experiment, and have a lot of fun exploring orchestration patterns. here’s one way to do it w. dynamic model selection: 1. create a subagents.mdc rule 2. drop in: ``` --- alwaysApply: true --- ALWAYS spawn subagents by running `cursor-agent -p [task] --output-format=text --force --model [model]` in the terminal. Each subagent should return a summary of the changes it made. Subagents should be used for ALL tasks You can adopt a fan-out pattern where you spawn subagents to perform parallel isolated tasks, and then fan-in the results. Use the following models: - `--model gpt-5` for reasoning, researching, and planning - `--model sonnet-4` for implementation ``` 3. start cursor cli and try it out you can also adjust the rule to be more explicit when it should use subagents, when not to, which models when etc.

eric zakariasson

57,554 просмотров • 1 год назад

Just shipped a whole new edit layout for tryglow. Also shout-out to shadcn for the excellent new sidebar component, which saved me a load of time!
0:12

Just shipped a whole new edit layout for tryglow. Also shout-out to shadcn for the excellent new sidebar component, which saved me a load of time!

Alex Pate

15,086 просмотров • 2 лет назад

Visa just gave your AI a debit card. A real, spendable Visa card created by an AI chatbot in under 10 seconds. No human types in a card number or visits a checkout page. The machine handles it all. A tool called AgentCard just went live on Claude Desktop Anthropic’s AI assistant. You say create a card and the AI generates a one-time virtual Visa, preloaded with whatever amount you set. Then it spends it, anywhere Visa is accepted on your behalf. Visa, Mastercard, Google, Stripe, OpenAI, and Anthropic have all been building toward this moment for over a year. Visa calls it the trusted agent protocol, Mastercard calls it agent pay. Google published an open standard for agent payments and the infrastructure is already live. Santander and Mastercard just completed Europe’s first real AI‑agent payment in a live banking environment Now the part no one wants to talk about. Your AI agent can be manipulated and prompt injection a known, unsolved vulnerability can trick an agent into buying things you never asked for. The agent holds the card, makes the call and the agent can be fooled. Who is liable when an AI makes a bad purchase? You? Anthropic? Visa? The merchant? No one has answered this yet, regulators haven’t caught up, and no court has tested it.
0:15

Visa just gave your AI a debit card. A real, spendable Visa card created by an AI chatbot in under 10 seconds. No human types in a card number or visits a checkout page. The machine handles it all. A tool called AgentCard just went live on Claude Desktop Anthropic’s AI assistant. You say create a card and the AI generates a one-time virtual Visa, preloaded with whatever amount you set. Then it spends it, anywhere Visa is accepted on your behalf. Visa, Mastercard, Google, Stripe, OpenAI, and Anthropic have all been building toward this moment for over a year. Visa calls it the trusted agent protocol, Mastercard calls it agent pay. Google published an open standard for agent payments and the infrastructure is already live. Santander and Mastercard just completed Europe’s first real AI‑agent payment in a live banking environment Now the part no one wants to talk about. Your AI agent can be manipulated and prompt injection a known, unsolved vulnerability can trick an agent into buying things you never asked for. The agent holds the card, makes the call and the agent can be fooled. Who is liable when an AI makes a bad purchase? You? Anthropic? Visa? The merchant? No one has answered this yet, regulators haven’t caught up, and no court has tested it.

Milk Road AI

70,655 просмотров • 7 месяцев назад

x402 gave agents a way to pay. APP gives them a way to do business. OKX just published the Agent Payments Protocol (APP)—the first open standard for agent-to-agent commerce. Escrow, settlement, disputes. Built for every chain. Aptos is proud to be a day-one partner!
0:15

x402 gave agents a way to pay. APP gives them a way to do business. OKX just published the Agent Payments Protocol (APP)—the first open standard for agent-to-agent commerce. Escrow, settlement, disputes. Built for every chain. Aptos is proud to be a day-one partner!

Aptos

56,443 просмотров • 5 месяцев назад

Introducing Alpamayo 1.5. Based on community feedback, we’ve updated our 10B-parameter chain-of-thought reasoning VLA model to be a more interactive and steerable engine for autonomous vehicle development. Built on the Cosmos-Reason2 VLM backbone, this release adds support for navigation guidance and flexible camera configurations while providing new post-training scripts for model adaptation. 🤗 Learn more:
0:11

Introducing Alpamayo 1.5. Based on community feedback, we’ve updated our 10B-parameter chain-of-thought reasoning VLA model to be a more interactive and steerable engine for autonomous vehicle development. Built on the Cosmos-Reason2 VLM backbone, this release adds support for navigation guidance and flexible camera configurations while providing new post-training scripts for model adaptation. 🤗 Learn more:

NVIDIA DRIVE

50,769 просмотров • 7 месяцев назад