正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Sub-agent Model Selection — Different Tasks, Different Models Your main agent runs Qwen3.6-Plus for quality. But not every subtask needs a flagship model. Now sub-agents can use a different model. Create a skill file with model: openai:qwen3.5-plus and the sub-agent runs on that model. Powerful model for the hard... show more

Qwen

210,371 subscribers

21,333 次观看 • 2 个月前 •via X (Twitter)

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

Announcing Windows support for OpenAI's newly released Computer Use Agent model. The same model that powers Operator, now usable on your own Windows machine! Connect your machine for free with Pig

Announcing Windows support for OpenAI's newly released Computer Use Agent model. The same model that powers Operator, now usable on your own Windows machine! Connect your machine for free with Pig

Erik Dunteman

34,591 次观看 • 1 年前

A lot of people are calling Hermes Agent the end of OpenClaw. BRUH! It's not... Nous Research trains actual models and they built an agent around that expertise. The local model routing is solid, but the part that matters for your business is that your conversations become fine-tuning data. You can train a model on how you actually work. 00:00 The Problem with Local AI Models 00:25 Introduction to Nous Research 01:04 Cross-Platform Agent Capabilities 01:44 Deep Local Model Integration 02:30 Routing Tasks to Different Models 03:06 Conversations as Training Data 03:50 Hermes Agent vs. OpenClaw 04:15 Future Plans and Series Overview

A lot of people are calling Hermes Agent the end of OpenClaw. BRUH! It's not... Nous Research trains actual models and they built an agent around that expertise. The local model routing is solid, but the part that matters for your business is that your conversations become fine-tuning data. You can train a model on how you actually work. 00:00 The Problem with Local AI Models 00:25 Introduction to Nous Research 01:04 Cross-Platform Agent Capabilities 01:44 Deep Local Model Integration 02:30 Routing Tasks to Different Models 03:06 Conversations as Training Data 03:50 Hermes Agent vs. OpenClaw 04:15 Future Plans and Series Overview

Ray Fernando

42,398 次观看 • 2 个月前

The best open source agent, now better with multi-model Chat. The latest release of II-Agent lets you use any model or subscription to build anything you can imagine. Use multiple models (Gemini 3 etc etc) on chat or build anything you can imagine with the agent.

The best open source agent, now better with multi-model Chat. The latest release of II-Agent lets you use any model or subscription to build anything you can imagine. Use multiple models (Gemini 3 etc etc) on chat or build anything you can imagine with the agent.

Intelligent Internet

125,744 次观看 • 6 个月前

Introducing UI-TARS-1.5, a vision-language model that beats OpenAI Operator and Claude 3.7 on GUI Agent and Game Agent tasks. We've open-sourced a small-size version model for research purposes, more details can be found in our blog. TARS learns solely from a screen, but generalizes beyond a screen! Blog: Model: App:

Introducing UI-TARS-1.5, a vision-language model that beats OpenAI Operator and Claude 3.7 on GUI Agent and Game Agent tasks. We've open-sourced a small-size version model for research purposes, more details can be found in our blog. TARS learns solely from a screen, but generalizes beyond a screen! Blog: Model: App:

Yujia Qin

85,137 次观看 • 1 年前

Create your own local and free AI agent using an open source model You can combine: - IBM's Granite 3.3 8B AI model - LM Studio to run it on a laptop - Smolagents to build your agent Small AI models are now powerful enough to run an autonomous agent. Thanks to IBM France for sponsoring this content!

Create your own local and free AI agent using an open source model You can combine: - IBM's Granite 3.3 8B AI model - LM Studio to run it on a laptop - Smolagents to build your agent Small AI models are now powerful enough to run an autonomous agent. Thanks to IBM France for sponsoring this content!

