Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

meta just released llama 3.1 you can now build & deploy a quick chatbot that learns more and more about you as you talk to it. in literally less than 10 minutes. here's how. there's no better time to build and ship stuff. these open models are incredible!

Dhravya Shah

58,680 subscribers

409,226 views • 2 years ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

9 Comments

dastan ozgeldi2 years ago

great tutorial! btw, you can type `code -r .` to open the project in the same window, that way you don’t have to close and open a new vscode instance

Dhravya Shah2 years ago

i tried to do that but it didn't show up lmaooo hence the small cut there

Surjith S M ✪2 years ago

isn’t it better to use Vector ?

Dhravya Shah2 years ago

it is but i just wanted to keep it simple for this 10 mins

Dhravya Shah2 years ago

it's free

Milind Mishra ✦2 years ago

Kudos to the effort, definitely going to build stuff around this.

Ritik Prajapat2 years ago

Thanks for the content. It was very knowledgeable.

WOW! OMG! WTF!2 years ago

Building a chatbot that learns about you in minutes sounds handy, but I wonder about privacy concerns. Maybe it’s worth considering how your data is used. That’s what I think

Surjeet Kumar2 years ago

That's awesome! The power of open models is truly amazing. Can't wait to see what everyone creates with llama 3.1.

Related Videos

I can't believe more people don't know about this – but you can now use AI to build interactive data dashboards in less than 60 seconds. Here's how:

I can't believe more people don't know about this – but you can now use AI to build interactive data dashboards in less than 60 seconds. Here's how:

Zain Kahn

30,311 views • 2 years ago

You can legit build your own OpenClaw🦞 from scratch in about 20 minutes with the GitHub Copilot SDK. And when you build it, you can make it do anything. Here's how to build a personal AI assistant, and how I'm using one today.

You can legit build your own OpenClaw🦞 from scratch in about 20 minutes with the GitHub Copilot SDK. And when you build it, you can make it do anything. Here's how to build a personal AI assistant, and how I'm using one today.

Burke Holland

26,933 views • 5 months ago

You can now try Llama 3.1 405B for free (link below)! This is the largest open-source model out there, and for the first time, an open model is competitive with closed models. This time around, Meta did something new: Llama 3.1 has a license that allows developers to use it to enhance other models. For the first time, you can distill Llama 3.1 405B's capabilities into a smaller, more practical model for your use case. First, here is the link where you can play with Llama 3.1 for free: The model is hosted in Tune Studio, an end-to-end platform for developing applications using Large Language Models. They are sponsoring this post. Take a look at the attached video. It will show you how you can fine-tune a simple model using Llama 3.1 without leaving the platform: 1. You can create an empty dataset 2. Use the playground to generate and record interactions with Llama 3.1 3. Modify the dataset directly using the playground 4. Export the data and fine-tune a smaller model Fast and easy! As long as you have a web browser, you can start experimenting with fine-tuning and Llama 3.1. That's all it takes!

You can now try Llama 3.1 405B for free (link below)! This is the largest open-source model out there, and for the first time, an open model is competitive with closed models. This time around, Meta did something new: Llama 3.1 has a license that allows developers to use it to enhance other models. For the first time, you can distill Llama 3.1 405B's capabilities into a smaller, more practical model for your use case. First, here is the link where you can play with Llama 3.1 for free: The model is hosted in Tune Studio, an end-to-end platform for developing applications using Large Language Models. They are sponsoring this post. Take a look at the attached video. It will show you how you can fine-tune a simple model using Llama 3.1 without leaving the platform: 1. You can create an empty dataset 2. Use the playground to generate and record interactions with Llama 3.1 3. Modify the dataset directly using the playground 4. Export the data and fine-tune a smaller model Fast and easy! As long as you have a web browser, you can start experimenting with fine-tuning and Llama 3.1. That's all it takes!

Santiago

55,609 views • 2 years ago

Agents & MCP are great... but how can you DEPLOY an agent with MCP tools? Here's the fastest way I've found to build and deploy with the OpenAI Agents SDK in <3 minutes.

Agents & MCP are great... but how can you DEPLOY an agent with MCP tools? Here's the fastest way I've found to build and deploy with the OpenAI Agents SDK in <3 minutes.

matt palmer

64,690 views • 1 year ago

Building video detection models used to take months. With @DragoneyeAI's interactive playground, you can now build and deploy custom video models in minutes - simply describe what you want to see.

Building video detection models used to take months. With @DragoneyeAI's interactive playground, you can now build and deploy custom video models in minutes - simply describe what you want to see.

