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.

This is it: A single-person project; Trained from scratch on TPUs (Google TRC) on the one and only SYTNH dataset by pleias; Neuroblast-v3 architecture running on my local vLLM instance Just wow (I'm amazed by how good it looks; speed is incredible, here slightly slowed by high-resolution recording) Todos... show more

Mariusz Kurman

3,855 subscribers

32,474 views • 7 months ago •via X (Twitter)

Health & Wellness Education Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

How tough is Rep. Tim Burchett? He got kicked in the ribs by a horse, broke one, and still barely missed a single meeting. No ambulance, no time off. America needs more grit like this. Christian Hartsock Guest hosts Fine Point only on One America News

How tough is Rep. Tim Burchett? He got kicked in the ribs by a horse, broke one, and still barely missed a single meeting. No ambulance, no time off. America needs more grit like this. Christian Hartsock Guest hosts Fine Point only on One America News

One America News

71,037 views • 1 year ago

HRM-Text 101 is here. This tutorial takes you from zero to one: from setup to fine-tuning to evaluation. Download the base checkpoint. Fine-tune it on a real task. Evaluate the results. End to end, on a single GPU. Watch the tutorial and start building with HRM-Text.

HRM-Text 101 is here. This tutorial takes you from zero to one: from setup to fine-tuning to evaluation. Download the base checkpoint. Fine-tune it on a real task. Evaluate the results. End to end, on a single GPU. Watch the tutorial and start building with HRM-Text.

Sapient Intelligence

188,105 views • 2 months ago

watch and let this sit for a second anon, a 35B AI model, building a complete multi-file game by itself on hermes agent. no cloud or api. not one line of code written by a human. running on a DGX spark in 2026. because not long ago this was science fiction. this is Ornith, a new open agentic coding model, running near lossless on a single DGX Spark, a 128GB box that sits on your desk. i hand it one spec and step back. it reasons about the architecture, creates the project structure, writes every module one by one, and here's the part that got me, it checks its own work as it goes. makes a call, reads the result, decides if it's right, corrects itself before moving on. no steering from me. this is what people keep underestimating about local AI. they hear "local" and think weaker, slower, a toy. watch the clip. a 35B at near full precision, planning and self correcting on a single desktop. the open models got genuinely good at agentic work, not benchmark good, actually builds the thing good. sped 5x so you can watch the whole build start to finish. this is where local AI actually is now. not coming soon. here.

watch and let this sit for a second anon, a 35B AI model, building a complete multi-file game by itself on hermes agent. no cloud or api. not one line of code written by a human. running on a DGX spark in 2026. because not long ago this was science fiction. this is Ornith, a new open agentic coding model, running near lossless on a single DGX Spark, a 128GB box that sits on your desk. i hand it one spec and step back. it reasons about the architecture, creates the project structure, writes every module one by one, and here's the part that got me, it checks its own work as it goes. makes a call, reads the result, decides if it's right, corrects itself before moving on. no steering from me. this is what people keep underestimating about local AI. they hear "local" and think weaker, slower, a toy. watch the clip. a 35B at near full precision, planning and self correcting on a single desktop. the open models got genuinely good at agentic work, not benchmark good, actually builds the thing good. sped 5x so you can watch the whole build start to finish. this is where local AI actually is now. not coming soon. here.

Sudo su

30,299 views • 1 month ago

New short course on Fine-tuning LLMs! Many developers are moving beyond only prompting, to also fine-tuning LLMs - that is, taking a pre-trained model and training it further on your own data, which can deliver superior results inexpensively. In this course, Sharon Zhou, CEO of Lamini (disclosure: I’m a minor shareholder) shows you how to recognize when fine-tuning can be help, and how to train an open-source LLM on your own data. I hope you enjoy the course!

New short course on Fine-tuning LLMs! Many developers are moving beyond only prompting, to also fine-tuning LLMs - that is, taking a pre-trained model and training it further on your own data, which can deliver superior results inexpensively. In this course, Sharon Zhou, CEO of Lamini (disclosure: I’m a minor shareholder) shows you how to recognize when fine-tuning can be help, and how to train an open-source LLM on your own data. I hope you enjoy the course!

Andrew Ng

502,854 views • 3 years ago

We just reached the text to mobile apps moment. CatDoes v3 lets you go from a single idea to a real iOS, Android and web app by chatting with AI agents. Here is a WhatsApp style app going from blank project to running on an iPhone in one session.

