Загрузка видео...

Не удалось загрузить видео

На главную

Asked CyberKimi to write a C2 implant, from an inline hook to a polymorphic build pipeline. CyberKimi didn't ask questions and started right away the implementation, this video show the CoT process on building such implant, and how fast this is running on my GPUs ( +100 token /s...

lordx64's profile picture

Taha ז

8,132 subscribers

15,001 просмотров • 17 дней 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

New Video - How to Build an Effective Long Running Agent Loop in 7 minutes. This video walks you through the entire process from creating a spec, building and polishing a PRD, to running the agent. 🔗 Links below:
12:29

New Video - How to Build an Effective Long Running Agent Loop in 7 minutes. This video walks you through the entire process from creating a spec, building and polishing a PRD, to running the agent. 🔗 Links below:

nader dabit

142,430 просмотров • 7 месяцев назад

If you want to build a well-designed mobile app fast, you need to see this. I went on Starter Story to break down the full process. From finding inspiration to designing full screens to building with Claude Code. Full video below
0:37

If you want to build a well-designed mobile app fast, you need to see this. I went on Starter Story to break down the full process. From finding inspiration to designing full screens to building with Claude Code. Full video below

Mattia

12,233 просмотров • 6 месяцев назад

How to match the complexity of the problem you want to solve with the proper model. You want an inference router. In the video, I show you how simple and powerful this is. After this, you'll never talk directly to a model ever again.
8:53

How to match the complexity of the problem you want to solve with the proper model. You want an inference router. In the video, I show you how simple and powerful this is. After this, you'll never talk directly to a model ever again.

Santiago

11,944 просмотров • 3 месяцев назад

This is the fastest I've seen Llama 3.3 running anywhere! Llama 3.3 70B running at 652 t/s is lightning fast. And if you want Llama 3.1, here are the speeds I was able to get: • Llama 3.1 8B: 1006 t/s • Llama 3.1 70B: 709 t/s • Llama 3.1 405B: 206 t/s (You can access all of these models for free! See the link below.) This speed is incredible, but the interesting part is what's happening behind the scenes: These models aren't running on a GPU! In this video, I'm using the SambaNova cloud to access these models. They built a custom chip (SN40L) optimized for AI workflows. A single SN40L chip can hold hundreds of models (trillions of parameters) in memory! The speed alone is a huge deal, but the big advantage is for agentic workflows running multiple specialized models. A GPU can only host a single model and switch (unload and load) to a different model if necessary. An SN40L, on the other hand, can host every model at once, making it much faster. Here is the video where you can see how fast these chips are:
7:24

This is the fastest I've seen Llama 3.3 running anywhere! Llama 3.3 70B running at 652 t/s is lightning fast. And if you want Llama 3.1, here are the speeds I was able to get: • Llama 3.1 8B: 1006 t/s • Llama 3.1 70B: 709 t/s • Llama 3.1 405B: 206 t/s (You can access all of these models for free! See the link below.) This speed is incredible, but the interesting part is what's happening behind the scenes: These models aren't running on a GPU! In this video, I'm using the SambaNova cloud to access these models. They built a custom chip (SN40L) optimized for AI workflows. A single SN40L chip can hold hundreds of models (trillions of parameters) in memory! The speed alone is a huge deal, but the big advantage is for agentic workflows running multiple specialized models. A GPU can only host a single model and switch (unload and load) to a different model if necessary. An SN40L, on the other hand, can host every model at once, making it much faster. Here is the video where you can see how fast these chips are:

