Loading video...

Video Failed to Load

Go Home

Lecture 11 is a tool-use/function calling/agentic 101! I almost skipped this one, as this chapter started as the only skill-specific topic in the book, but since writing it tool-use has only become more foundational to modern models. This is a tour from the basics -- why LLMs need tools...

natolambert's profile picture

Nathan Lambert

97,411 subscribers

43,065 views • 9 days ago •via X (Twitter)

Science & TechnologyEducationHealth & Wellness
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

The final lecture of my course is an intro to character training! This is a topic that I've been quietly very invested in for ~18 months, as it: * Has potential for high real world impact * Clearly used extensively at frontier labs * Almost no empirical literature exists * More accessible on academic compute This lecture covers what character training is, reviews model specs, constitutions, the differences, the motivations in real world events, some example research papers I like, and open questions in how it relates to post-training/model use generally. Hopefully this brings more people into the field (and reach out if you have questions). It is one of the more research-y chapters in my book, but one that I felt needed the reference. There is still so little, educational content on the topic online. 0:00 Intro 6:22 Part 1: Fundamentals — character, constitutions, and model specs 19:21 Part 2: Character training in practice 23:23 Part 3: Character elicitation without gradient steps 28:03 Part 4: Open questions (and the end of the course) 32:27 The course, complete Thanks for watching. No need to like and subscribe now that the course is done, you definitely wouldn't! h/t to Sharan for leading the technical work I got to do in the space, and Zafir Stojanovski for investing a lot of attention at this book chapter.
32:55

The final lecture of my course is an intro to character training! This is a topic that I've been quietly very invested in for ~18 months, as it: * Has potential for high real world impact * Clearly used extensively at frontier labs * Almost no empirical literature exists * More accessible on academic compute This lecture covers what character training is, reviews model specs, constitutions, the differences, the motivations in real world events, some example research papers I like, and open questions in how it relates to post-training/model use generally. Hopefully this brings more people into the field (and reach out if you have questions). It is one of the more research-y chapters in my book, but one that I felt needed the reference. There is still so little, educational content on the topic online. 0:00 Intro 6:22 Part 1: Fundamentals — character, constitutions, and model specs 19:21 Part 2: Character training in practice 23:23 Part 3: Character elicitation without gradient steps 28:03 Part 4: Open questions (and the end of the course) 32:27 The course, complete Thanks for watching. No need to like and subscribe now that the course is done, you definitely wouldn't! h/t to Sharan for leading the technical work I got to do in the space, and Zafir Stojanovski for investing a lot of attention at this book chapter.

Nathan Lambert

54,625 views • 3 days ago

gm! If you missed yesterday's space, here is the clip that you can listen explaining why Agent NFTs are important and future of NFTs. Also here is the TL;DR Agentic NFTs as productive assets. An NFT can own an AI agent's shared memory, tools, websites, and products it has built. Selling the NFT transfers the entire business/agent state to the new owner. ERC-8257 for tool-gating. CodinCowboy and ryan is working on the standard where agents register tools on-chain and access is gated by NFT ownership. That component that tells an agent "you need this NFT to use this tool" creating a market for exclusive tools. Use case: anyone can publish a tool and restrict it (e.g., "only Normies agents can call this"), letting tool value flow back to the gating NFT. Normies community fit. Normies API has served ~500M requests in 3 months, with 100+ community-built tools/games. ERC-8257 will let them build gated games, rewards, and skills exclusively for Normie agent holders. Why Normies is "agent-ready"? - Because everything is fully on-chain, metadata, ERCs, binding transaction. So the project is highly composable. My take on this topic: So far holding an NFT giving access to community, discord and merch. What we are doing with Normies is to give access to a business, tools, skills that agents can use effectively and be part of the economy layer of agentic future. Imagine someone builds a tool that does really 100% successful trading and only gates that skill to Normie Agents, and at some point you will only need a Normie NFT which has binding with the agent and access all these skills, tools. Future is now, Normies are the builders.
6:08

