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.

Something new to try this weekend or on your next flight! ☀️✈️ Starting today, you can download the smallest DeepSeek R1 model for free in Craft. This lets you use a basic AI reasoning model in Craft Assistant without the internet, keeping your data completely on your device. This... show more

Craft.do

34,205 subscribers

173,755 views • 1 year ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

10 Comments

ARK Electronics2 years ago

Excited about the latest tech for your drone product? Our NDAA-compliant, US-made flight controllers are designed to accelerate your path to market and provide a solid platform for developing your autonomous software. Check them out! #Drones #UAV #UAS #Robotics #MadeInUSA

Dr. Tab1 year ago

I will be trying this in about 10 days. Fantastic stuff guys

St.Hillz1 year ago

Perfect timing! I’ll be offline this weekend training my AI with PublicAI while pretending to be a tech wizard. Who needs Wi-Fi when you have creativity? ✈️✨

Roberto Salermo1 year ago

Exciting announcement. When can we expect the iPad version? It looks like it was launched on iPhone only.

szmr1 year ago

Noticed that the little info tooltip doesn’t work for the DeepSeek model option (the little ? Button)

Craft.do1 year ago

Thanks, we will fix it!

Ivan1 year ago

Are we going to be able to use it to query our notes by using natural language search?

Misha Perez1 year ago

I tried to use it but at least in Spanish it gives me back gibberish.

帕西1 year ago

I tried it out, and as a Traditional Chinese user, I found that it responds in Simplified Chinese and contains a lot of garbled text.

robertpowell1 year ago

Im serious,y concerned about the privacy here.. on device? Maybe but I bet it phones home at t some point.

Related Videos

NVIDIA AI now lets you run Deepseek R1 in VSCode as a code assistant! 😱 With the CodeGPT extension, you can connect NVIDIA AI, then choose the Deepseek R1 model. Then select your project files to use them as context 👇

NVIDIA AI now lets you run Deepseek R1 in VSCode as a code assistant! 😱 With the CodeGPT extension, you can connect NVIDIA AI, then choose the Deepseek R1 model. Then select your project files to use them as context 👇

Daniel San

262,504 views • 1 year ago

Bauhaus Clock for iPhone and iPad is here. Most apps you open. This one you display. The clock loved by thousands on Mac. Now in your pocket. On your desk. On your nightstand. Same obsessive craft. New canvas. Here's what's inside…

Bauhaus Clock for iPhone and iPad is here. Most apps you open. This one you display. The clock loved by thousands on Mac. Now in your pocket. On your desk. On your nightstand. Same obsessive craft. New canvas. Here's what's inside…

Atilla

212,392 views • 3 months ago

Here are some tips for those who want to practice face acting: ➡️U motion: Move your head in a "U" Shape so it's never stuck in the same place. This will help your movements look more interesting. ➡️Key points: When practicing with your model, learn to get to a "Key point." This is when you can automatically get to an expression without using toggles. I use surprised and angry expressions a lot, so I know exactly how to move my face to achieve that look, mainly for clips or comedic effect. I practiced enough so I know what it will look like on the model. ➡️Head tilts: If you struggle with face acting, a simple head tilt will go a long way. Overall, the movement and face acting of your model does matter. It can help it look more interesting, but also, it's okay if you can't face acting all the time. Using just key animations when you're gaming will work perfectly. Example: You died in a game, and you go to the key point of surprise. You know, making this face will make your model look shocked, so you will do a dramatic eye open and mouth agape to achieve this, to reflect onto your model. Lastly. The way your model moves is usually 30% rigging artist,20% tracking (webcam/iPhone), and 50% you. Your rigging artist can give you the tools, but only you can make your models' results reflect your emotions. As always, DO YOUR PARAMETERS AND SETTINGS IN VTUBE STUDIO. It will not be perfect to your face and camera settings unless you adjust the model, (This is an old video I did on parameters) Holy Yapfest.

Here are some tips for those who want to practice face acting: ➡️U motion: Move your head in a "U" Shape so it's never stuck in the same place. This will help your movements look more interesting. ➡️Key points: When practicing with your model, learn to get to a "Key point." This is when you can automatically get to an expression without using toggles. I use surprised and angry expressions a lot, so I know exactly how to move my face to achieve that look, mainly for clips or comedic effect. I practiced enough so I know what it will look like on the model. ➡️Head tilts: If you struggle with face acting, a simple head tilt will go a long way. Overall, the movement and face acting of your model does matter. It can help it look more interesting, but also, it's okay if you can't face acting all the time. Using just key animations when you're gaming will work perfectly. Example: You died in a game, and you go to the key point of surprise. You know, making this face will make your model look shocked, so you will do a dramatic eye open and mouth agape to achieve this, to reflect onto your model. Lastly. The way your model moves is usually 30% rigging artist,20% tracking (webcam/iPhone), and 50% you. Your rigging artist can give you the tools, but only you can make your models' results reflect your emotions. As always, DO YOUR PARAMETERS AND SETTINGS IN VTUBE STUDIO. It will not be perfect to your face and camera settings unless you adjust the model, (This is an old video I did on parameters) Holy Yapfest.