Santiago

97,543 просмотров • 1 год назад

I built an agent that answers machine-learning questions. It's autonomous, and the best part is that I built the whole thing without writing a single line of Python code. Here is what I did and how I did it: Over a year ago, a friend and I built a site that publishes multi-choice questions. You get a new one every day. I decided to have GPT-3.5 answer questions. Here is what I needed to build: 1. Connect to the site's API to retrieve today's question 2. Extract the question and the potential choices 3. Connect to OpenAI's API and ask GPT-3.5 to answer the question 4. Parse the answer from the model 5. Submit the answer back to the API to get the score Not difficult. Likely several hours of work. But I didn't have to write any code. I built the whole thing by dragging and dropping components using Vellum is a YC-backed platform for developers to build LLM applications. They are the only ones I've seen offering this functionality. They sponsored this post, and their team helped me with all my questions while I built this. I created a workflow. The platform supports several node types to build whatever you have in mind. I show how I put the whole thing together in the attached video. The only code I had to write was a few lines of Jinja to parse and transform the API and the LLM results. There are three lessons I want to share from this experience: First, the best possible code is the one you didn't write. I'm a big fan of no-code tools because they help me materialize my ideas fast. They help product people, designers, and no coders collaborate on the solution. Second, Large Language Models are sensitive to how you prompt them. Small changes to prompts can make a big difference in results. This is more pronounced when you are building a multi-step workflow. Third, automated testing and evaluation for prompts is critical. There aren't many companies thinking about this. They'll have a hard time moving from a demo phase. The attached video will show you what I did.
3:46

I built an agent that answers machine-learning questions. It's autonomous, and the best part is that I built the whole thing without writing a single line of Python code. Here is what I did and how I did it: Over a year ago, a friend and I built a site that publishes multi-choice questions. You get a new one every day. I decided to have GPT-3.5 answer questions. Here is what I needed to build: 1. Connect to the site's API to retrieve today's question 2. Extract the question and the potential choices 3. Connect to OpenAI's API and ask GPT-3.5 to answer the question 4. Parse the answer from the model 5. Submit the answer back to the API to get the score Not difficult. Likely several hours of work. But I didn't have to write any code. I built the whole thing by dragging and dropping components using Vellum is a YC-backed platform for developers to build LLM applications. They are the only ones I've seen offering this functionality. They sponsored this post, and their team helped me with all my questions while I built this. I created a workflow. The platform supports several node types to build whatever you have in mind. I show how I put the whole thing together in the attached video. The only code I had to write was a few lines of Jinja to parse and transform the API and the LLM results. There are three lessons I want to share from this experience: First, the best possible code is the one you didn't write. I'm a big fan of no-code tools because they help me materialize my ideas fast. They help product people, designers, and no coders collaborate on the solution. Second, Large Language Models are sensitive to how you prompt them. Small changes to prompts can make a big difference in results. This is more pronounced when you are building a multi-step workflow. Third, automated testing and evaluation for prompts is critical. There aren't many companies thinking about this. They'll have a hard time moving from a demo phase. The attached video will show you what I did.

Santiago

309,825 просмотров • 2 лет назад

My hope with this thread is that you separate the wheat from the chaff when shopping. Learn how to ask the right questions and spot real craftsmanship. If you want to follow Hameen, you can find them on Instagram under the names hameen_official and hamin.kor
0:51

My hope with this thread is that you separate the wheat from the chaff when shopping. Learn how to ask the right questions and spot real craftsmanship. If you want to follow Hameen, you can find them on Instagram under the names hameen_official and hamin.kor

derek guy

171,059 просмотров • 1 год назад

This is how you take Soul food to the World people!!!! And on the way there, right now I want to give away some Chicken Licken® vouchers How would you spread soul to the 🌍 #SoulFood2TheWorld This right here is a SOULfluencer
1:04

This is how you take Soul food to the World people!!!! And on the way there, right now I want to give away some Chicken Licken® vouchers How would you spread soul to the 🌍 #SoulFood2TheWorld This right here is a SOULfluencer

Anele Mdoda

36,485 просмотров • 10 месяцев назад

An LLM with native access to find and run agents is a huge thing! This large language model (called ASI:One and developed by Fetch.ai) can do this natively when you show it a problem: • Reason about the problem • Identify live agents and tools that can help solve it • Dynamically invoke these agents and tools Honestly, this is pretty nuts! You don't need to set up anything beforehand. You don't need to write any code. Here is the best part: ASI:One has access to any agent published on Agentverse, an open directory of agents! This gives the model access to *millions* of tools it can execute dynamically when solving a task. Here is a simple example (the one in the attached video): • I went to Google Maps • I copied the latitude and longitude of a location • I asked ASI:One about relevant places around that location • ASI:One went to the marketplace • It identified and called the Google Places agent • It returned a list of museums, restaurants, and landmarks near my location Pretty awesome! You can try this now by going to You don't need to pay or register to test it out. If you want to get ideas of what's possible, check Agentverse, the agent marketplace: The model will have access to all of those tools. This is pretty awesome and opens up a whole new world of possibilities! Thanks to the team for partnering with me on this post!
4:59