gm! If you missed yesterday's space, here is the clip that you can listen explaining why Agent NFTs are important and future of NFTs. Also here is the TL;DR Agentic NFTs as productive assets. An NFT can own an AI agent's shared memory, tools, websites, and products it has built. Selling the NFT transfers the entire business/agent state to the new owner. ERC-8257 for tool-gating. CodinCowboy and ryan is working on the standard where agents register tools on-chain and access is gated by NFT ownership. That component that tells an agent "you need this NFT to use this tool" creating a market for exclusive tools. Use case: anyone can publish a tool and restrict it (e.g., "only Normies agents can call this"), letting tool value flow back to the gating NFT. Normies community fit. Normies API has served ~500M requests in 3 months, with 100+ community-built tools/games. ERC-8257 will let them build gated games, rewards, and skills exclusively for Normie agent holders. Why Normies is "agent-ready"? - Because everything is fully on-chain, metadata, ERCs, binding transaction. So the project is highly composable. My take on this topic: So far holding an NFT giving access to community, discord and merch. What we are doing with Normies is to give access to a business, tools, skills that agents can use effectively and be part of the economy layer of agentic future. Imagine someone builds a tool that does really 100% successful trading and only gates that skill to Normie Agents, and at some point you will only need a Normie NFT which has binding with the agent and access all these skills, tools. Future is now, Normies are the builders.

serc

14,066 views • 2 months ago

I was asked a few times at work and by some other folks how I go about making pipes, cables, edge decals, etc in #maya I use the Sweep Tool for a ton of this stuff. I had to break this up but I hope you enjoy it, have fun! The non broken up video is below this post.
2:16

I was asked a few times at work and by some other folks how I go about making pipes, cables, edge decals, etc in #maya I use the Sweep Tool for a ton of this stuff. I had to break this up but I hope you enjoy it, have fun! The non broken up video is below this post.

Kill the Butcher 🪨⚰️☕️

17,149 views • 2 years ago

Jensen Huang just said this is the greatest era in history to build software. AI agents will not kill software. They will do the exact opposite: create a massive new wave of software demand. at NVIDIA GTC Taipei 2026 "Click and type. We now replace that with explaining to the AI what we want, our intent, and the AI generates the code or uses tools to produce the necessary output. This is how computers are going to work in the future. This is Agentic AI. For two years, we've been building toward this, and now it has arrived. One of the big breakthroughs, of course, is tool use. A lot of people have said, “Jensen, AI is coming. Agentic AI is coming. Therefore, all the software companies are going to go out of business.” This is exactly the opposite. Because there are going to be so many agents, the world is no longer limited by the number of people. Therefore, those agents are going to use more tools than ever. This is actually an incredible time to be a software company. But the software has to be presented to the agent in a way that the agent can use it. This is a big breakthrough. And in fact, what we have done, as you know, what Nvidia’s treasure..." ---- From 'NVIDIA' YT channel (link in comment)
0:59

Jensen Huang just said this is the greatest era in history to build software. AI agents will not kill software. They will do the exact opposite: create a massive new wave of software demand. at NVIDIA GTC Taipei 2026 "Click and type. We now replace that with explaining to the AI what we want, our intent, and the AI generates the code or uses tools to produce the necessary output. This is how computers are going to work in the future. This is Agentic AI. For two years, we've been building toward this, and now it has arrived. One of the big breakthroughs, of course, is tool use. A lot of people have said, “Jensen, AI is coming. Agentic AI is coming. Therefore, all the software companies are going to go out of business.” This is exactly the opposite. Because there are going to be so many agents, the world is no longer limited by the number of people. Therefore, those agents are going to use more tools than ever. This is actually an incredible time to be a software company. But the software has to be presented to the agent in a way that the agent can use it. This is a big breakthrough. And in fact, what we have done, as you know, what Nvidia’s treasure..." ---- From 'NVIDIA' YT channel (link in comment)

Rohan Paul

16,584 views • 2 months ago

This is what Kamala Harris was talking in that one interview. This is just a small part but she explains this whole thing very clearly in the rest of the interview. I believe they did the same with kanye and more, they do this only to the naive and already dumb so they can use them as a manipulation tool for their own agenda. Who would have thought that the pink wig gays will turn MAGA that fast, and here we are.
0:50

This is what Kamala Harris was talking in that one interview. This is just a small part but she explains this whole thing very clearly in the rest of the interview. I believe they did the same with kanye and more, they do this only to the naive and already dumb so they can use them as a manipulation tool for their own agenda. Who would have thought that the pink wig gays will turn MAGA that fast, and here we are.