♥️Cutiepierin | L2D RIG ARTIST

94,177 views • 9 months ago

Ragnarok shattered the world. The gods have chosen you to shape the next one. Fight, craft, and manage your shop in the skies in this brand new co-op adventure. Wishlist Cloudheim now! ⚔️

Epic Games Store

36,989 views • 1 year ago

Windows users, this one’s for you. Computer use now works on Windows, so Codex can take action on your Windows computer. And with Windows support for Codex in the ChatGPT mobile app, you can start, review, and steer tasks on the go while work continues on your Windows machine. An early experience, but we’re working on more ways to keep your work moving, wherever you are.

Windows users, this one’s for you. Computer use now works on Windows, so Codex can take action on your Windows computer. And with Windows support for Codex in the ChatGPT mobile app, you can start, review, and steer tasks on the go while work continues on your Windows machine. An early experience, but we’re working on more ways to keep your work moving, wherever you are.

OpenAI

1,402,798 views • 2 months ago

If you are new to Crypto and Web3, Here is an excellent guide on how you can get started on learning the basics for free. With just your smartphone, You can get started on your journey in the Web3 space. Share this with a friend interested in Web3.

If you are new to Crypto and Web3, Here is an excellent guide on how you can get started on learning the basics for free. With just your smartphone, You can get started on your journey in the Web3 space. Share this with a friend interested in Web3.

Denise

31,132 views • 3 years ago

Here is how you can install an open-source, enterprise-grade RAG system on your server (with the best document understanding I've seen.) First, something obvious to anyone trying to sell RAG in the market: You are crazy if you think companies will let their data travel to a hosted model. No one wants to send their data anywhere (those who do haven't found an alternative.) Every single company would rather have an air-gapped system with no internet access. GroundX is an open-source RAG system that you can run on your servers (or any cloud provider, as long as you have access to GPUs) and works without a network. (If the military wants to do RAG, this is precisely what they will be looking for.) I installed GroundX on my AWS account and recorded a video to show you how to use it. There are two services you can use: 1. Ingest: This service uses a pretrained vision model to ingest and understand your knowledge base. 2. Search: This service combines text and vector search with a fine-tuned re-ranker model to retrieve information from your knowledge base. A quick note about the Ingest service: 99% of people think they need better "retrieval" mechanisms. I think they need better "ingestion." That's where this service comes in! Ingest "understands" your documents in a way I haven't seen before. After you try it, you'll realize why showing your LLM your raw documents is a bad idea. In the video, I use a free tool called X-Ray to test a document and understand how the Ingest service breaks it down. You can access this tool by signing up for a free GroundX cloud account and uploading your documents. You'll see a bit more about this in the video.

Here is how you can install an open-source, enterprise-grade RAG system on your server (with the best document understanding I've seen.) First, something obvious to anyone trying to sell RAG in the market: You are crazy if you think companies will let their data travel to a hosted model. No one wants to send their data anywhere (those who do haven't found an alternative.) Every single company would rather have an air-gapped system with no internet access. GroundX is an open-source RAG system that you can run on your servers (or any cloud provider, as long as you have access to GPUs) and works without a network. (If the military wants to do RAG, this is precisely what they will be looking for.) I installed GroundX on my AWS account and recorded a video to show you how to use it. There are two services you can use: 1. Ingest: This service uses a pretrained vision model to ingest and understand your knowledge base. 2. Search: This service combines text and vector search with a fine-tuned re-ranker model to retrieve information from your knowledge base. A quick note about the Ingest service: 99% of people think they need better "retrieval" mechanisms. I think they need better "ingestion." That's where this service comes in! Ingest "understands" your documents in a way I haven't seen before. After you try it, you'll realize why showing your LLM your raw documents is a bad idea. In the video, I use a free tool called X-Ray to test a document and understand how the Ingest service breaks it down. You can access this tool by signing up for a free GroundX cloud account and uploading your documents. You'll see a bit more about this in the video.

