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.

Our universe is a model with twenty or so carefully fine-tuned parameters that generate all the content inside. Using these parameters and a reduced-scale model you can simulate the history of the cosmos. With the full-scale model, you get to be part of the simulation.

Andrew Côté

111,196 subscribers

90,707 views • 2 years ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

11 Comments

Andrew Côté2 years ago

Heres the leaked parameters.

Rainmaker2 years ago

In this free Substack post I share code for several machine learning models and engage in hyperparameter tuning that yields a model that delivers superior returns in the Gold market.

Brandon Goldman2 years ago

The ultimate procedural generation

YAD2 years ago

When people try to explain the world like this, it reveals more about the person and the context rather than the universe itself

Andrew Côté2 years ago

Go on, elaborate

Georges2 years ago

And can you twitch the parameters and rerun it ? And if not, does the full scale model fit with the recent observation of disk and spiral galaxies in the very early universe?

Litos2 years ago

You are speaking of consciousness The known universe according to our senses To be correct, refer as cosmos

Fartin’ Around2 years ago

Just need initial conditions

wayne hall2 years ago

Yet life isn't a calculation, it is beyond that.

f w2 years ago

beautiful

Jude Gomila2 years ago

@vincentweisser does it leverage holographic representations for cascading efficiency? i want to see the life emerging as well :)

Related Videos

SCIENTISTS SIMULATE UNIVERSE WITH 36,000 GRAPHICS CARDS They built the largest model ever to study dark matter and how stars evolve. Every dot in the simulation represents a galaxy—and this is only 0.001% of the entire thing. At this scale, Earth is so small it’s almost laughable. Source: Black Hole

SCIENTISTS SIMULATE UNIVERSE WITH 36,000 GRAPHICS CARDS They built the largest model ever to study dark matter and how stars evolve. Every dot in the simulation represents a galaxy—and this is only 0.001% of the entire thing. At this scale, Earth is so small it’s almost laughable. Source: Black Hole

Mario Nawfal

105,005 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

Scientists have created the largest simulation of the Universe using 36,000 AMD Instinct MI250X graphics cards. This project will allow us to better understand the nature of dark matter and the processes of stellar evolution. In the video, each dot represents a separate galaxy. However, all this is only 0.001% of the scale model that is planned to be completed. On such a scale, the Earth turns out to be much smaller than we are used to thinking.

Scientists have created the largest simulation of the Universe using 36,000 AMD Instinct MI250X graphics cards. This project will allow us to better understand the nature of dark matter and the processes of stellar evolution. In the video, each dot represents a separate galaxy. However, all this is only 0.001% of the scale model that is planned to be completed. On such a scale, the Earth turns out to be much smaller than we are used to thinking.

Black Hole

40,188 views • 1 year ago

🤯 Prof. David Kipping Says the James Webb Telescope Changes Our Understanding of the Universe “Something's wrong. Either our measurements of the local universe must be wrong in some way, or this model that we're using to calculate the whole history of the universe … is wrong.”

🤯 Prof. David Kipping Says the James Webb Telescope Changes Our Understanding of the Universe “Something's wrong. Either our measurements of the local universe must be wrong in some way, or this model that we're using to calculate the whole history of the universe … is wrong.”

Chief Nerd

261,183 views • 11 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

2/ And with our Rubber Duck agent you get a multi-model reflection loop as a reviewer. GPT-5.5 can review the output of another model or vice versa!

2/ And with our Rubber Duck agent you get a multi-model reflection loop as a reviewer. GPT-5.5 can review the output of another model or vice versa!

Satya Nadella

41,239 views • 3 months ago

I've seen so many people criticize the stock sonic model and say the model needs changing. But no, the model is fine. the problem is with how it's always posed. here for example with the unleashed model you can simply deform the brows and the muzzle to curve. This is pretty much the sonic unleashed game model but with a good rig that makes anything possible with the face. (Rig by DANCADA³ᴰ)

I've seen so many people criticize the stock sonic model and say the model needs changing. But no, the model is fine. the problem is with how it's always posed. here for example with the unleashed model you can simply deform the brows and the muzzle to curve. This is pretty much the sonic unleashed game model but with a good rig that makes anything possible with the face. (Rig by DANCADA³ᴰ)

TBSF

192,128 views • 1 year ago

We're thrilled to have worked with Holly Herndon to train a model finetuned on her vocal style to share with all of you. Playing with Holly’s model, you can use additional controls to get vocalizations that contour the music or "color" the instruments with a timbre that resembles Holly's voice

We're thrilled to have worked with Holly Herndon to train a model finetuned on her vocal style to share with all of you. Playing with Holly’s model, you can use additional controls to get vocalizations that contour the music or "color" the instruments with a timbre that resembles Holly's voice

Jesse Engel

11,373 views • 1 year ago

New open-source 3D world-generation model. I'm rendering a couple of worlds in the video, so check it out. You'll find the GitHub and the Hugging Face links to the model below. This is a multi-modal world model that you can use for a bunch of things: • To generate new worlds • To reconstruct worlds • To simulate 3D interactive worlds from a prompt, images, or a video You can edit the 3D outputs in Unity and Unreal Engine (they export as meshes, 3DGS files, and point clouds). You can also generate 3D characters in the world and walk around. Pretty fun stuff!

