Loading video...

Video Failed to Load

Go Home

People will gradually understand how good it is for ComfyUI to work with agent tools locally. I ask my agent to recreate any social media videos I saw and all I do is dropping the urls. This was a demo a month ago. I have a way better version now.

jojodecayz's profile picture

JO. Z

2,104 subscribers

80,531 views • 3 months ago •via X (Twitter)

ComedyEducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

I think you need to understand how cool and good the Codex sub-agent feature is. For example, here is the perfect task for parallel agents: cleaning and refactoring components based on a skill. So I ask Codex to split the work to speed things up.
0:40

I think you need to understand how cool and good the Codex sub-agent feature is. For example, here is the perfect task for parallel agents: cleaning and refactoring components based on a skill. So I ask Codex to split the work to speed things up.

Thomas Ricouard

55,852 views • 5 months ago

This is a speech I gave in DC a few years ago to advocate for veterans. I hope you enjoy it… and I hope it helps people understand more. All the way, Boone
7:01

This is a speech I gave in DC a few years ago to advocate for veterans. I hope you enjoy it… and I hope it helps people understand more. All the way, Boone

Boone Cutler 🦬🇺🇸 🦅

10,281 views • 1 year ago

Three months ago I started walking bc I was jealous of the people I saw walking on my way to work and I decided that was what I wanted to do with my mornings. This wasn’t just about being fit for me, it was me proving to myself that I could have discipline and be consistent with
0:22

Three months ago I started walking bc I was jealous of the people I saw walking on my way to work and I decided that was what I wanted to do with my mornings. This wasn’t just about being fit for me, it was me proving to myself that I could have discipline and be consistent with

Reni

100,638 views • 11 months ago

I am rebuilding my AI financial agent. Fully open source. Runnable locally. Today's change adds stock price charts. How it works: • ask a question • agent selects best tool • agent renders UI components • agent answers question is perfect for this project: • rich existing toolkits • new tools easy to add • backend is python • frontend is typescript This will be one of my core projects moving forward. Feature requests are welcome.
0:20

I am rebuilding my AI financial agent. Fully open source. Runnable locally. Today's change adds stock price charts. How it works: • ask a question • agent selects best tool • agent renders UI components • agent answers question is perfect for this project: • rich existing toolkits • new tools easy to add • backend is python • frontend is typescript This will be one of my core projects moving forward. Feature requests are welcome.

Virat Singh

37,180 views • 1 year ago

I wanted to share a quick demo of what we've been working on with our ai agent cloud. This enables fast deployment of agents that have access to a suite of tools, and was designed with agent interoperability in mind. This demo shows how you can go from nothing to an AI twitter agent in a couple minutes. This is what we are using internally to manage deployments, so we will consistently upgrading its capabilities. The next goals are to enable simple TEE deployments for agents, and focus on building out feature for agent interoperability to simplify agent to agent collaboration.
4:16

I wanted to share a quick demo of what we've been working on with our ai agent cloud. This enables fast deployment of agents that have access to a suite of tools, and was designed with agent interoperability in mind. This demo shows how you can go from nothing to an AI twitter agent in a couple minutes. This is what we are using internally to manage deployments, so we will consistently upgrading its capabilities. The next goals are to enable simple TEE deployments for agents, and focus on building out feature for agent interoperability to simplify agent to agent collaboration.

Johnny

27,176 views • 1 year ago

Hermes agent is insane I gave Hermes access to Browser Use so it has access to my social media accounts. It retains context about my codebase, tone, and workflows. Now i just ask it to post on X for me...
0:23

Hermes agent is insane I gave Hermes access to Browser Use so it has access to my social media accounts. It retains context about my codebase, tone, and workflows. Now i just ask it to post on X for me...

shawn

121,027 views • 3 months ago

"I have been labelled a Pakistani, a Khalistani, an American agent—but thank God I haven't been labelled a Russian agent yet. Our people didn’t believe these accusations. The way the NC has been fighting for the people, it will continue to do so."
0:41

"I have been labelled a Pakistani, a Khalistani, an American agent—but thank God I haven't been labelled a Russian agent yet. Our people didn’t believe these accusations. The way the NC has been fighting for the people, it will continue to do so."

JKNC

37,588 views • 1 year ago

AI Art. I realize not all AI Art tools work the same way. Part of the problem is that we don’t quite understand “how” it works, and until we have a better understanding, some pause for concern is good imo. 1/3
2:10

AI Art. I realize not all AI Art tools work the same way. Part of the problem is that we don’t quite understand “how” it works, and until we have a better understanding, some pause for concern is good imo. 1/3

Watch It Played

23,161 views • 2 years ago

This was a wild one. Thank you to all who defended me in the comments. Now it is my turn to put my opinion on all of it out there. For those who are telling me to never necklace my rifle I have made a short response video. I ask you to watch it to understand how I feel about the matter.
1:42

This was a wild one. Thank you to all who defended me in the comments. Now it is my turn to put my opinion on all of it out there. For those who are telling me to never necklace my rifle I have made a short response video. I ask you to watch it to understand how I feel about the matter.

