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.

FULL INTERVIEW: Engineers Edward Coristine (Edward Coristine) and Tai Groot (Tai Groot 🐧) just released an ML model called Rampart for the National Design Studio. It's a local-first, open-source AI privacy model that runs entirely in the browser. They joined TBPN to explain the model and why the National... show more

TBPN

1,033,831 subscribers

116,392 views • 21 days ago •via X (Twitter)

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

i tested a fully local ai coding setup: gemma4 from Google DeepMind running through LM Studio, paired with pi which is a minimal open source coding harness this is part 1 of a two part series. here we cover the why and the complete hands-on setup 0:00 - Running a coding agent fully local 0:47 - Why Pi as the coding agent harness 1:39 - Why Gemma 4 and which variant to pick 2:44 - Architecture: Pi, LM Studio and Gemma 4 3:45 - LM Studio setup and model download 5:01 - Starting the local server 5:19 - API sanity check with curl 6:08 - Installing the Pi coding agent 6:20 - Configuring models.json for local models 8:20 - First run: selecting the model in Pi 8:58 - Fixing the context length error 10:16 - Testing the working setup 10:50 - What is coming in Part 2

i tested a fully local ai coding setup: gemma4 from Google DeepMind running through LM Studio, paired with pi which is a minimal open source coding harness this is part 1 of a two part series. here we cover the why and the complete hands-on setup 0:00 - Running a coding agent fully local 0:47 - Why Pi as the coding agent harness 1:39 - Why Gemma 4 and which variant to pick 2:44 - Architecture: Pi, LM Studio and Gemma 4 3:45 - LM Studio setup and model download 5:01 - Starting the local server 5:19 - API sanity check with curl 6:08 - Installing the Pi coding agent 6:20 - Configuring models.json for local models 8:20 - First run: selecting the model in Pi 8:58 - Fixing the context length error 10:16 - Testing the working setup 10:50 - What is coming in Part 2

Nidhi Singh

16,289 views • 1 month ago

America’s first Chief Design Officer is redesigning how 300M people interact with their government. We sat down with Joe Gebbia — Airbnb cofounder, now leading National Design Studio from the White House — to talk about why the role was created and the team he’s assembling to pull it off. FIRST OF KIND, Season 2 premieres Wed 2/11 Follow: for updates

America’s first Chief Design Officer is redesigning how 300M people interact with their government. We sat down with Joe Gebbia — Airbnb cofounder, now leading National Design Studio from the White House — to talk about why the role was created and the team he’s assembling to pull it off. FIRST OF KIND, Season 2 premieres Wed 2/11 Follow: for updates

Soleio

123,603 views • 5 months ago

You can run a free and open-source alternative to Claude Code locally on your laptop! - Local AI model w/ Qwen3 Coder - Runs on your machine w/ LM Studio - Open-source VS Code extension w/ Cline Completely private (offline) and unlimited Setup and how it works: 00:00 Intro 01:11 LM Studio 02:10 Local AI model 03:38 Load the model 05:09 Start the server 05:33 Setup Cline 07:20 Prompt & example 09:02 Developer logs 10:12 Result reveal

You can run a free and open-source alternative to Claude Code locally on your laptop! - Local AI model w/ Qwen3 Coder - Runs on your machine w/ LM Studio - Open-source VS Code extension w/ Cline Completely private (offline) and unlimited Setup and how it works: 00:00 Intro 01:11 LM Studio 02:10 Local AI model 03:38 Load the model 05:09 Start the server 05:33 Setup Cline 07:20 Prompt & example 09:02 Developer logs 10:12 Result reveal