Santiago

89,664 views • 1 year ago

Use this FREE tool to analyze data in 10 sec. This tool is used by more than 500,000 researchers. 1. Go to and log in 2. Click on Data Analysis and upload your data file. 3. Write your prompt for data analysis. 4. E.g., generate graphs for exploratory data analysis. 5. Liner will generate a variety of graphs for you. 6. It also generates an insightful data analysis report. ✦ You can edit the report. For example, you can: ✦ Insert citations in the report ✦ Make changes to the text ✦ Add/remove any graphs After making changes, you can download the report. Try Liner today. It’s FREE. Liner link:

Use this FREE tool to analyze data in 10 sec. This tool is used by more than 500,000 researchers. 1. Go to and log in 2. Click on Data Analysis and upload your data file. 3. Write your prompt for data analysis. 4. E.g., generate graphs for exploratory data analysis. 5. Liner will generate a variety of graphs for you. 6. It also generates an insightful data analysis report. ✦ You can edit the report. For example, you can: ✦ Insert citations in the report ✦ Make changes to the text ✦ Add/remove any graphs After making changes, you can download the report. Try Liner today. It’s FREE. Liner link:

Faheem Ullah

11,959 views • 4 months ago

Struggling to find copyright-free music you can use in your content? Music Generation Agent creates original music you can use straight away in your content. Perfect if you’re starting (or scaling) a content creation journey. 👉 Generate music for your next video. Query this agent on

Struggling to find copyright-free music you can use in your content? Music Generation Agent creates original music you can use straight away in your content. Perfect if you’re starting (or scaling) a content creation journey. 👉 Generate music for your next video. Query this agent on

Fetch.ai

11,317 views • 5 months ago

Google Chrome invited Atomic Mail to test how the built-in Google Gemini can improve private email. Now you can run Atomic Mail AI features with Local Models on your device: – 100% private – Your data stays on your laptop – Zero cost Joint case study with Chrome for Developers coming soon – follow us! Guide + link in the comments.

Google Chrome invited Atomic Mail to test how the built-in Google Gemini can improve private email. Now you can run Atomic Mail AI features with Local Models on your device: – 100% private – Your data stays on your laptop – Zero cost Joint case study with Chrome for Developers coming soon – follow us! Guide + link in the comments.

Atomic Mail

62,288 views • 3 months ago

This week we launched the HSE Health app to make your healthcare available to you on your phone. This is part of our plan to digitalise our public services so you can access your information more efficiently. 📲The app is now available to download.

This week we launched the HSE Health app to make your healthcare available to you on your phone. This is part of our plan to digitalise our public services so you can access your information more efficiently. 📲The app is now available to download.

Fine Gael

26,964 views • 1 year ago

I made a new thing called Warvis is an input that lets you use AI wherver you can type on your iPhone without having to switch to ChatGPT or Claude i have been using in a lot to fix grammar, draft messages and search the internet while i'm chatting give it a try and let me know what you think

I made a new thing called Warvis is an input that lets you use AI wherver you can type on your iPhone without having to switch to ChatGPT or Claude i have been using in a lot to fix grammar, draft messages and search the internet while i'm chatting give it a try and let me know what you think

Massi

15,863 views • 20 days ago

Ok this is wild I found an AI tool that analyzes all of your posts based on the current X algo You enter in your post then the AI rates your post on 9 different X algo criteria It then gives you recommendations for improvement so you can make sure your post is a banger Oh ya: I made this tool. It's called Creator Buddy. I've been coding it for 12 months straight now 24 hours a day 7 days a week It's a complete AI content tool that helps make your content WAY better and get you way more followers It's the ONLY AI in the entire world trained on ALL of your posts I'm paying thousands a month for the X API to get all of this data. NO other tool is doing this. If you use Creator Buddy you will grow on X and go viral. Period. Link down below to try for free Would you use an Algo Analyzer to improve your content? (5 random people who comment, like and RT will get a free sub)

Ok this is wild I found an AI tool that analyzes all of your posts based on the current X algo You enter in your post then the AI rates your post on 9 different X algo criteria It then gives you recommendations for improvement so you can make sure your post is a banger Oh ya: I made this tool. It's called Creator Buddy. I've been coding it for 12 months straight now 24 hours a day 7 days a week It's a complete AI content tool that helps make your content WAY better and get you way more followers It's the ONLY AI in the entire world trained on ALL of your posts I'm paying thousands a month for the X API to get all of this data. NO other tool is doing this. If you use Creator Buddy you will grow on X and go viral. Period. Link down below to try for free Would you use an Algo Analyzer to improve your content? (5 random people who comment, like and RT will get a free sub)

Alex Finn

13,121 views • 1 year ago

Speak with ChatGPT: You can now use voice to engage in a back-and-forth conversation with your assistant. The hyper-realistic text-to-speech model allows you to choose from five different voices. On mobile, opt-in to voice in Settings → New Features on the mobile app.