Emily Fisher

142,258 views • 7 months ago

I just shipped Design Feedback Agent using Replit ⠕ agent without writing a single line of code. You can use this agent to get constructive feedback on your designs--website, mobile app, email newsletter etc. Check out the video demo, and try it for yourself at My biggest takeaway as I continue to experiment with these tools is how good they are getting at building complex flows and how precise they are at taking design feedback and applying it accurately from a text prompt. I'm excited to build even more complex products to see how far I can push these tools. Let me know what you think of this agent and how you would improve it.
2:06

I just shipped Design Feedback Agent using Replit ⠕ agent without writing a single line of code. You can use this agent to get constructive feedback on your designs--website, mobile app, email newsletter etc. Check out the video demo, and try it for yourself at My biggest takeaway as I continue to experiment with these tools is how good they are getting at building complex flows and how precise they are at taking design feedback and applying it accurately from a text prompt. I'm excited to build even more complex products to see how far I can push these tools. Let me know what you think of this agent and how you would improve it.

Levin Stanley

17,762 views • 1 year ago

7 months ago i kept myself awake and starved myself for 3 days to self-induce psychosis and i made this. I am doing alot better now and my life is going really well, im happy to be where i am now and do not want to go back to where i was 7 months ago. What i learned much later is how i now cant make myself replicate this project anymore, i noticed how the mental state ur in affects the art you produce. I dont regret what i did to myself, it gave me a good lesson along the way, and is a good reminder of what i managed to get myself away from
1:03

7 months ago i kept myself awake and starved myself for 3 days to self-induce psychosis and i made this. I am doing alot better now and my life is going really well, im happy to be where i am now and do not want to go back to where i was 7 months ago. What i learned much later is how i now cant make myself replicate this project anymore, i noticed how the mental state ur in affects the art you produce. I dont regret what i did to myself, it gave me a good lesson along the way, and is a good reminder of what i managed to get myself away from

saleh

99,630 views • 11 months ago

Hit 122.5 overhead press for 3x5 today. This is another OHP PR. Felt good. I still have plenty to improve, but I know my form is better than it was a month ago. Felt hard. Looking forward to seeing how 125lbs will feel later this week. How's training going?
0:32

Hit 122.5 overhead press for 3x5 today. This is another OHP PR. Felt good. I still have plenty to improve, but I know my form is better than it was a month ago. Felt hard. Looking forward to seeing how 125lbs will feel later this week. How's training going?

Daniel Polehn

23,720 views • 6 months ago

This is how i build everything now. Before the agents touch a line of code "before you do any building make 10 mock ups in html of how we can make it look" I then pick a path and ask for more mockups until I feel happy with the feel. The only way to work with these things.
0:43

This is how i build everything now. Before the agents touch a line of code "before you do any building make 10 mock ups in html of how we can make it look" I then pick a path and ask for more mockups until I feel happy with the feel. The only way to work with these things.

0xSero

25,695 views • 3 months ago

#Pradeep Recent - I usually ask for a synopsis, so I told him to mail it. - I read the synopsis and replied "no" to it. - The main crux of the story was a shocker to me. - I was like, will people take this in a good way. #Dude #Keerthiswaran
1:51

#Pradeep Recent - I usually ask for a synopsis, so I told him to mail it. - I read the synopsis and replied "no" to it. - The main crux of the story was a shocker to me. - I was like, will people take this in a good way. #Dude #Keerthiswaran

Movie Tamil

60,847 views • 9 months ago

The Copilot CLI - how to configure and use it, some tweaks I make and a few of my own workflows / custom agent. I was proud of this one. Pretty much a one shot. It's wild how easy it is to make content when a thing is good.
36:20

The Copilot CLI - how to configure and use it, some tweaks I make and a few of my own workflows / custom agent. I was proud of this one. Pretty much a one shot. It's wild how easy it is to make content when a thing is good.

Burke Holland

34,578 views • 4 months ago

Almost ready, I guess I will finally work on the onboarding experience. I have been using vllm-studio for work all day, this is so good. I legit haven't noticed a single issue with the model, the outputs or even the app's usability. You will have your coding agent at home.
2:15

Almost ready, I guess I will finally work on the onboarding experience. I have been using vllm-studio for work all day, this is so good. I legit haven't noticed a single issue with the model, the outputs or even the app's usability. You will have your coding agent at home.

0xSero

14,301 views • 1 month ago

I read the RLM paper and it’s like, this is the simplest way to do solve a general problem, seriously it’s just this simple. Love this kind of vibe. Last one like this for me was the ReAct paper from 4 years ago, and that one defined agent we use today. I made a visualization to help understand how RLM works.
0:58

I read the RLM paper and it’s like, this is the simplest way to do solve a general problem, seriously it’s just this simple. Love this kind of vibe. Last one like this for me was the ReAct paper from 4 years ago, and that one defined agent we use today. I made a visualization to help understand how RLM works.