COWBOY 🇵🇱

949,192 views • 8 months ago

Lecture 10 of my course! Nominally on regularization in RL, so I discuss the evolving role of the KL penalty in RL, but also a set of nice RL papers that explain what RL helps models generalize better than SFT -- with theory supporting it. When going through these, it's so interesting how seasonal problems in ML are. Lots of problems from controlling reward models overopt will rhyme as we try to control rubrics for agents. 00:00 Intro & the role of regularization 02:50 The KL penalty in RL 10:53 RL as a reverse KL loss 21:09 Why RL generalizes better than SFT 25:15 Other regularization tools Just a few videos left as I get to the end of the course. Thanks all, and keep sending questions. Spread the word if you have a second.
31:33

Lecture 10 of my course! Nominally on regularization in RL, so I discuss the evolving role of the KL penalty in RL, but also a set of nice RL papers that explain what RL helps models generalize better than SFT -- with theory supporting it. When going through these, it's so interesting how seasonal problems in ML are. Lots of problems from controlling reward models overopt will rhyme as we try to control rubrics for agents. 00:00 Intro & the role of regularization 02:50 The KL penalty in RL 10:53 RL as a reverse KL loss 21:09 Why RL generalizes better than SFT 25:15 Other regularization tools Just a few videos left as I get to the end of the course. Thanks all, and keep sending questions. Spread the word if you have a second.

Nathan Lambert

87,914 views • 12 days ago

Excited to present the LLM-Council skill. Initial idea by Karpathy. I just packaged it as a skill. You can easily spin up a council of LLMs or agents via Fireworks. Watch how the new GLM-5 model "deliberates" on other LLMs' thoughts on the big question, "Can LLMs reason?" Things worth paying attention to: New open models like GLM-5 have surprisingly improved on complex reasoning and long-running agentic tasks. The AskUserQuestion tool in Claude Code came in handy to select the council and chairperson. As Andrej Karpathy puts it, it's a really interesting way to get different perspectives from LLMs, which can lead to better decision-making on whatever task you are working on. You can use it for other agentic coding use cases, like evaluation, tool building, designing, and research.
0:35

Excited to present the LLM-Council skill. Initial idea by Karpathy. I just packaged it as a skill. You can easily spin up a council of LLMs or agents via Fireworks. Watch how the new GLM-5 model "deliberates" on other LLMs' thoughts on the big question, "Can LLMs reason?" Things worth paying attention to: New open models like GLM-5 have surprisingly improved on complex reasoning and long-running agentic tasks. The AskUserQuestion tool in Claude Code came in handy to select the council and chairperson. As Andrej Karpathy puts it, it's a really interesting way to get different perspectives from LLMs, which can lead to better decision-making on whatever task you are working on. You can use it for other agentic coding use cases, like evaluation, tool building, designing, and research.

elvis

39,593 views • 5 months ago

I’m excited to kick off the first of our short courses focused on agents, starting with Building Agentic RAG with LlamaIndex, taught by Jerry Liu, CEO of LlamaIndex 🦙. This covers an important shift in RAG (retrieval augmented generation), in which rather than having the developer write explicit routines to retrieve information to feed into the LLM context, we instead build a RAG agent that that has access to tools for retrieving information. This lets the agent decide what information to fetch, and enables it to answer more complex questions using multi-step reasoning. In detail, you'll learn about: - Routing: Where your agent will use decision-making to route requests to multiple tools. - Tool Use: Where you'll create an interface for agents to select what tool (function call) to use as well as generate the right arguments. - Multi-step reasoning with tool use: Where you'll use an LLM to carry out multiple steps of reasoning, while retaining memory throughout the process. You’ll also learn how to step through what your agent is doing to debug and improve it iteratively. It’s an exciting time to build agents. Sign up and get started here!
2:06

I’m excited to kick off the first of our short courses focused on agents, starting with Building Agentic RAG with LlamaIndex, taught by Jerry Liu, CEO of LlamaIndex 🦙. This covers an important shift in RAG (retrieval augmented generation), in which rather than having the developer write explicit routines to retrieve information to feed into the LLM context, we instead build a RAG agent that that has access to tools for retrieving information. This lets the agent decide what information to fetch, and enables it to answer more complex questions using multi-step reasoning. In detail, you'll learn about: - Routing: Where your agent will use decision-making to route requests to multiple tools. - Tool Use: Where you'll create an interface for agents to select what tool (function call) to use as well as generate the right arguments. - Multi-step reasoning with tool use: Where you'll use an LLM to carry out multiple steps of reasoning, while retaining memory throughout the process. You’ll also learn how to step through what your agent is doing to debug and improve it iteratively. It’s an exciting time to build agents. Sign up and get started here!