Speak with ChatGPT: You can now use voice to engage in a back-and-forth conversation with your assistant. The hyper-realistic text-to-speech model allows you to choose from five different voices. On mobile, opt-in to voice in Settings → New Features on the mobile app.

Rowan Cheung

55,777 views • 2 years ago

Netflix opened up an attraction called “Netflix House” and you need to hear this “When you enter Netflix house, you give Netflix the right to you use your name, your likeness, and your voice in any use worldwide, forever, without compensation” This is real “When you go in and you read all the terms, when you walk in there, you're giving them everything. You're giving them your face, your, your movements, your identity, how you talk, how you walk, you're giving them everything. And you're giving them the right to AI generate you, and you're giving them the right to use all that in their content without compensating you whatsoever.” “Oh, and if you bring your child in there, you're also saying that it's okay for you, for, like, them to take your child's data, which is scary.” “So then I got to thinking, you know, why would they be doing this, right? Well, I live in New Jersey, and if you know, New Jersey is the home to the new Netflix, like, Hollywood Studio, essentially. And we know that Warner Brothers Netflix merge. Like, we know that there's a lot happening in the entertainment industry. They're going to need a lot more content to get put out. It's going to be AI generated. It's going to be us. You could not catch me dead walking in there dead.”

Netflix opened up an attraction called “Netflix House” and you need to hear this “When you enter Netflix house, you give Netflix the right to you use your name, your likeness, and your voice in any use worldwide, forever, without compensation” This is real “When you go in and you read all the terms, when you walk in there, you're giving them everything. You're giving them your face, your, your movements, your identity, how you talk, how you walk, you're giving them everything. And you're giving them the right to AI generate you, and you're giving them the right to use all that in their content without compensating you whatsoever.” “Oh, and if you bring your child in there, you're also saying that it's okay for you, for, like, them to take your child's data, which is scary.” “So then I got to thinking, you know, why would they be doing this, right? Well, I live in New Jersey, and if you know, New Jersey is the home to the new Netflix, like, Hollywood Studio, essentially. And we know that Warner Brothers Netflix merge. Like, we know that there's a lot happening in the entertainment industry. They're going to need a lot more content to get put out. It's going to be AI generated. It's going to be us. You could not catch me dead walking in there dead.”

Wall Street Apes

600,304 views • 8 months ago

How can you solve complex tasks using a Large Language Model? Here is a 2-minute introduction to everything you need to know to 10x the quality of your results. Let's talk about three techniques, in order of complexity, starting with the easiest one: • In-Context Learning • Indexing + In-Context Learning • Fine-tuning In-Context Learning The team that trained GPT-3 found something they couldn't explain: You can condition a model using examples of how you want it to behave. I included an example prompt in the attached video. You can "teach" the model how you want it to interpret questions, select the correct answers, and format the results by giving a few examples. You can also give specific knowledge to the model that will be helpful when formulating answers. We call this approach "grounding the model." There's another example in the video. Indexing + In-Context Learning Unfortunately, there is a limit to how much data you can include in a prompt. We call this the "context size." One version of GPT-4 supports a context of approximately 6,000 words, while the other supports 25,000 words. Although this sounds like a lot, many applications need more than that. Imagine you wrote a book and want to build an application to answer any questions about your story. What happens if your book is longer than the context? That's where Indexing comes in. Using a model, you can turn every book passage into an embedding. These are vectors, numbers that "encode" the passage's text. You can then store these embeddings in a particular database that supports fast retrieval of these vectors. You can then turn any question into an embedding and search the database for the list of passages that are similar to that query. Instead of using the entire book to ask the model, you can now use the relevant passages as in-context information, effectively working around the context size limitation. Fine-tuning Fine-tuning can give you an extra boost to get reliable outputs from your LLM. It is, however, the most complex approach on the list. There are different approaches to fine-tuning a model with your data. A popular technique is to process your data with your LLM and use the outputs to train a new classifier that solves your specific task. Notice that here you aren't modifying the LLM. Instead, you are chaining it with your trained classifier. Another approach is to modify the parameters of the LLM using your data. Think of this as "rewiring" the model in a way that solves your particular task. The results and costs will vary depending on how many layers you want to fine-tune from the original model. Many companies think that fine-tuning is the solution to their problems. In my experience, many will benefit from exploring the other two approaches. I love explaining Machine Learning and Artificial Intelligence ideas. If you enjoy in-depth content like this, follow me Santiago so you don't miss what comes next.