Paul Couvert

72,498 views • 9 months ago

First of Kind: The Joe Gebbia interview Why did Joe Gebbia go to Washington? I met with America’s first-ever Chief Design Officer last fall to find out. We met on the White House grounds to discuss his newly created role, the formation of National Design Studio, and how Joe plans to weave design into the fabric of U.S. federal government. 00:00 - Eisenhower Exec Office Bldg 01:34 - From Airbnb to Washington 04:39 - The Federal Retirement Problem 06:31 - The Mine in the Mountain 08:29 - Do Things That Don’t Scale 11:35 - The Julie Prototype 14:20 - Down to 60 Seconds 16:33 - Consumer-Grade Government 18:31 - Nixon’s Federal Beautification 20:22 - The National Design Studio 24:24 - Trust Through Design 27:43 - Building the Dream Team 31:22 - The Silicon Valley Coalition 35:33 - A Golden Age of Design Special thanks to Joe Gebbia and his team for making this conversation possible. S2:E1 Joe Gebbia, Designer-in-Chief Hosted by Soleio and produced by Room 3 is powered by our sponsors: Framer Cursor Vercel Profound

First of Kind: The Joe Gebbia interview Why did Joe Gebbia go to Washington? I met with America’s first-ever Chief Design Officer last fall to find out. We met on the White House grounds to discuss his newly created role, the formation of National Design Studio, and how Joe plans to weave design into the fabric of U.S. federal government. 00:00 - Eisenhower Exec Office Bldg 01:34 - From Airbnb to Washington 04:39 - The Federal Retirement Problem 06:31 - The Mine in the Mountain 08:29 - Do Things That Don’t Scale 11:35 - The Julie Prototype 14:20 - Down to 60 Seconds 16:33 - Consumer-Grade Government 18:31 - Nixon’s Federal Beautification 20:22 - The National Design Studio 24:24 - Trust Through Design 27:43 - Building the Dream Team 31:22 - The Silicon Valley Coalition 35:33 - A Golden Age of Design Special thanks to Joe Gebbia and his team for making this conversation possible. S2:E1 Joe Gebbia, Designer-in-Chief Hosted by Soleio and produced by Room 3 is powered by our sponsors: Framer Cursor Vercel Profound

Soleio

757,650 views • 5 months ago

Boltz-2 was released recently. It is an Open Source protein-ligand co-folding model, which means it can predict the structure of a protein along with the ligand. It has various applications from drug discovery to protein design. I thought why not make a OSS web app for it.

Boltz-2 was released recently. It is an Open Source protein-ligand co-folding model, which means it can predict the structure of a protein along with the ligand. It has various applications from drug discovery to protein design. I thought why not make a OSS web app for it.

Ravi Sharma

43,917 views • 1 year ago

In this episode of Design Review, Aaron Epstein sits down with Jorn van Dijk, the CEO and Co-founder of Framer. Together they unpack the brutal “gray zone” between early revenue and real product-market fit, the pivot that reignited their growth, and how to adapt as AI reshapes how we build and design software. 00:00 - Intro to Jorn van Dijk, the CEO and co-founder of Framer 00:34 - Framer’s Scale: $2B Valuation, 120 People around the globe 01:06 - Jorn’s Design Roots 01:49 - Why Dutch Design Culture Is So Strong 03:43 - Sofa: The Studio That Shaped Jorn (and His Co-Founder) 04:39 - Building Mac Products: Checkout, Versions, Kaleidoscope 06:13 - Apple Design Awards And A Game Changing Email 07:24 - Facebook Acquisition: Why They Wanted Designers 09:27 - Culture Shock: From 15-Person Studio to Facebook Scale 10:27 - Leaving Facebook: Intentionally Learning to Build a Big Company 13:12 - Early Experiments: Bitcoin App, Fashion App, Framer Prototype Tool 18:37 - The Plateau: Why Framer Studio Hit a Ceiling Around $4–5M ARR 23:52 - The Decision: Sell, Quit, or Pivot 25:30 - The Big Insight: People Hate Rebuilding 34:55 - AI + Design: What’s Changing & What Isn’t