We just reached the text to mobile apps moment. CatDoes v3 lets you go from a single idea to a real iOS, Android and web app by chatting with AI agents. Here is a WhatsApp style app going from blank project to running on an iPhone in one session.

Chubby♨️

24,878 views • 7 months ago

YOUR NEW PATRIOTIC SONG JUST DROPPED! 🇺🇸 "One Nation," from Steve Gruber & The Freedom Project and Real America's Music, is a new patriotic anthem you're going to have on repeat. "This country needs patriotism. This country needs a chance to come together." 🎶 DOWNLOAD it now by scanning the QR code or clicking the link in the comments.

YOUR NEW PATRIOTIC SONG JUST DROPPED! 🇺🇸 "One Nation," from Steve Gruber & The Freedom Project and Real America's Music, is a new patriotic anthem you're going to have on repeat. "This country needs patriotism. This country needs a chance to come together." 🎶 DOWNLOAD it now by scanning the QR code or clicking the link in the comments.

Real America's Voice (RAV)

398,946 views • 1 month ago

Still the best hour on graph engineering ever recorded, Andrew Ng breaking down how to build agentic knowledge graphs from scratch: 00:00 - what agentic knowledge graphs actually are 03:05 - building a graph from scratch 13:58 - the architecture behind multi-agent systems 22:57 - building a real one with Google ADK 01:06:02 - why graphs are the future of AI agents I've seen $500 courses that teach less. Watch it, then take it further with my step-by-step guide on graph engineering below.

Still the best hour on graph engineering ever recorded, Andrew Ng breaking down how to build agentic knowledge graphs from scratch: 00:00 - what agentic knowledge graphs actually are 03:05 - building a graph from scratch 13:58 - the architecture behind multi-agent systems 22:57 - building a real one with Google ADK 01:06:02 - why graphs are the future of AI agents I've seen $500 courses that teach less. Watch it, then take it further with my step-by-step guide on graph engineering below.

Anatoli Kopadze

259,501 views • 8 days ago

This may look like a game of Counterstrike running slowly, but it actually extraordinary. The entire game is created, frame-by-frame, on my *home computer* by an AI diffusion model in response to my actions. There is no game engine, just a "world model" trained on Counterstrike

This may look like a game of Counterstrike running slowly, but it actually extraordinary. The entire game is created, frame-by-frame, on my home computer by an AI diffusion model in response to my actions. There is no game engine, just a "world model" trained on Counterstrike

Ethan Mollick

376,399 views • 1 year ago

Row by row fine tuning and singulation testing. It’s tedious as hell but the picket fence spacing is worth it in looks and in my opinion, financially as well.. Bean variety testing is done. Corn is on deck for hybrid singulation testing but not before I start planting beans this week. It’s go time!

Row by row fine tuning and singulation testing. It’s tedious as hell but the picket fence spacing is worth it in looks and in my opinion, financially as well.. Bean variety testing is done. Corn is on deck for hybrid singulation testing but not before I start planting beans this week. It’s go time!

Banded Ag, LLC

13,860 views • 1 year ago

Apple built a large foundation model and fine-tuned it on multiple tasks. But they are doing something very clever: They load a single model in memory and use different adapters to specialize the model on the fly. I recorded a video to show you how to write the code to do the same thing Apple is doing. I explain everything step by step. Here is what I'll show you in the video: 1. We'll load two datasets 2. Then load a large model 3. Then, we'll fine-tune the model on both datasets I'll use LoRA to fine-tune the model. This process creates two small adapters, each specializing in solving one of the datasets. The base model's original parameters will remain unchanged. From here: 4. We'll generate a list of tasks 5. We'll load the correct adapter to solve each task The large model I'm using needs 346 MB of memory, but I only need to load it once. Each adapter is only 2.7 MB. I only need to load the base model once and pair it with any of the fine-tuned adapters. Minimum memory footprint and I can solve multiple tasks. Hope this helps!

Apple built a large foundation model and fine-tuned it on multiple tasks. But they are doing something very clever: They load a single model in memory and use different adapters to specialize the model on the fly. I recorded a video to show you how to write the code to do the same thing Apple is doing. I explain everything step by step. Here is what I'll show you in the video: 1. We'll load two datasets 2. Then load a large model 3. Then, we'll fine-tune the model on both datasets I'll use LoRA to fine-tune the model. This process creates two small adapters, each specializing in solving one of the datasets. The base model's original parameters will remain unchanged. From here: 4. We'll generate a list of tasks 5. We'll load the correct adapter to solve each task The large model I'm using needs 346 MB of memory, but I only need to load it once. Each adapter is only 2.7 MB. I only need to load the base model once and pair it with any of the fine-tuned adapters. Minimum memory footprint and I can solve multiple tasks. Hope this helps!