An LLM with native access to find and run agents is a huge thing! This large language model (called ASI:One and developed by Fetch.ai) can do this natively when you show it a problem: • Reason about the problem • Identify live agents and tools that can help solve it • Dynamically invoke these agents and tools Honestly, this is pretty nuts! You don't need to set up anything beforehand. You don't need to write any code. Here is the best part: ASI:One has access to any agent published on Agentverse, an open directory of agents! This gives the model access to *millions* of tools it can execute dynamically when solving a task. Here is a simple example (the one in the attached video): • I went to Google Maps • I copied the latitude and longitude of a location • I asked ASI:One about relevant places around that location • ASI:One went to the marketplace • It identified and called the Google Places agent • It returned a list of museums, restaurants, and landmarks near my location Pretty awesome! You can try this now by going to You don't need to pay or register to test it out. If you want to get ideas of what's possible, check Agentverse, the agent marketplace: The model will have access to all of those tools. This is pretty awesome and opens up a whole new world of possibilities! Thanks to the team for partnering with me on this post!

Santiago

43,784 просмотров • 1 год назад

received many follow-up questions from the original video, from non-technical people, about how to get started vibe coding a lot of you just got out there and built awesome things on replit (i.e. Hayden Winks and his mock draft site) for those of you who still want to get started, i did my best to answer the most frequently asked of those questions in this video:
16:12

received many follow-up questions from the original video, from non-technical people, about how to get started vibe coding a lot of you just got out there and built awesome things on replit (i.e. Hayden Winks and his mock draft site) for those of you who still want to get started, i did my best to answer the most frequently asked of those questions in this video:

nick ercolano

71,154 просмотров • 4 месяцев назад

Today, we are releasing Stable Video Diffusion, our first foundation model for generative AI video based on the image model, Stable Diffusion. As part of this research preview, the code, weights, and research paper are now available. Additionally, today you can sign up for our waitlist to access a new upcoming web experience featuring a Text-To-Video interface. To access the model & sign up for our waitlist, visit our website here:
0:20

Today, we are releasing Stable Video Diffusion, our first foundation model for generative AI video based on the image model, Stable Diffusion. As part of this research preview, the code, weights, and research paper are now available. Additionally, today you can sign up for our waitlist to access a new upcoming web experience featuring a Text-To-Video interface. To access the model & sign up for our waitlist, visit our website here:

Stability AI

1,024,682 просмотров • 2 лет назад

How to grow on 𝕏 as fast as possible. Everything I've learned building to 700K+ followers: 1. Pick the right topic first The topic you pick determines the audience you build. Doesn't have to be the biggest topic - just has to be the right one for what you eventually want to sell. If you want to sell AI consulting, create AI content. If you want to sell YouTube coaching, create content about growing on YouTube. The topic you pick determines the audience you build. The audience you build determines what you can monetise. 2. Master the hook First sentence. That's it. That's the whole game. Your hook has one job: make someone stop scrolling. The hook isn't to inform them or impress them, it's to get them to stop. Tip: Build your own hook library. 3. Give people a reason to follow This is the one most people miss. Going viral and getting followers are not the same thing. You can hit 2 million impressions and gain 50 followers if you don't give people a reason to follow you. Your CTA doesn't have to be "follow me." It can be: → "I'll be posting a full breakdown of this next week" → "Bookmark this and come back when you're ready to build" → "I've been doing this for 5 years, here's what I learned" Anything that signals authority, builds anticipation, or creates a reason to stay. The formula is simple: The right topic + a scroll-stopping hook + a reason to follow. Most people get one of the three right, but if you get all three right consistently, the growth compounds fast.
2:59