In this episode of Design Review, Aaron Epstein sits down with Jorn van Dijk, the CEO and Co-founder of Framer. Together they unpack the brutal “gray zone” between early revenue and real product-market fit, the pivot that reignited their growth, and how to adapt as AI reshapes how we build and design software. 00:00 - Intro to Jorn van Dijk, the CEO and co-founder of Framer 00:34 - Framer’s Scale: $2B Valuation, 120 People around the globe 01:06 - Jorn’s Design Roots 01:49 - Why Dutch Design Culture Is So Strong 03:43 - Sofa: The Studio That Shaped Jorn (and His Co-Founder) 04:39 - Building Mac Products: Checkout, Versions, Kaleidoscope 06:13 - Apple Design Awards And A Game Changing Email 07:24 - Facebook Acquisition: Why They Wanted Designers 09:27 - Culture Shock: From 15-Person Studio to Facebook Scale 10:27 - Leaving Facebook: Intentionally Learning to Build a Big Company 13:12 - Early Experiments: Bitcoin App, Fashion App, Framer Prototype Tool 18:37 - The Plateau: Why Framer Studio Hit a Ceiling Around $4–5M ARR 23:52 - The Decision: Sell, Quit, or Pivot 25:30 - The Big Insight: People Hate Rebuilding 34:55 - AI + Design: What’s Changing & What Isn’t

Y Combinator

18,957 views • 5 months ago

Tune Studio is an end-to-end platform for developing applications using Large Language Models. So far, I haven't seen any other platform like this one. You can do everything here: 1. You can curate your data. 2. Use the playground to play with different models and try your ideas. 3. Fine-tune an open-source model on your data. 4. Deploy the model when you are done. This is awesome for anyone building generative AI applications. You can use Tune Studio to work with any of the open-source models out there. They were one of the few companies to host Llama 2 and Llama 3 before anyone else. Here is a link to check it out: One of their main selling points is that Tune Studio scales! You don't have to worry about serving your model to lots of users. They also have built-in user management, authentication, on-prem support, user context management, and pretty much everything you need to build generative AI applications. Thanks to the Tune team for collaborating with me on this post. We are living through the best years of development tools for AI developers. The field is unstoppable.

Tune Studio is an end-to-end platform for developing applications using Large Language Models. So far, I haven't seen any other platform like this one. You can do everything here: 1. You can curate your data. 2. Use the playground to play with different models and try your ideas. 3. Fine-tune an open-source model on your data. 4. Deploy the model when you are done. This is awesome for anyone building generative AI applications. You can use Tune Studio to work with any of the open-source models out there. They were one of the few companies to host Llama 2 and Llama 3 before anyone else. Here is a link to check it out: One of their main selling points is that Tune Studio scales! You don't have to worry about serving your model to lots of users. They also have built-in user management, authentication, on-prem support, user context management, and pretty much everything you need to build generative AI applications. Thanks to the Tune team for collaborating with me on this post. We are living through the best years of development tools for AI developers. The field is unstoppable.

Santiago

39,101 views • 2 years ago

Ideogram just released the #1 open weight image model in the world. It punches way above its weight - it's small enough to run on a consumer GPU, but goes head-to-head with Nano Banana and GPT Image for design. We went deep with Mohammad Norouzi on how they did it + hot takes 👇

Ideogram just released the #1 open weight image model in the world. It punches way above its weight - it's small enough to run on a consumer GPU, but goes head-to-head with Nano Banana and GPT Image for design. We went deep with Mohammad Norouzi on how they did it + hot takes 👇

Justine Moore

39,666 views • 1 month 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 • 1 year ago

Jason Calacanis: Anthropic, OpenAI and others are trying to kill OpenClaw Why? Because an open source agent platform is an existential threat to frontier model companies. @jason: “ People are going to say I'm a conspiracy theorist, but the number one goal, I believe, in the large language model, frontier model space, is to kill (OpenClaw). This is a giant movement to stop it, because this is the equivalent of having an open source Android-like player in the market, and that could be incredibly disruptive. Because, I believe, open source is going to win the day on the large language models and take 90% of the token usage, and I think the entire frontier model space could be undercut by open source. And I think they realize that SLMs, the smaller language models that are verticalized now, that will run on desktops and laptops and are even starting to run on the top ones, that is their biggest competitive threat, and I hope it happens.”

Jason Calacanis: Anthropic, OpenAI and others are trying to kill OpenClaw Why? Because an open source agent platform is an existential threat to frontier model companies. @jason: “ People are going to say I'm a conspiracy theorist, but the number one goal, I believe, in the large language model, frontier model space, is to kill (OpenClaw). This is a giant movement to stop it, because this is the equivalent of having an open source Android-like player in the market, and that could be incredibly disruptive. Because, I believe, open source is going to win the day on the large language models and take 90% of the token usage, and I think the entire frontier model space could be undercut by open source. And I think they realize that SLMs, the smaller language models that are verticalized now, that will run on desktops and laptops and are even starting to run on the top ones, that is their biggest competitive threat, and I hope it happens.”