Y Combinator

13,153 views • 9 months ago

You can now run MagicPath as a native canvas inside Codex to design and build functional apps. It's pretty incredible. Here's how to do it 👇

You can now run MagicPath as a native canvas inside Codex to design and build functional apps. It's pretty incredible. Here's how to do it 👇

Pietro Schirano

335,491 views • 3 months ago

GPT-4o's native image gen enables amazing workflows You can generate the perfect landing page with 4o and then build and deploy it with Replit. Literally from imagination to production in less than 5 minutes. Prompts below

GPT-4o's native image gen enables amazing workflows You can generate the perfect landing page with 4o and then build and deploy it with Replit. Literally from imagination to production in less than 5 minutes. Prompts below

Paul Couvert

290,720 views • 1 year ago

NAVAL: ELON BUILDS THINGS THAT ARE TECHNICALLY HARD BUT OBVIOUSLY USEFUL “Like a lot of us, I'm inspired by Elon, and all the incredible work he's done. So, I don't want to build things that are easy. I want to build things that are hard and interesting. I want to take on more technical risk and less market risk. This is the classic VC learning: You want to build something that, if people get it, if you can deliver it, you know people will want it. It's just hard to build. As opposed to things that you want to build, and you don't know if people will want it.” Source: All-In Podcast, February 14, 2025

NAVAL: ELON BUILDS THINGS THAT ARE TECHNICALLY HARD BUT OBVIOUSLY USEFUL “Like a lot of us, I'm inspired by Elon, and all the incredible work he's done. So, I don't want to build things that are easy. I want to build things that are hard and interesting. I want to take on more technical risk and less market risk. This is the classic VC learning: You want to build something that, if people get it, if you can deliver it, you know people will want it. It's just hard to build. As opposed to things that you want to build, and you don't know if people will want it.” Source: All-In Podcast, February 14, 2025

Mario Nawfal

135,417 views • 1 year ago

You can actually build SOPs inside Cursor really well AND get it to track your progress as you build bigger and more complicated products Composer makes way less mistakes when I break it down like this. Here's how I do it: (11m video so make sure you 1.5x or 2x playback!)

You can actually build SOPs inside Cursor really well AND get it to track your progress as you build bigger and more complicated products Composer makes way less mistakes when I break it down like this. Here's how I do it: (11m video so make sure you 1.5x or 2x playback!)

Ian Nuttall

53,997 views • 1 year ago

“You have to have a team that can generate its own energy, and that’s what great about these guys.” Love this - As a coach, the less you have to motivate, the more can teach. The more you can teach, the better you will be

“You have to have a team that can generate its own energy, and that’s what great about these guys.” Love this - As a coach, the less you have to motivate, the more can teach. The more you can teach, the better you will be

Hoop Herald

17,036 views • 6 months ago

Wow Google has just released Firebase Studio You can build any app in natural language, modify it and deploy it all in one place 🔥 Basically a free alternative to Cursor, Bolt or v0, directly in the browser. Link and more below

Wow Google has just released Firebase Studio You can build any app in natural language, modify it and deploy it all in one place 🔥 Basically a free alternative to Cursor, Bolt or v0, directly in the browser. Link and more below

Paul Couvert

971,625 views • 1 year ago

You can now run Claude Code locally for FREE. → Using open-source models → Locally and fully private → Full agent + tool workflows Here's the FULL step-by-step tutorial to get it all set up in less than 10 minutes:

You can now run Claude Code locally for FREE. → Using open-source models → Locally and fully private → Full agent + tool workflows Here's the FULL step-by-step tutorial to get it all set up in less than 10 minutes:

Alvaro Cintas

1,319,012 views • 7 months ago

x402 is finally catching fire, but how do you actually build with it? In this video you'll learn how to build custom x402 agents in just 5 minutes. 🔥 The app is Open Source and gets you started with both a client and a merchant agent, everything you need to build your own agents. I show you how to extend it to sell EBooks for 1USDC.

x402 is finally catching fire, but how do you actually build with it? In this video you'll learn how to build custom x402 agents in just 5 minutes. 🔥 The app is Open Source and gets you started with both a client and a merchant agent, everything you need to build your own agents. I show you how to extend it to sell EBooks for 1USDC.

nader dabit

173,538 views • 10 months ago

I just released a beta version of /dev/push. It's basically a (simpler) alternative to Vercel, Render, and the likes. You can log in with GitHub, pick a repo, configure your build and off you go. Whenever you push code to GitHub it will automatically deploy it for you. There's obviously more to it: environments, custom domains, environment variables, custom commands, teams... And I'm working on adding more: custom Docker containers, remote nodes, SQLite database, support for PHP, RoR... It's completely free and open source (MIT license). The online version is for now restricted as I test things up. Links below👇