Andrew Ng

297,131 views • 2 years ago

Finally got a chance to play around with Andrej Karpathy's LLM Council. I built it as a plugin inside of Claude Code. Hooked it up with OpenRouter for models. The AskUserQuestion tool came in handy to select the council and chairman. This is my first test, but I agree with Karpathy that the concept of LLM ensembles can be used beyond models that offer perspectives on interesting questions. I feel like this could have really cool applications in agentic coding. More on that soon. I built this as a plugin, so next I will be exploring other user cases around agentic coding, like evaluation, tool building, designing, and research. If there is enough interest, I will clean it up and push it out as an open plugin.
0:38

Finally got a chance to play around with Andrej Karpathy's LLM Council. I built it as a plugin inside of Claude Code. Hooked it up with OpenRouter for models. The AskUserQuestion tool came in handy to select the council and chairman. This is my first test, but I agree with Karpathy that the concept of LLM ensembles can be used beyond models that offer perspectives on interesting questions. I feel like this could have really cool applications in agentic coding. More on that soon. I built this as a plugin, so next I will be exploring other user cases around agentic coding, like evaluation, tool building, designing, and research. If there is enough interest, I will clean it up and push it out as an open plugin.

elvis

79,766 views • 7 months ago

I've used basically every knowledge management and project management tool out there, and every tool has the same problem. they expect me to do things that computers should do. meanwhile, so many AI tools replace the wrong work. i want to do more creative work, less administrative work. the right tool SHOULD assist me at doing my best work. but no tool has ever done that for me! so here's the first public demo of my dream solution to both problems, in the form of deeply personalized software. i've had so much fun building this, and it's already had a materially positive impact on my life. would love to share more, so ask questions and I'll go deeper into how various parts of the system work under the hood!
49:36

I've used basically every knowledge management and project management tool out there, and every tool has the same problem. they expect me to do things that computers should do. meanwhile, so many AI tools replace the wrong work. i want to do more creative work, less administrative work. the right tool SHOULD assist me at doing my best work. but no tool has ever done that for me! so here's the first public demo of my dream solution to both problems, in the form of deeply personalized software. i've had so much fun building this, and it's already had a materially positive impact on my life. would love to share more, so ask questions and I'll go deeper into how various parts of the system work under the hood!

📙 Alex Hillman

47,462 views • 7 months ago

We live in the solo founder era. That's for sure and building with AI has accelerated. I am building software to use for myself and replace the expensive tools I used to use. And partially thanks to AI we can build faster, but not dramatically faster if you want to build a commercial grade product. Before I was using a live chat and customer support tool that costed around 50-100$ a month. This helped me to interact with the customers of my agency or prospects. But I decided a few months ago to build my own and stop paying for these more expensive solutions. I did and turned into a product for everyone to use. The build was not 1-2 hours of work using AI, but it was a several-month process on and off as I needed it. Finally, it has turned into a commercial grade product. I have built several of these and this is when we will see more and more solutions like these. Let's start bootstrapping before showing MRR figures.
0:42

We live in the solo founder era. That's for sure and building with AI has accelerated. I am building software to use for myself and replace the expensive tools I used to use. And partially thanks to AI we can build faster, but not dramatically faster if you want to build a commercial grade product. Before I was using a live chat and customer support tool that costed around 50-100$ a month. This helped me to interact with the customers of my agency or prospects. But I decided a few months ago to build my own and stop paying for these more expensive solutions. I did and turned into a product for everyone to use. The build was not 1-2 hours of work using AI, but it was a several-month process on and off as I needed it. Finally, it has turned into a commercial grade product. I have built several of these and this is when we will see more and more solutions like these. Let's start bootstrapping before showing MRR figures.