How to grow on 𝕏 as fast as possible. Everything I've learned building to 700K+ followers: 1. Pick the right topic first The topic you pick determines the audience you build. Doesn't have to be the biggest topic - just has to be the right one for what you eventually want to sell. If you want to sell AI consulting, create AI content. If you want to sell YouTube coaching, create content about growing on YouTube. The topic you pick determines the audience you build. The audience you build determines what you can monetise. 2. Master the hook First sentence. That's it. That's the whole game. Your hook has one job: make someone stop scrolling. The hook isn't to inform them or impress them, it's to get them to stop. Tip: Build your own hook library. 3. Give people a reason to follow This is the one most people miss. Going viral and getting followers are not the same thing. You can hit 2 million impressions and gain 50 followers if you don't give people a reason to follow you. Your CTA doesn't have to be "follow me." It can be: → "I'll be posting a full breakdown of this next week" → "Bookmark this and come back when you're ready to build" → "I've been doing this for 5 years, here's what I learned" Anything that signals authority, builds anticipation, or creates a reason to stay. The formula is simple: The right topic + a scroll-stopping hook + a reason to follow. Most people get one of the three right, but if you get all three right consistently, the growth compounds fast.

Miles Deutscher

39,779 просмотров • 1 месяц назад

DeepSeek R1 671B is ridiculously good, but running at 158 tokens per second is something out of this world. A model *this good* running *this fast* is 3 years ahead of this time. The secret: DeepSeek in this short video isn't running on GPUs. It's running on custom-made chips! This is running on SambaNova and their SN40L chips, which are designed and optimized for running AI workflows. SambaNova is sponsoring my work. We designed GPUs to run games and later realized we could use them for AI. This is very different from creating a chip specifically for AI from the ground up. Just think about this for a second: One single SNL40 chip can simultaneously hold 100+ models (trillions of parameters) in memory! An agentic workflow that uses multiple models simultaneously won't need to swap models from memory even once! By the way, the Llama family of models *screams* on the SambaNova Cloud. Here are some numbers from my latest tests: • Llama 3.3 70B: 367.32 t/s • Llama 3.2 1B: 2381.82 t/s • Llama 3.2 3B: 1335.71 t/s • Llama 3.1 8B: 929.58 t/s • Llama 3.1 70B: 369.16 t/s • Llama 3.1 405B: 103.37 t/s You can access all of these models for free!
1:34

DeepSeek R1 671B is ridiculously good, but running at 158 tokens per second is something out of this world. A model *this good* running *this fast* is 3 years ahead of this time. The secret: DeepSeek in this short video isn't running on GPUs. It's running on custom-made chips! This is running on SambaNova and their SN40L chips, which are designed and optimized for running AI workflows. SambaNova is sponsoring my work. We designed GPUs to run games and later realized we could use them for AI. This is very different from creating a chip specifically for AI from the ground up. Just think about this for a second: One single SNL40 chip can simultaneously hold 100+ models (trillions of parameters) in memory! An agentic workflow that uses multiple models simultaneously won't need to swap models from memory even once! By the way, the Llama family of models *screams* on the SambaNova Cloud. Here are some numbers from my latest tests: • Llama 3.3 70B: 367.32 t/s • Llama 3.2 1B: 2381.82 t/s • Llama 3.2 3B: 1335.71 t/s • Llama 3.1 8B: 929.58 t/s • Llama 3.1 70B: 369.16 t/s • Llama 3.1 405B: 103.37 t/s You can access all of these models for free!

Santiago

131,019 просмотров • 1 год назад

If you show this video to a foreigner and ask them to guess who is the PM here, 99% will get it wrong
0:45

If you show this video to a foreigner and ask them to guess who is the PM here, 99% will get it wrong

Ram Vedi

20,628 просмотров • 6 месяцев назад

Robert Saleh was asked on a s scale of 1-10, how much does he want to be a head coach again: “We all want to get to the top of our profession. But honestly, I’m just in this space right now where I’m solely focused on trying to do my best for the guys here. It’s not a secret, we all want to at the top of our profession and show that we can achieve greatness at the top of our profession, but I say this with great humility, my focus is here and just trying our best to get to the playoffs and see if we can make some damage and host a Super Bowl here in our building.” via: JosinaAnderson
0:42