Santiago

84,747 views • 1 year ago

it is always so fun working on high areas of the map and fine tuning the beautiful vistas you see from up top :) - work in progress! (game is ABYSS X ZERO for those who do not know! an upcoming low-poly 3D metroidvania, developed by me and IronFairy - Fernanda Dias) #gamedev #lowpoly

it is always so fun working on high areas of the map and fine tuning the beautiful vistas you see from up top :) - work in progress! (game is ABYSS X ZERO for those who do not know! an upcoming low-poly 3D metroidvania, developed by me and IronFairy - Fernanda Dias) #gamedev #lowpoly

Tiani Pixel | Follow me on BSky!

94,093 views • 9 months ago

Revolutionizing Move Programming with OpenLedger In this demo, we showcase how Move datasets contributed by data providers to OpenLedger’s datanets are used to fine-tune specialized models with LoRA fine-tuning. As seen in the video, we showcase an example on how builders can deploy a Move-specialized model that powers Co-pilot agents using our no-code model fine-tuning platform. This is the future of AI and Web3 innovation. Watch this space to see more specialised models and data feeds being built for next generation agents on top of OpenLedger #Move

Revolutionizing Move Programming with OpenLedger In this demo, we showcase how Move datasets contributed by data providers to OpenLedger’s datanets are used to fine-tune specialized models with LoRA fine-tuning. As seen in the video, we showcase an example on how builders can deploy a Move-specialized model that powers Co-pilot agents using our no-code model fine-tuning platform. This is the future of AI and Web3 innovation. Watch this space to see more specialised models and data feeds being built for next generation agents on top of OpenLedger #Move

OpenLedger

61,662 views • 1 year ago

This is a world model running locally on an RTX 5090. It was built from scratch by a team in India, lucidml. Like modern video games, you can choose between performance and graphics by choosing how many times the neural network is run to generate each frame. Absolutely wild.

This is a world model running locally on an RTX 5090. It was built from scratch by a team in India, lucidml. Like modern video games, you can choose between performance and graphics by choosing how many times the neural network is run to generate each frame. Absolutely wild.

Caleb

44,784 views • 5 months ago

It’s been a massive week for embodied AI foundation models: the pace of this field is truly staggering. Throwing it back to the SimToolReal work by Kushal and Tyler Lum (Cornell & Stanford labs). In February, they achieved zero-shot tool manipulation across 24 tasks using a single RL policy and a robotic arm fitted with the SharpaWave hand. Watching the robot nail these high-speed in-hand rotations is incredible. The precision is especially impressive when you consider the policy was never trained on these specific objects or tasks. This is what solving the manipulation bottleneck looks like. ⚡️

It’s been a massive week for embodied AI foundation models: the pace of this field is truly staggering. Throwing it back to the SimToolReal work by Kushal and Tyler Lum (Cornell & Stanford labs). In February, they achieved zero-shot tool manipulation across 24 tasks using a single RL policy and a robotic arm fitted with the SharpaWave hand. Watching the robot nail these high-speed in-hand rotations is incredible. The precision is especially impressive when you consider the policy was never trained on these specific objects or tasks. This is what solving the manipulation bottleneck looks like. ⚡️

Sharpa

868,354 views • 3 months ago

Hurricane Melissa by herself is not the problem. The problem is the fact that it has been raining here incessantly for weeks now and the entire island is saturated. So if this is how corporate Kingston looks on a regular morning, what will it look like when the actual storm hits? Jamaica needs your prayers 🇯🇲🙏🏼

Hurricane Melissa by herself is not the problem. The problem is the fact that it has been raining here incessantly for weeks now and the entire island is saturated. So if this is how corporate Kingston looks on a regular morning, what will it look like when the actual storm hits? Jamaica needs your prayers 🇯🇲🙏🏼