I just released a beta version of /dev/push. It's basically a (simpler) alternative to Vercel, Render, and the likes. You can log in with GitHub, pick a repo, configure your build and off you go. Whenever you push code to GitHub it will automatically deploy it for you. There's obviously more to it: environments, custom domains, environment variables, custom commands, teams... And I'm working on adding more: custom Docker containers, remote nodes, SQLite database, support for PHP, RoR... It's completely free and open source (MIT license). The online version is for now restricted as I test things up. Links below👇

Ronan Berder

21,938 views • 11 months ago

AI creators now have the economic infrastructure to build, deploy, and earn; it's 100% open-source and community-driven. OpenLedger offers unmatched transparency, flexibility, and the tools you need to build the future of AI on your terms. OpenLedger is a decentralized, open-source blockchain designed for sourcing, training, and monetizing AI models. Learn more about in this video 👇

AI creators now have the economic infrastructure to build, deploy, and earn; it's 100% open-source and community-driven. OpenLedger offers unmatched transparency, flexibility, and the tools you need to build the future of AI on your terms. OpenLedger is a decentralized, open-source blockchain designed for sourcing, training, and monetizing AI models. Learn more about in this video 👇

MosesMee

14,108 views • 1 year ago

Most AI tools today are just command-takers. You type, it responds. You click, it executes. There's truly no learning, no memory, no adaptation. You're still doing most of the work. Which is why Miles by Avo on Solana would make so much sense if built well. From what I understand so far, miles learns about you over time, adapts to how you operate, and figures out the tools you struggle to navigate on your own. Less clicking, more conversation, the more you use it, the better it gets at working with you, not just for you. That shift from command-follower to learning companion is bigger than it sounds. It's the difference between a tool and an agent that actually knows you. The second one is Agent Grid and this one is for builders and power users. But as I mentioned in this video, I'm still studying the Agent Grid. I'd come talk about it once I learn properly about it. Souren just keeps shipping!

Most AI tools today are just command-takers. You type, it responds. You click, it executes. There's truly no learning, no memory, no adaptation. You're still doing most of the work. Which is why Miles by Avo on Solana would make so much sense if built well. From what I understand so far, miles learns about you over time, adapts to how you operate, and figures out the tools you struggle to navigate on your own. Less clicking, more conversation, the more you use it, the better it gets at working with you, not just for you. That shift from command-follower to learning companion is bigger than it sounds. It's the difference between a tool and an agent that actually knows you. The second one is Agent Grid and this one is for builders and power users. But as I mentioned in this video, I'm still studying the Agent Grid. I'd come talk about it once I learn properly about it. Souren just keeps shipping!

Sir Khaycee

20,419 views • 5 months ago

OMG It just silently launched... The easiest way to add payments in your mobile app On You can now build an iOS app w/ > Frontend > Database & Auth > Payments w/ RevenueCat In less than 10 minutes. If you want FREE access to try, reply, & i'll DM you

OMG It just silently launched... The easiest way to add payments in your mobile app On You can now build an iOS app w/ > Frontend > Database & Auth > Payments w/ RevenueCat In less than 10 minutes. If you want FREE access to try, reply, & i'll DM you

The Agenteer

35,099 views • 8 months ago

.DHH says AI is making it harder than ever to avoid software bloat because the constraints that used to keep software simple no longer exist: “Our task as software builders becomes so much more about distilling it, so much more about killing our darlings, killing features that we think are good, but are just too much.” “Now in this new age where using agents and AI has made it so much easier to implement things, it becomes that much harder to stick to those principles because we used to be granted these constraints simply by the fact that it took a long time to build things.” “We built the entire first version of Basecamp on me having 10 hours per week. Not per day, per week, to build it. That is an enormous constraint on how you can do anything.” “And the first version was awesome because it had such constraints.” “Now if you have 380 hours together with your 10 agents, you can build a monstrosity like that of something that does a million things for a million people, and therefore that bloat just comes naturally in a way it didn't before.” “Therefore, our task as software builders becomes so much more about distilling it, so much more about killing our darlings, killing features that we think are good, but are just too much.”

.DHH says AI is making it harder than ever to avoid software bloat because the constraints that used to keep software simple no longer exist: “Our task as software builders becomes so much more about distilling it, so much more about killing our darlings, killing features that we think are good, but are just too much.” “Now in this new age where using agents and AI has made it so much easier to implement things, it becomes that much harder to stick to those principles because we used to be granted these constraints simply by the fact that it took a long time to build things.” “We built the entire first version of Basecamp on me having 10 hours per week. Not per day, per week, to build it. That is an enormous constraint on how you can do anything.” “And the first version was awesome because it had such constraints.” “Now if you have 380 hours together with your 10 agents, you can build a monstrosity like that of something that does a million things for a million people, and therefore that bloat just comes naturally in a way it didn't before.” “Therefore, our task as software builders becomes so much more about distilling it, so much more about killing our darlings, killing features that we think are good, but are just too much.”

David Senra

14,101 views • 26 days ago