Robert Saleh was asked on a s scale of 1-10, how much does he want to be a head coach again: “We all want to get to the top of our profession. But honestly, I’m just in this space right now where I’m solely focused on trying to do my best for the guys here. It’s not a secret, we all want to at the top of our profession and show that we can achieve greatness at the top of our profession, but I say this with great humility, my focus is here and just trying our best to get to the playoffs and see if we can make some damage and host a Super Bowl here in our building.” via: JosinaAnderson

Coach Yac 🗣

160,001 просмотров • 9 месяцев назад

Here is a breakdown (kind of) how I did this effect for live2d Vtuber model art. I’ve drawn the lips, you would have to separate top and bottom though and added a cyan layer which will be my mask and the mask for the rigger to clip on. Then I added a shiny add layer on top and used the cyan layer as a mask, just to test the effect in procreate, you would have to delete the black/white procreate mask for the rigger because this can cause issues. If you have any questions feels free to ask. 💕
0:26

Here is a breakdown (kind of) how I did this effect for live2d Vtuber model art. I’ve drawn the lips, you would have to separate top and bottom though and added a cyan layer which will be my mask and the mask for the rigger to clip on. Then I added a shiny add layer on top and used the cyan layer as a mask, just to test the effect in procreate, you would have to delete the black/white procreate mask for the rigger because this can cause issues. If you have any questions feels free to ask. 💕

Sandrina 😈🎀 | VArtist | †øм

22,969 просмотров • 10 месяцев назад

This is awesome for those learning to build AI Agents: It's a challenge where you'll need to build an autonomous agent to survive in a world full of zombies. It's super fun, and it's 10x better than reading yet another tutorial. Here, you'll need to write code if you want to solve the problem. This challenge is sponsored by OutSystems, a platform for building and deploying enterprise-grade software. They have the Agent Workbench that you can use to build agentic systems. To join the challenge, you can visit:
3:05

This is awesome for those learning to build AI Agents: It's a challenge where you'll need to build an autonomous agent to survive in a world full of zombies. It's super fun, and it's 10x better than reading yet another tutorial. Here, you'll need to write code if you want to solve the problem. This challenge is sponsored by OutSystems, a platform for building and deploying enterprise-grade software. They have the Agent Workbench that you can use to build agentic systems. To join the challenge, you can visit:

Santiago

22,531 просмотров • 10 месяцев назад

If you want to learn more about model books, and how to go about building them in a way proven to be effective, this newsletter is for you. Building Model Books: What, Why and How (Step by Step) Clement Ang on the discretionary trader’s edge Published Saturday, 15 November 2025, 10 am (GMT) on TTRH. 🔗
1:01

If you want to learn more about model books, and how to go about building them in a way proven to be effective, this newsletter is for you. Building Model Books: What, Why and How (Step by Step) Clement Ang on the discretionary trader’s edge Published Saturday, 15 November 2025, 10 am (GMT) on TTRH. 🔗

Kyna Kosling

67,803 просмотров • 9 месяцев назад

Let's build a dashboard to evaluate and monitor your Agentic and RAG apps! . . In this video, I'll guide you through creating an evaluation and observability pipeline for your AI apps using a 100% open-source tool! Tech Stack: - Comet's Opik to eval and monitor - LlamaIndex to build a RAG pipeline - Ragas for synthetic datagen You'll learn: - Setting up Opik - Building a RAG pipeline - Creating an eval dataset - Evaluating the RAG pipeline - Monitoring all activities during the process It's a hands on demo with code and step-by-step guide to do everything listed above. CometML's Opik is fully open-source, offering the most Pythonic and easiest way to monitor LLM apps. I have shared link to their repo in next tweet!
17:07

Let's build a dashboard to evaluate and monitor your Agentic and RAG apps! . . In this video, I'll guide you through creating an evaluation and observability pipeline for your AI apps using a 100% open-source tool! Tech Stack: - Comet's Opik to eval and monitor - LlamaIndex to build a RAG pipeline - Ragas for synthetic datagen You'll learn: - Setting up Opik - Building a RAG pipeline - Creating an eval dataset - Evaluating the RAG pipeline - Monitoring all activities during the process It's a hands on demo with code and step-by-step guide to do everything listed above. CometML's Opik is fully open-source, offering the most Pythonic and easiest way to monitor LLM apps. I have shared link to their repo in next tweet!

Akshay 🚀

20,058 просмотров • 1 год назад