The All-In Podcast

64,605 views • 3 months ago

$FIG just launched the Figma Design Agent, a dedicated agent that works alongside users in Figma. The agent lives directly on the canvas, so you can prompt from any design layer, iterate and edit alongside the agent, and hand it boring tasks that would have otherwise taken up a lot of your time. $FIG CEO Dylan Field came on the show today to discuss the launch. Here's our full conversation. 01:18 – Clocking AI-generated designs 03:31 – Figma’s new Design Agent 05:40 – AI code bloat and slop 09:09 – Using AI to augment creativity and branding 15:08 – Why Figma should be the front door to building apps in the AI era 18:53 – How design becomes more important as code commoditizes

$FIG just launched the Figma Design Agent, a dedicated agent that works alongside users in Figma. The agent lives directly on the canvas, so you can prompt from any design layer, iterate and edit alongside the agent, and hand it boring tasks that would have otherwise taken up a lot of your time. $FIG CEO Dylan Field came on the show today to discuss the launch. Here's our full conversation. 01:18 – Clocking AI-generated designs 03:31 – Figma’s new Design Agent 05:40 – AI code bloat and slop 09:09 – Using AI to augment creativity and branding 15:08 – Why Figma should be the front door to building apps in the AI era 18:53 – How design becomes more important as code commoditizes

TBPN

46,212 views • 2 months ago

“Enterprises should probably never train an AI model.” In this episode of our AI Explainer Series, Sr. Product Marketing Manager for AI, Meena Ganesh, and Box CTO, Ben Kus explain the challenges enterprises will face with training a model, and then explore why the smarter path is a combination of AI agents + RAG. Timestamps: 1:07 Reasons why enterprises shouldn't train a model 1:24 What it means to train a model 2:36 Explaining the concept of fine-tuning 4:50 Privacy challenges: AI doesn't keep secrets 6:40 What can enterprises do? 9:48 How enterprises can choose the right path

“Enterprises should probably never train an AI model.” In this episode of our AI Explainer Series, Sr. Product Marketing Manager for AI, Meena Ganesh, and Box CTO, Ben Kus explain the challenges enterprises will face with training a model, and then explore why the smarter path is a combination of AI agents + RAG. Timestamps: 1:07 Reasons why enterprises shouldn't train a model 1:24 What it means to train a model 2:36 Explaining the concept of fine-tuning 4:50 Privacy challenges: AI doesn't keep secrets 6:40 What can enterprises do? 9:48 How enterprises can choose the right path

Box

354,042 views • 7 months ago

AI isn't just changing the tools designers use. It's changing the way they think, prototype, and build. In this episode of Design Review, YC Head of Design eve joins Aaron Epstein to share the AI-first workflow she uses to design products, websites, and events. Using projects like Paxel, STATE OF THE ART, and YC Startup School as examples, she explains how coding agents are transforming everything from rapid prototyping and branding to design systems, and why the biggest bottleneck is no longer software. It's imagination. 00:00 - Eve's AI-First Design Workflow 01:27 - Why She Designs With Her Voice 03:44 - Paxel: Spotify Wrapped for Coding Sessions 07:13 - Building Tools for Yourself 11:01 - Turning Coding Transcripts Into Feedback 12:53 - The Story Behind SOTA Zine 16:57 - Designing With Context, Not Prompts 21:07 - How to Get Better AI Design Outputs 23:20 - Building an Interactive Map of San Francisco 25:17 - Behind Startup School's Visual Identity 29:59 - The Future of Design