andrei saioc

14,422 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!
1:28

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 • 4 months ago

people have been constantly asking what i use to scan for/find coins i only use one tool: DEXSCREENER.. & THAT'S IT as someone who has been trading on chain for years i have been around for the advent of a ton of bots & tools and have tried using a majority of them many have actually made the trading process a lot more streamlined but the MAJORITY are just useless noise imo let me explain: everyone is looking for the "magic" tool/bot that is going to find them the next 100x-1000x coin when i first started out i thought that using all of them or finding that "magic" tool was going to be the secret to help me trade better but i can promise you 99% of experienced traders would say that manual action & research will beat out these "bots/tools" every time get good at one or few of them and cut out all the noise by thinking you need to try and use them all to successfully trade ---------- with dexscreener all i do is throughout the entire day whether im on my phone or computer i: - cycle through the 5 min, 1 hour, 6 hour, & 24 hour timeframes - will input FDV of max of 1,000,000 & 500,000 - switch between highest volume & most makers why? when i cycle through all of that over and over it will not only find fresh launches with a lot of velocity & potential but it also gives a good gauge on whats working and what the true "meta" is i have found a ton of hidden gems this way too cycling through it all will find you some diamond in the rough coins that are getting low key bid hard but arent talked about on CT yet is this a perfect science? no. but i like to simplify my trading & it is what i use/my preference for hunting and finding coins ---------- while my tool of choice is dexscreener you might find a liking to something else & that's completely fine - we all have our own preferences but whatever you like using just become a master of it
1:00

people have been constantly asking what i use to scan for/find coins i only use one tool: DEXSCREENER.. & THAT'S IT as someone who has been trading on chain for years i have been around for the advent of a ton of bots & tools and have tried using a majority of them many have actually made the trading process a lot more streamlined but the MAJORITY are just useless noise imo let me explain: everyone is looking for the "magic" tool/bot that is going to find them the next 100x-1000x coin when i first started out i thought that using all of them or finding that "magic" tool was going to be the secret to help me trade better but i can promise you 99% of experienced traders would say that manual action & research will beat out these "bots/tools" every time get good at one or few of them and cut out all the noise by thinking you need to try and use them all to successfully trade ---------- with dexscreener all i do is throughout the entire day whether im on my phone or computer i: - cycle through the 5 min, 1 hour, 6 hour, & 24 hour timeframes - will input FDV of max of 1,000,000 & 500,000 - switch between highest volume & most makers why? when i cycle through all of that over and over it will not only find fresh launches with a lot of velocity & potential but it also gives a good gauge on whats working and what the true "meta" is i have found a ton of hidden gems this way too cycling through it all will find you some diamond in the rough coins that are getting low key bid hard but arent talked about on CT yet is this a perfect science? no. but i like to simplify my trading & it is what i use/my preference for hunting and finding coins ---------- while my tool of choice is dexscreener you might find a liking to something else & that's completely fine - we all have our own preferences but whatever you like using just become a master of it

patience

130,661 views • 2 years ago

I had to do this of course - test out the new Google Omni Flash model with my favorite 3d art sandbox - Dreams. Just a quick test for now.. I'll be sharing more examples and techniques soon but wanted to show you this one. There's something very fitting about combining "handmade" 3d models and animations sculpted from scratch in software that runs on 2013 hardware, with some of the most advanced AI technology in the world. As part of my work for Google, I've used Google V2V models on a few different projects now - Ancestra, Dear Upstairs Neighbors and most recently one of the IO films (I'll share more about that project soon) 🥰 - and video continues to be my favorite form of input for Generative Ai workflows. If an image says more than a thousand words, a video says more than a million. And knowing that these capabilities are now in the hands of all of you, makes me very excited to see the new workflows and projects that will come out of it. What do you think of Omni so far?
0:45

I had to do this of course - test out the new Google Omni Flash model with my favorite 3d art sandbox - Dreams. Just a quick test for now.. I'll be sharing more examples and techniques soon but wanted to show you this one. There's something very fitting about combining "handmade" 3d models and animations sculpted from scratch in software that runs on 2013 hardware, with some of the most advanced AI technology in the world. As part of my work for Google, I've used Google V2V models on a few different projects now - Ancestra, Dear Upstairs Neighbors and most recently one of the IO films (I'll share more about that project soon) 🥰 - and video continues to be my favorite form of input for Generative Ai workflows. If an image says more than a thousand words, a video says more than a million. And knowing that these capabilities are now in the hands of all of you, makes me very excited to see the new workflows and projects that will come out of it. What do you think of Omni so far?