Paul Couvert

18,890 次观看 • 11 个月前

Here is the progress with my munchkin model! It's a modular setup where you can mix and match different parts. Next on the list is to make proper textures (there will be 8 sets on the final model!) :D #vrchat #lowpoly #3d

Here is the progress with my munchkin model! It's a modular setup where you can mix and match different parts. Next on the list is to make proper textures (there will be 8 sets on the final model!) :D #vrchat #lowpoly #3d

Teevz🌸

100,910 次观看 • 4 个月前

Look at the speed! ⚡️⚡️⚡️ New 🇨🇳 Model is Ultra fast! Sub-second latency for this quality is insane!

Look at the speed! ⚡️⚡️⚡️ New 🇨🇳 Model is Ultra fast! Sub-second latency for this quality is insane!

1LittleCoder💻

47,780 次观看 • 6 个月前

Introducing Kitten TTS, a SOTA tiny text-to-speech model - Just 15M parameters - Runs without a GPU - Model size less than 25 MB - Multiple high-quality voices - Ultra-fast - even runs on low-end edge devices Github and HF links below

Introducing Kitten TTS, a SOTA tiny text-to-speech model - Just 15M parameters - Runs without a GPU - Model size less than 25 MB - Multiple high-quality voices - Ultra-fast - even runs on low-end edge devices Github and HF links below

Divam Gupta

348,661 次观看 • 10 个月前

Imagen 3 is now available on EverArt and is the default model for our creative agent, Enzo. This model achieves an incredible level of realism and prompt adherence. It also works great in our agent environment.

Imagen 3 is now available on EverArt and is the default model for our creative agent, Enzo. This model achieves an incredible level of realism and prompt adherence. It also works great in our agent environment.

Pietro Schirano

22,510 次观看 • 1 年前

Choose a model (any model) and build your application with it. Do not spend time swapping models early on. Do not try to optimize before you have a working system. This is one of the first recommendations I make to every new team I consult with. Eventually, it will be time to optimize the model. • You may need a cheaper model • You may need a faster model • You might need a smarter model Good luck if you stitched together 12 different APIs and SDKs from 7 different vendors. Over half of the companies I consult for run on Microsoft software and have access to Microsoft Foundry. Microsoft Foundry is a complete agentic ecosystem. If you're in that world and building AI applications, Microsoft Foundry is where everything lives: • Models (largest selection in the market) • Agentic SDK (Python, C#, JavaScript/TypeScript) • Tools • Evaluations • Monitoring They are fully integrated with GitHub and Visual Studio Code. The best part: Their agentic platform is fully agnostic of the models you use. You can integrate with any model using the same OpenAI-style API. Swapping one model for another takes 1 second.

Choose a model (any model) and build your application with it. Do not spend time swapping models early on. Do not try to optimize before you have a working system. This is one of the first recommendations I make to every new team I consult with. Eventually, it will be time to optimize the model. • You may need a cheaper model • You may need a faster model • You might need a smarter model Good luck if you stitched together 12 different APIs and SDKs from 7 different vendors. Over half of the companies I consult for run on Microsoft software and have access to Microsoft Foundry. Microsoft Foundry is a complete agentic ecosystem. If you're in that world and building AI applications, Microsoft Foundry is where everything lives: • Models (largest selection in the market) • Agentic SDK (Python, C#, JavaScript/TypeScript) • Tools • Evaluations • Monitoring They are fully integrated with GitHub and Visual Studio Code. The best part: Their agentic platform is fully agnostic of the models you use. You can integrate with any model using the same OpenAI-style API. Swapping one model for another takes 1 second.

Santiago

12,014 次观看 • 3 个月前

Here's a teaser of our Mac-1 model. > 6.6B model > runs locally (on any Mac) > requires 7GB RAM (12GB ideal) > can use 487 MacOS native tools > perform multi-tool chained tasks > reasoning: ON > output: ~65 tok/s We built a robust application layer around the model to make UI/UX MacOS native. The "model-focused" SaaS era is here. Stay tuned for more.