AI isn't just changing the tools designers use. It's changing the way they think, prototype, and build. In this episode of Design Review, YC Head of Design eve joins Aaron Epstein to share the AI-first workflow she uses to design products, websites, and events. Using projects like Paxel, STATE OF THE ART, and YC Startup School as examples, she explains how coding agents are transforming everything from rapid prototyping and branding to design systems, and why the biggest bottleneck is no longer software. It's imagination. 00:00 - Eve's AI-First Design Workflow 01:27 - Why She Designs With Her Voice 03:44 - Paxel: Spotify Wrapped for Coding Sessions 07:13 - Building Tools for Yourself 11:01 - Turning Coding Transcripts Into Feedback 12:53 - The Story Behind SOTA Zine 16:57 - Designing With Context, Not Prompts 21:07 - How to Get Better AI Design Outputs 23:20 - Building an Interactive Map of San Francisco 25:17 - Behind Startup School's Visual Identity 29:59 - The Future of Design

Y Combinator

100,671 views • 10 days ago

Wild. Kimi K2 Thinking just released and it's insane. It's an AI model that can run by itself for hours on end and make HUNDREDS of tool calls It's the 1st model I think that can replace humans In this video I show why it's so special and how to use it to build your first app

Wild. Kimi K2 Thinking just released and it's insane. It's an AI model that can run by itself for hours on end and make HUNDREDS of tool calls It's the 1st model I think that can replace humans In this video I show why it's so special and how to use it to build your first app

Alex Finn

70,013 views • 8 months ago

$We’re shipping two major updates to streamline your creative workflow, allowing you to generate high-speed images with one model and then instantly animate them with the other—all at a fraction of the cost 🍌⚡️ 1️⃣ Introducing Nano Banana 2 Lite: Our fastest and most cost-efficient Gemini Image model yet delivers text-to-image outputs in under 4 seconds. Now available via the Gemini API and Google AI Studio, and rolling out soon across @NotebookLM, Google Flow, Google Gemini, Stitch by Google, Google Search and Google Photos. 2️⃣ Gemini Omni Flash in Public Preview: Our natively multimodal model for cost-efficient video generation and conversational editing. Now available via the Gemini API, Google AI Studio, and Gemini Enterprise Agent Platform so you can integrate the model into your workflow. While exciting on their own, the real magic happens when you build using these models together. Watch how our interior design demo integrates Nano Banana 2 Lite and Omni to instantly reimagine any space. Upload a photo, swipe through tailored design concepts, and see Omni bring the details to life in cinematic motion. Try out the demo app in AI Studio:$

We’re shipping two major updates to streamline your creative workflow, allowing you to generate high-speed images with one model and then instantly animate them with the other—all at a fraction of the cost 🍌⚡️ 1️⃣ Introducing Nano Banana 2 Lite: Our fastest and most cost-efficient Gemini Image model yet delivers text-to-image outputs in under 4 seconds. Now available via the Gemini API and Google AI Studio, and rolling out soon across @NotebookLM, Google Flow, Google Gemini, Stitch by Google, Google Search and Google Photos. 2️⃣ Gemini Omni Flash in Public Preview: Our natively multimodal model for cost-efficient video generation and conversational editing. Now available via the Gemini API, Google AI Studio, and Gemini Enterprise Agent Platform so you can integrate the model into your workflow. While exciting on their own, the real magic happens when you build using these models together. Watch how our interior design demo integrates Nano Banana 2 Lite and Omni to instantly reimagine any space. Upload a photo, swipe through tailored design concepts, and see Omni bring the details to life in cinematic motion. Try out the demo app in AI Studio:

Google AI

119,113 views • 20 days ago

Introducing Docker 🐳 AI Models for local + private LLMs in VSCode 🤩 You can now use Docker as a local model provider in VSCode, JetBrains, Cursor, and soon Visual Studio Enterprise. With Docker Model Runner (v4.40+), run AI models locally on your machine... no data sharing, no cloud dependency 👏 Just update Docker, open CodeGPT, select the model, click "Download", and enjoy 👉 Here’s how to update Docker:

Introducing Docker 🐳 AI Models for local + private LLMs in VSCode 🤩 You can now use Docker as a local model provider in VSCode, JetBrains, Cursor, and soon Visual Studio Enterprise. With Docker Model Runner (v4.40+), run AI models locally on your machine... no data sharing, no cloud dependency 👏 Just update Docker, open CodeGPT, select the model, click "Download", and enjoy 👉 Here’s how to update Docker:

Daniel San

65,228 views • 1 year ago

“We have a crisis of open source models in the Western world. Outside of China, there are no good open source models. We don't even have any in the US now. The talent, the capital and the focus to be best-in-class at pre-training, mid-training, post-training is an extremely scarce skillset. The answer for a lot of countries may just be to take an open weights model from China, post-train or fine-tune their own version, and have that be what they start from." Everett Randle Why does the West have such poor open source models and is it a national security threat to rely on open-source Chinese models Demis Hassabis Yann LeCun Aidan Gomez Lilian Weng Jan Leike

“We have a crisis of open source models in the Western world. Outside of China, there are no good open source models. We don't even have any in the US now. The talent, the capital and the focus to be best-in-class at pre-training, mid-training, post-training is an extremely scarce skillset. The answer for a lot of countries may just be to take an open weights model from China, post-train or fine-tune their own version, and have that be what they start from." Everett Randle Why does the West have such poor open source models and is it a national security threat to rely on open-source Chinese models Demis Hassabis Yann LeCun Aidan Gomez Lilian Weng Jan Leike

Harry Stebbings

63,397 views • 1 month ago

1/ Tencent releases HY World 1.5 (WorldPlay), an open-source real-time world model with 24fps A streaming video diffusion model that enables real-time, interactive world modeling with long-term geometric consistency In direct comparison to Genie 3, it's technically inferior, and there's no information on how long the consistency will last. However, Tencent has released a significant world model as open source for the first time, making it available to everyone. A few more examples, a thread 🧵

1/ Tencent releases HY World 1.5 (WorldPlay), an open-source real-time world model with 24fps A streaming video diffusion model that enables real-time, interactive world modeling with long-term geometric consistency In direct comparison to Genie 3, it's technically inferior, and there's no information on how long the consistency will last. However, Tencent has released a significant world model as open source for the first time, making it available to everyone. A few more examples, a thread 🧵

Chubby♨️

37,776 views • 7 months ago

We asked Dylan Field about organizational design in the age of AI, the importance of design. "As the inputs to software change, as more people are creating software, design becomes the differentiator." "Two decades ago, design was lipstick on a pig." "Design now is how you win or lose. We're going to start seeing so many more designer CEOs and design-oriented folks who are leading and shaping the future of software and companies." "Incredible designers are more in demand than ever. Good luck recruiting them because they have 50 other offers and infinite optionality."

We asked Dylan Field about organizational design in the age of AI, the importance of design. "As the inputs to software change, as more people are creating software, design becomes the differentiator." "Two decades ago, design was lipstick on a pig." "Design now is how you win or lose. We're going to start seeing so many more designer CEOs and design-oriented folks who are leading and shaping the future of software and companies." "Incredible designers are more in demand than ever. Good luck recruiting them because they have 50 other offers and infinite optionality."

TBPN

27,749 views • 11 months ago

GLM-5.2 running on Mac Studio Clusters or RTX GPU rigs isn't how Local AI will get mass adopted. For mass adoption we need to focus on two axes: 1. Intelligence/Speed Frontier. This is being tracked on local dot ai. Aggressive co-design is needed across the entire stack to push up the frontier specifically for local hardware. Better kernels, inference tricks like spec decoding, quantizing models, model routing. 2. Usability / UX. To use Local AI today, you need to install CLIs, select a model, a quantization, a harness that works best with that model, and you need to configure your inference engine. It's not very accessible. More work needs to be done on making this seamless, so the user doesn't even know the AI is running locally.

GLM-5.2 running on Mac Studio Clusters or RTX GPU rigs isn't how Local AI will get mass adopted. For mass adoption we need to focus on two axes: 1. Intelligence/Speed Frontier. This is being tracked on local dot ai. Aggressive co-design is needed across the entire stack to push up the frontier specifically for local hardware. Better kernels, inference tricks like spec decoding, quantizing models, model routing. 2. Usability / UX. To use Local AI today, you need to install CLIs, select a model, a quantization, a harness that works best with that model, and you need to configure your inference engine. It's not very accessible. More work needs to be done on making this seamless, so the user doesn't even know the AI is running locally.

Alex Cheema

30,443 views • 11 days ago