Eric Zhu

44,978 views • 2 months ago

I've been trying to move from imperative prompting to declarative prompting. • Imperative prompting: I tell the agent how to do something. • Declarative prompting: I describe my goal to the agent. This was impossible before, but since Opus 4.5, I'm letting models fill in the blanks more and more. I recorded a video using Quest + Opus 4.5. This is a coding agent designed specifically for this purpose.
4:11

I've been trying to move from imperative prompting to declarative prompting. • Imperative prompting: I tell the agent how to do something. • Declarative prompting: I describe my goal to the agent. This was impossible before, but since Opus 4.5, I'm letting models fill in the blanks more and more. I recorded a video using Quest + Opus 4.5. This is a coding agent designed specifically for this purpose.

Santiago

96,471 views • 5 months ago

I had every intention of showing a “good” high tee session but this is how it went. High tee always humbles me. I take a lot of pride in my tee work. This is where I really work out my swing and am rarely so inconsistent. However, this wasn’t my day. I know it may not seem terrible (and to be honest these angles make it look way better than what it was) but like I said, this is where I really focus on my swing and I have a tough time accepting just average work. I was pulling the ball too much for my liking. I wanted more center field opposed to right center. I was getting under the ball more than I wanted. I am posting this to show that you’re going to have days where it just doesn’t click or go your way. Especially scrolling social media you see perfection everywhere. Unfortunately it happens and it’s normal to get frustrated but try to not let it consume you. Come back the next day, refreshed, and ready to dominate.
0:57

I had every intention of showing a “good” high tee session but this is how it went. High tee always humbles me. I take a lot of pride in my tee work. This is where I really work out my swing and am rarely so inconsistent. However, this wasn’t my day. I know it may not seem terrible (and to be honest these angles make it look way better than what it was) but like I said, this is where I really focus on my swing and I have a tough time accepting just average work. I was pulling the ball too much for my liking. I wanted more center field opposed to right center. I was getting under the ball more than I wanted. I am posting this to show that you’re going to have days where it just doesn’t click or go your way. Especially scrolling social media you see perfection everywhere. Unfortunately it happens and it’s normal to get frustrated but try to not let it consume you. Come back the next day, refreshed, and ready to dominate.

Megan Rembielak

19,861 views • 1 year ago

$VET, #VeFam. In this video, I demonstrate in less than 4:30 minutes how to create an AI agent on veworld(.)ai. Watch me build a Mr. Robot Monologue Writer agent. If you haven't seen Mr. Robot, I suggest you watch it! This is just early bird access. The options for tools and integrations and such are limited, but what exists is already working quite well. The process is easy peasy. The UI is simple, but effective. It asks you for... 1. Role & Purpose 2. Voice & Style 3. Behavior 4. Rules 5. Tags 6. Avatar image 7. Welcome text. 8. Test drive before publication. ... and that's about it. This free version lets you have at most 3 agents, I am told. This implies that there is also a paid version. I'm all for it, because it sounds to me like VeChain is ready to do real business! I am providing feedback to Jérôme Grillères in order to help improve VeChain's AI agent marketplace. I didn't have to set up anything. The web UI is all I needed! The agent is running on Claude Sonnet 3.7. I did not have to provide a Claude API key. We seem to be riding along on VeChain's. I hope there'll be a choice for more models, including ChatGPT, in the future. This is so user friendly, that I can easily imagine that this would take off in a big, big way. I'm definitely building on this, when it goes into production with full features. Even if my own AI agents aren't successful, then I'm sure others' will be. And that means the $VET / $VTHO / $B3TR flywheel is going to take off in a big, big way. I, for one, am here for it. (See the reply below for the listing of the AI agent I just created.)
4:26

$VET, #VeFam. In this video, I demonstrate in less than 4:30 minutes how to create an AI agent on veworld(.)ai. Watch me build a Mr. Robot Monologue Writer agent. If you haven't seen Mr. Robot, I suggest you watch it! This is just early bird access. The options for tools and integrations and such are limited, but what exists is already working quite well. The process is easy peasy. The UI is simple, but effective. It asks you for... 1. Role & Purpose 2. Voice & Style 3. Behavior 4. Rules 5. Tags 6. Avatar image 7. Welcome text. 8. Test drive before publication. ... and that's about it. This free version lets you have at most 3 agents, I am told. This implies that there is also a paid version. I'm all for it, because it sounds to me like VeChain is ready to do real business! I am providing feedback to Jérôme Grillères in order to help improve VeChain's AI agent marketplace. I didn't have to set up anything. The web UI is all I needed! The agent is running on Claude Sonnet 3.7. I did not have to provide a Claude API key. We seem to be riding along on VeChain's. I hope there'll be a choice for more models, including ChatGPT, in the future. This is so user friendly, that I can easily imagine that this would take off in a big, big way. I'm definitely building on this, when it goes into production with full features. Even if my own AI agents aren't successful, then I'm sure others' will be. And that means the $VET / $VTHO / $B3TR flywheel is going to take off in a big, big way. I, for one, am here for it. (See the reply below for the listing of the AI agent I just created.)

₿lackthorne AI

13,636 views • 8 days ago