Martin Nebelong

38,411 views • 2 months ago

Elon Musk: Neuralink will be a jet airplane for neurosurgeons. “I think this is going to be an incredibly powerful tool for neurosurgeons for helping to fix brain-related issues. If it was a weapon situation, it might be like the difference between bows and arrows and jet airplanes. A big difference, in a positive, constructive way. One can only do as well as the tools that one is given. By essentially giving neurosurgeons a much more sophisticated, powerful tool like the Neuralink device, you could really help a lot of people.” Interview at CNS, October 2024
0:42

Elon Musk: Neuralink will be a jet airplane for neurosurgeons. “I think this is going to be an incredibly powerful tool for neurosurgeons for helping to fix brain-related issues. If it was a weapon situation, it might be like the difference between bows and arrows and jet airplanes. A big difference, in a positive, constructive way. One can only do as well as the tools that one is given. By essentially giving neurosurgeons a much more sophisticated, powerful tool like the Neuralink device, you could really help a lot of people.” Interview at CNS, October 2024

ELON CLIPS

53,686 views • 10 months ago

I'm currently going through this "Developing Large Language Models" course. You definitely want to check it out. Actually, this is much more than a course: it's a complete skill track from DataCamp. It starts with an introduction to PyTorch, neural networks, all the way to large language models. This starts from the very beginning. Literally, the solution to the first exercise is to `import torch`! I recorded the attached video to tell you a bit more about this. I partnered with Datacamp because their platform is one of the best for leveling up in the DS/ML/AI space. Then, I found this course and started taking it. Now, I don't want to stop!
2:43

I'm currently going through this "Developing Large Language Models" course. You definitely want to check it out. Actually, this is much more than a course: it's a complete skill track from DataCamp. It starts with an introduction to PyTorch, neural networks, all the way to large language models. This starts from the very beginning. Literally, the solution to the first exercise is to `import torch`! I recorded the attached video to tell you a bit more about this. I partnered with Datacamp because their platform is one of the best for leveling up in the DS/ML/AI space. Then, I found this course and started taking it. Now, I don't want to stop!

Santiago

30,047 views • 1 year ago

this is Zero. i was going to launch Zero 6 months ago, but decided not to. i felt if we launched too early, the team would get distracted. the product still had areas where i wanted to make the experience incredible, not just 'good'. Zero is more like a video game or movie, where the experience matters. it's not a tool, it's immersive. how people feel when they use it matters. it needed to be fast, feel real, and actually work. so instead of launching, we went heads down for 6 months to craft the best learning experience the world has seen. it has the best applied AI models, immersive experiences that feel like the real-world (like kick-off meetings, feedback walk-throughs, and real-time collaboration), and modern workflows that train people on how to use AI tools to make them more productive, rather than use them mindlessly as a crutch. it was a tough decision because my team put a ton of work into this video and wanted the world to see it. imagine, this was made 6 months ago! i'm super proud of my team for what they made, and i'm even more proud to finally share this with the world. so yea, this is Zero. this is the future of education. to join the beta, let me know in the thread.
4:18

this is Zero. i was going to launch Zero 6 months ago, but decided not to. i felt if we launched too early, the team would get distracted. the product still had areas where i wanted to make the experience incredible, not just 'good'. Zero is more like a video game or movie, where the experience matters. it's not a tool, it's immersive. how people feel when they use it matters. it needed to be fast, feel real, and actually work. so instead of launching, we went heads down for 6 months to craft the best learning experience the world has seen. it has the best applied AI models, immersive experiences that feel like the real-world (like kick-off meetings, feedback walk-throughs, and real-time collaboration), and modern workflows that train people on how to use AI tools to make them more productive, rather than use them mindlessly as a crutch. it was a tough decision because my team put a ton of work into this video and wanted the world to see it. imagine, this was made 6 months ago! i'm super proud of my team for what they made, and i'm even more proud to finally share this with the world. so yea, this is Zero. this is the future of education. to join the beta, let me know in the thread.

Navid Nathoo

14,068 views • 2 months ago