How can you solve complex tasks using a Large Language Model? Here is a 2-minute introduction to everything you need to know to 10x the quality of your results. Let's talk about three techniques, in order of complexity, starting with the easiest one: • In-Context Learning • Indexing + In-Context Learning • Fine-tuning In-Context Learning The team that trained GPT-3 found something they couldn't explain: You can condition a model using examples of how you want it to behave. I included an example prompt in the attached video. You can "teach" the model how you want it to interpret questions, select the correct answers, and format the results by giving a few examples. You can also give specific knowledge to the model that will be helpful when formulating answers. We call this approach "grounding the model." There's another example in the video. Indexing + In-Context Learning Unfortunately, there is a limit to how much data you can include in a prompt. We call this the "context size." One version of GPT-4 supports a context of approximately 6,000 words, while the other supports 25,000 words. Although this sounds like a lot, many applications need more than that. Imagine you wrote a book and want to build an application to answer any questions about your story. What happens if your book is longer than the context? That's where Indexing comes in. Using a model, you can turn every book passage into an embedding. These are vectors, numbers that "encode" the passage's text. You can then store these embeddings in a particular database that supports fast retrieval of these vectors. You can then turn any question into an embedding and search the database for the list of passages that are similar to that query. Instead of using the entire book to ask the model, you can now use the relevant passages as in-context information, effectively working around the context size limitation. Fine-tuning Fine-tuning can give you an extra boost to get reliable outputs from your LLM. It is, however, the most complex approach on the list. There are different approaches to fine-tuning a model with your data. A popular technique is to process your data with your LLM and use the outputs to train a new classifier that solves your specific task. Notice that here you aren't modifying the LLM. Instead, you are chaining it with your trained classifier. Another approach is to modify the parameters of the LLM using your data. Think of this as "rewiring" the model in a way that solves your particular task. The results and costs will vary depending on how many layers you want to fine-tune from the original model. Many companies think that fine-tuning is the solution to their problems. In my experience, many will benefit from exploring the other two approaches. I love explaining Machine Learning and Artificial Intelligence ideas. If you enjoy in-depth content like this, follow me Santiago so you don't miss what comes next.

Santiago

384,510 views • 3 years ago

I've missed doing design explorations. Tried to do some cool stuff for Valentine's day. So you can probably use this for page for your partner. You can try this out on desktop only - Link is on the thread. Thank me later 🧡.

I've missed doing design explorations. Tried to do some cool stuff for Valentine's day. So you can probably use this for page for your partner. You can try this out on desktop only - Link is on the thread. Thank me later 🧡.

Design Chief Priest

44,594 views • 6 months ago

Imagine an AI application that can type anywhere you can and use the full context of what's on your screen. This is the application we all deserve (at least if you have macOS.) Check out Omnipilot. It's an app that works with every other macOS application and uses Claude Sonet 3.5 in the background—it also supports Gemini and GPT-4o. Here is the idea: You can use the tool to ask questions about anything on your screen. Or you can use it to autocomplete the text you are typing. You don't need to copy and paste anymore or waste your time providing context to a model. It sees what you see. It works right where you are. That's pretty cool. Here are a couple of cool examples: • Use it to reply to an email • Use it in the terminal to autocomplete a command • Use it to finish a document • Use to send a message on Slack AI at the system level is bonkers. You can read a ton more on their Product Hunt launch page: Thanks to the Omnipilot team for collaborating with me on this post!

Imagine an AI application that can type anywhere you can and use the full context of what's on your screen. This is the application we all deserve (at least if you have macOS.) Check out Omnipilot. It's an app that works with every other macOS application and uses Claude Sonet 3.5 in the background—it also supports Gemini and GPT-4o. Here is the idea: You can use the tool to ask questions about anything on your screen. Or you can use it to autocomplete the text you are typing. You don't need to copy and paste anymore or waste your time providing context to a model. It sees what you see. It works right where you are. That's pretty cool. Here are a couple of cool examples: • Use it to reply to an email • Use it in the terminal to autocomplete a command • Use it to finish a document • Use to send a message on Slack AI at the system level is bonkers. You can read a ton more on their Product Hunt launch page: Thanks to the Omnipilot team for collaborating with me on this post!

Santiago

72,306 views • 2 years ago