°♡✧*Ṡ𝙤ϻϻə𝖗 Ʈ𝗵уოе*✧♡°

417,472 views • 9 months ago

Unsloth AI and NVIDIA are Revolutionizing Local LLM Fine-Tuning: From RTX Desktops to DGX Spark Fine-tune popular AI models faster with Unsloth on NVIDIA RTX AI PCs such as GeForce RTX desktops and laptops to RTX PRO workstations and the new DGX Spark to build personalized assistants for coding, creative work, and complex agentic workflows. The landscape of modern AI is shifting. We are moving away from a total reliance on massive, generalized cloud models and entering the era of local, agentic AI. Whether it is tuning a chatbot to handle hyper-specific product support or building a personal assistant that manages intricate schedules, the potential for generative AI on local hardware is boundless. However, developers face a persistent bottleneck: How do you get a Small Language Model (SLM) to punch above its weight class and respond with high accuracy for specialized tasks? The answer is Fine-Tuning, and the tool of choice is Unsloth. Unsloth provides an easy and high-speed method to customize models. Optimized for efficient, low-memory training on NVIDIA GPUs, Unsloth scales effortlessly from GeForce RTX desktops and laptop all the way to the DGX Spark, the world’s smallest AI supercomputer...... Full analysis: NVIDIA NVIDIA AI NVIDIA AIDev NVIDIAnewsroom Unsloth AI Unsloth

Unsloth AI and NVIDIA are Revolutionizing Local LLM Fine-Tuning: From RTX Desktops to DGX Spark Fine-tune popular AI models faster with Unsloth on NVIDIA RTX AI PCs such as GeForce RTX desktops and laptops to RTX PRO workstations and the new DGX Spark to build personalized assistants for coding, creative work, and complex agentic workflows. The landscape of modern AI is shifting. We are moving away from a total reliance on massive, generalized cloud models and entering the era of local, agentic AI. Whether it is tuning a chatbot to handle hyper-specific product support or building a personal assistant that manages intricate schedules, the potential for generative AI on local hardware is boundless. However, developers face a persistent bottleneck: How do you get a Small Language Model (SLM) to punch above its weight class and respond with high accuracy for specialized tasks? The answer is Fine-Tuning, and the tool of choice is Unsloth. Unsloth provides an easy and high-speed method to customize models. Optimized for efficient, low-memory training on NVIDIA GPUs, Unsloth scales effortlessly from GeForce RTX desktops and laptop all the way to the DGX Spark, the world’s smallest AI supercomputer...... Full analysis: NVIDIA NVIDIA AI NVIDIA AIDev NVIDIAnewsroom Unsloth AI Unsloth

Marktechpost AI Dev News ⚡

31,551 views • 7 months ago

"Let's build it." Less than 24 hours later, the DeNet team had a working demo running. At the Google Gemma × Cerebras hackathon, we've built a new use case for the DeNet Storage Protocol - helping businesses adopt AI safely by storing agent sessions, fine-tuning data, and open code on DeNet, not on centralized servers prone to leaks. This is exactly why we build: to turn emerging market needs into real infrastructure. We're excited to share more soon. If you believe AI needs decentralized infrastructure, we'd love your likes, comments and reposts 🚀 Watch demo 👇

"Let's build it." Less than 24 hours later, the DeNet team had a working demo running. At the Google Gemma × Cerebras hackathon, we've built a new use case for the DeNet Storage Protocol - helping businesses adopt AI safely by storing agent sessions, fine-tuning data, and open code on DeNet, not on centralized servers prone to leaks. This is exactly why we build: to turn emerging market needs into real infrastructure. We're excited to share more soon. If you believe AI needs decentralized infrastructure, we'd love your likes, comments and reposts 🚀 Watch demo 👇

DeNet

73,344 views • 1 month ago

Here’s a demo of our Agentic Memory system, inspired by how our own brain holds information in a 3D spatial space. This feels, natural. Extending this further, we announced the Agentic Memory Protocol on July 15th in SF - which enables memory to be local, encrypted and available to other agents and apps based on your permission-only. We believe this is the future of memory - not owned by any one app, spatial, and always improving. Aaron Levie Andrej Karpathy

Here’s a demo of our Agentic Memory system, inspired by how our own brain holds information in a 3D spatial space. This feels, natural. Extending this further, we announced the Agentic Memory Protocol on July 15th in SF - which enables memory to be local, encrypted and available to other agents and apps based on your permission-only. We believe this is the future of memory - not owned by any one app, spatial, and always improving. Aaron Levie Andrej Karpathy

Varun

187,489 views • 1 year ago