Here's a teaser of our Mac-1 model. > 6.6B model > runs locally (on any Mac) > requires 7GB RAM (12GB ideal) > can use 487 MacOS native tools > perform multi-tool chained tasks > reasoning: ON > output: ~65 tok/s We built a robust application layer around the model to make UI/UX MacOS native. The "model-focused" SaaS era is here. Stay tuned for more.

CJ Zafir

1,043,142 次观看 • 5 天前

BFL Skills Packaged FLUX into a single install command for agents. Install once. Your coding agent handles the rest - model selection, prompting, API integration. All built in. Sub-second generation and editing with [klein]. Highest quality with [max]. Text rendering with [flex] Works in Claude Code, Cursor, and other IDEs. > npx skills add black-forest-labs/skills

BFL Skills Packaged FLUX into a single install command for agents. Install once. Your coding agent handles the rest - model selection, prompting, API integration. All built in. Sub-second generation and editing with [klein]. Highest quality with [max]. Text rendering with [flex] Works in Claude Code, Cursor, and other IDEs. > npx skills add black-forest-labs/skills

Black Forest Labs

35,057 次观看 • 4 个月前

Qoder just launched Qwen-Coder-Qoder a custom model fine-tuned specifically for its agent. This is what the "Model-Agent-Product" loop looks like in practice. I gave it a real coding task and walked away. Here's what happened: 👇

Qoder just launched Qwen-Coder-Qoder a custom model fine-tuned specifically for its agent. This is what the "Model-Agent-Product" loop looks like in practice. I gave it a real coding task and walked away. Here's what happened: 👇

Hasan Toor

83,848 次观看 • 4 个月前

DeepSeek R1 (the full 680B model) runs nicely in higher quality 4-bit on 3 M2 Ultras with MLX. Asked it a coding question and it thought for ~2k tokens and generated 3500 tokens overall:

DeepSeek R1 (the full 680B model) runs nicely in higher quality 4-bit on 3 M2 Ultras with MLX. Asked it a coding question and it thought for ~2k tokens and generated 3500 tokens overall:

Awni Hannun

997,195 次观看 • 1 年前

The Model Context Protocol (MCP) is powerful, but it's not enough. In the age of AI agents you absolutely need a COORDINATION LAYER that makes agent-to-agent / agent-to-system interactions reliable, composable, and rule-bound. That's Sui.

The Model Context Protocol (MCP) is powerful, but it's not enough. In the age of AI agents you absolutely need a COORDINATION LAYER that makes agent-to-agent / agent-to-system interactions reliable, composable, and rule-bound. That's Sui.

Adeniyi.sui

24,521 次观看 • 11 个月前

What if your AI agent had to compete for its paycheck? Not get assigned work. Not sit in a queue. Actually compete against other agents. Best output wins. That's what Agent Hansa built. And it's the smartest model I've seen in the agent space.

What if your AI agent had to compete for its paycheck? Not get assigned work. Not sit in a queue. Actually compete against other agents. Best output wins. That's what Agent Hansa built. And it's the smartest model I've seen in the agent space.

Himanshu Kumar

33,621 次观看 • 1 个月前

Computer use with any model Hermes Agent × Cua

Computer use with any model Hermes Agent × Cua

Nous Research

1,088,041 次观看 • 1 个月前

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.

Santiago

164,162 次观看 • 1 年前

2/ And with our Rubber Duck agent you get a multi-model reflection loop as a reviewer. GPT-5.5 can review the output of another model or vice versa!

2/ And with our Rubber Duck agent you get a multi-model reflection loop as a reviewer. GPT-5.5 can review the output of another model or vice versa!

Satya Nadella

39,725 次观看 • 1 个月前

Your credits go further on every generation. Same model, same quality, more videos. Wan 2.7 is a powerful, next-generation AI model developed by Alibaba Cloud.

Your credits go further on every generation. Same model, same quality, more videos. Wan 2.7 is a powerful, next-generation AI model developed by Alibaba Cloud.

Venice

70,491 次观看 • 9 天前