New open-source 3D world-generation model. I'm rendering a couple of worlds in the video, so check it out. You'll find the GitHub and the Hugging Face links to the model below. This is a multi-modal world model that you can use for a bunch of things: • To generate new worlds • To reconstruct worlds • To simulate 3D interactive worlds from a prompt, images, or a video You can edit the 3D outputs in Unity and Unreal Engine (they export as meshes, 3DGS files, and point clouds). You can also generate 3D characters in the world and walk around. Pretty fun stuff!

Santiago

65,446 views • 3 months ago

Introducing Music Finetunes in ElevenCreative. Generate individual vocals, instruments, or full tracks with stylistic consistency using a fine-tuned version of our Music model. Create your own Finetune or get started instantly with 11 Finetunes curated by ElevenLabs.

Introducing Music Finetunes in ElevenCreative. Generate individual vocals, instruments, or full tracks with stylistic consistency using a fine-tuned version of our Music model. Create your own Finetune or get started instantly with 11 Finetunes curated by ElevenLabs.

ElevenCreative

20,272 views • 4 months ago

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.

Santiago

164,162 views • 2 years 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

i built a full game on a single GPU with a 3B model and this is the worst local AI will ever be. this was supposed to be a benchmark test. load the model, measure tokens per second, write it up, move on. instead i spent 20 minutes playing Octopus Invaders because the game is genuinely fun and i couldn't stop. a model with 3B active parameters built this from a single prompt. it debugged its own collision system when bullets were phasing through enemies. read the error, found the fix, kept building. this is not a frontier API. this is a quantized open source model running on hardware you can buy used for $800-$1200. no cloud. no subscription. no API costs. just a mass produced consumer GPU doing things that would have been absurd 12 months ago. and here's the part that should keep you up at night: every month the models get smaller and smarter. the quants get tighter. the context windows get longer. the tooling gets cleaner. what 3B active parameters does today on 24gb, a 1B model will do on 8gb within a year. you are looking at the floor. not the ceiling.

i built a full game on a single GPU with a 3B model and this is the worst local AI will ever be. this was supposed to be a benchmark test. load the model, measure tokens per second, write it up, move on. instead i spent 20 minutes playing Octopus Invaders because the game is genuinely fun and i couldn't stop. a model with 3B active parameters built this from a single prompt. it debugged its own collision system when bullets were phasing through enemies. read the error, found the fix, kept building. this is not a frontier API. this is a quantized open source model running on hardware you can buy used for $800-$1200. no cloud. no subscription. no API costs. just a mass produced consumer GPU doing things that would have been absurd 12 months ago. and here's the part that should keep you up at night: every month the models get smaller and smarter. the quants get tighter. the context windows get longer. the tooling gets cleaner. what 3B active parameters does today on 24gb, a 1B model will do on 8gb within a year. you are looking at the floor. not the ceiling.

Sudo su

36,251 views • 5 months ago

Mirage is LIVE Generate energetic, high-converting ads with people that don’t exist — complete with animated body language and micro-expressions — using Mirage, the first foundation model built to generate UGC-style content. Get started with a script or an audio file, then specify the look of your spokesperson, their background, outfit, objects, and even emotion. It’s never been easier to iterate and scale ad production with Mirage, now available in Captions Ad Studio.

Mirage is LIVE Generate energetic, high-converting ads with people that don’t exist — complete with animated body language and micro-expressions — using Mirage, the first foundation model built to generate UGC-style content. Get started with a script or an audio file, then specify the look of your spokesperson, their background, outfit, objects, and even emotion. It’s never been easier to iterate and scale ad production with Mirage, now available in Captions Ad Studio.

Mirage

144,775 views • 1 year ago

One of our engineers built an interactive math art generator using the new 3.6 Flash model. You can customize speed, colors, and geometry parameters on the fly, then export the design directly to a 3D-printable STL file. Watch the video to see how the physical print turned out!

One of our engineers built an interactive math art generator using the new 3.6 Flash model. You can customize speed, colors, and geometry parameters on the fly, then export the design directly to a 3D-printable STL file. Watch the video to see how the physical print turned out!

Josh Woodward

36,954 views • 12 days ago

Bentov said the universe was not “out there” It was *inside you* He called it the “holographic model of consciousness” You are not a *body* living in the universe You are the *universe* living through a body Watch this carefully to understand it:👇

Bentov said the universe was not “out there” It was inside you He called it the “holographic model of consciousness” You are not a body living in the universe You are the universe living through a body Watch this carefully to understand it:👇

Darshak Rana ⚡️

52,670 views • 1 year ago

Bentov said the universe was not “out there” It was *inside you* He called it the “holographic model of consciousness” You are not a *body* living in the universe You are the *universe* living through a body Watch this carefully to understand it:👇

Bentov said the universe was not “out there” It was inside you He called it the “holographic model of consciousness” You are not a body living in the universe You are the universe living through a body Watch this carefully to understand it:👇

Darshak Rana ⚡️

42,780 views • 2 months ago

Bentov said the universe was not “out there” It was *inside you* He called it the “holographic model of consciousness” You are not a *body* living in the universe You are the *universe* living through a body Watch this carefully to understand it:👇

Bentov said the universe was not “out there” It was inside you He called it the “holographic model of consciousness” You are not a body living in the universe You are the universe living through a body Watch this carefully to understand it:👇

Darshak Rana ⚡️

49,904 views • 1 year ago