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.

offers full-stack privacy across queries, data, payments and devices / hardware 1. The best open-source models (eg. Kimi K2.5) served in secure enclaves (TEEs) 2. The best closed-source models (eg. GPT-5.2 Pro) with queries pooled into proxy servers and PII anonymized with a specialized Silo model 3. The only... show more

Freysa

27,362 subscribers

16,647 views • 4 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

This robot assistant from the NVIDIA CES Keynote on Monday is going viral. Nader Khalil🍊 explains all the hottest emerging AI trends in one demo: AI applications in 2026 will be multi-model, multi-modal, hybrid cloud/local, use open source models as well as proprietary models, control robots and embedded devices in the physical world, and have voice interfaces. (And the demo had a cute robot *and* a cute dog. Gold.) The demo was built with Pipecat AI. NVIDIA posted a really nice technical walk-through and complete code. The Reachy Mini robot from Hugging Face is open source hardware. (You can order it now, I have one!). You can run the assistant locally on your own hardware, in the cloud, or both.

This robot assistant from the NVIDIA CES Keynote on Monday is going viral. Nader Khalil🍊 explains all the hottest emerging AI trends in one demo: AI applications in 2026 will be multi-model, multi-modal, hybrid cloud/local, use open source models as well as proprietary models, control robots and embedded devices in the physical world, and have voice interfaces. (And the demo had a cute robot and a cute dog. Gold.) The demo was built with Pipecat AI. NVIDIA posted a really nice technical walk-through and complete code. The Reachy Mini robot from Hugging Face is open source hardware. (You can order it now, I have one!). You can run the assistant locally on your own hardware, in the cloud, or both.

kwindla

49,010 views • 6 months ago

"Mac Minis for example are a very good fit" - Andrej Karpathy Andrej Karpathy shouted out my work on EXO Labs in his keynote at Y Combinator AI SUS! Here's the breakdown: Right now most AI workloads run in the cloud where requests from different users are continuously batched together. These workloads are FLOPS-bound and favors hardware with the best unit economics of $ per FLOP, i.e. enterprise GPUs. The personal computing revolution will shift these workloads to personal devices with lower batch sizes (mostly batch_size=1). batch_size=1 inference is memory-bound, because all of the model parameters need to be loaded into the GPU every time a token is generated. Apple Silicon with its Unified Memory architecture has a lot of memory and memory bandwidth per $ compared to other hardware: - M4 Pro Mac Mini, 24GB @ 273GB/s, $58.33/GB, $5.13/GB/s - H100, 80GB @ 3350GB/s, $625/GB, $14.93/GB/s The unit economics of Apple Silicon are becoming more compelling with every release of the Mac. The future of AI inference looks more like open weights models (OpenAI open weights model soonTM) run at low batch_size on personal devices.

"Mac Minis for example are a very good fit" - Andrej Karpathy Andrej Karpathy shouted out my work on EXO Labs in his keynote at Y Combinator AI SUS! Here's the breakdown: Right now most AI workloads run in the cloud where requests from different users are continuously batched together. These workloads are FLOPS-bound and favors hardware with the best unit economics of $ per FLOP, i.e. enterprise GPUs. The personal computing revolution will shift these workloads to personal devices with lower batch sizes (mostly batch_size=1). batch_size=1 inference is memory-bound, because all of the model parameters need to be loaded into the GPU every time a token is generated. Apple Silicon with its Unified Memory architecture has a lot of memory and memory bandwidth per $ compared to other hardware: - M4 Pro Mac Mini, 24GB @ 273GB/s, $58.33/GB, $5.13/GB/s - H100, 80GB @ 3350GB/s, $625/GB, $14.93/GB/s The unit economics of Apple Silicon are becoming more compelling with every release of the Mac. The future of AI inference looks more like open weights models (OpenAI open weights model soonTM) run at low batch_size on personal devices.

Alex Cheema

103,566 views • 1 year ago

Leo Nightly now runs GLM-5 inside NEAR AI's Trusted Execution Environments, upgrading from DeepSeek V3.1. GLM-5 is currently one of the best open weight models from that leads every other open model on reasoning, coding, and agentic benchmarks. It's running inside Nvidia-backed TEEs via NEAR AI, which means your conversations are processed in a hardware-secured enclave where no one, not Brave, not NEAR, not anyone, can see your prompts or responses. Every computation is cryptographically signed so you can verify the model running is actually the model you selected. This is what we mean by moving from "trust me bro" to "trust but verify." Most AI assistants ask you to take their privacy claims on faith. Leo with NEAR AI TEEs gives you cryptographic proof. Update to the latest Nightly build and select GLM-5 with the "Verifiably Private with NEAR AI TEE" label in Leo to try it.

Leo Nightly now runs GLM-5 inside NEAR AI's Trusted Execution Environments, upgrading from DeepSeek V3.1. GLM-5 is currently one of the best open weight models from that leads every other open model on reasoning, coding, and agentic benchmarks. It's running inside Nvidia-backed TEEs via NEAR AI, which means your conversations are processed in a hardware-secured enclave where no one, not Brave, not NEAR, not anyone, can see your prompts or responses. Every computation is cryptographically signed so you can verify the model running is actually the model you selected. This is what we mean by moving from "trust me bro" to "trust but verify." Most AI assistants ask you to take their privacy claims on faith. Leo with NEAR AI TEEs gives you cryptographic proof. Update to the latest Nightly build and select GLM-5 with the "Verifiably Private with NEAR AI TEE" label in Leo to try it.

Brave Nightly

52,374 views • 4 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

🚀 Introducing AgentCPM-Explore: The First Open-Source 4B-Agent Model to Conquer GAIA & Complex Real-World Tasks! 🤗 Hugging Face: 🔗 GitHub: ✨ Key Highlights: ✅ SOTA Agentic Performance: Sets a new benchmark for 4B-scale agent models—outperforming all peers, surpassing 8B models, and rivaling select 30B+ and closed-source LLMs. 🧠 Deep Research Capability: Excels at long-horizon reasoning, supports 100+ turns of autonomous interaction with multi-source cross-validation, human-like self-correction, and dynamic tool use + strategy adaptation—just like a real researcher! 🔓 Full-Stack Open Source: We’re open-sourcing the entire end-to-end agent stack—not just the model! Empower your own innovations with - AgentRL: Asynchronous reinforcement learning framework - AgentDock: Secure, extensible tool sandbox - AgentToLeaP: An one-click evaluation platform for agent tool-learning capabilitie - Full training data pipeline & reproducible workflows #AgentCPM #OpenSourceAI #AgenticAI #AI #GAIA #LLM #OpenBMB #AIAgents #HuggingFace

🚀 Introducing AgentCPM-Explore: The First Open-Source 4B-Agent Model to Conquer GAIA & Complex Real-World Tasks! 🤗 Hugging Face: 🔗 GitHub: ✨ Key Highlights: ✅ SOTA Agentic Performance: Sets a new benchmark for 4B-scale agent models—outperforming all peers, surpassing 8B models, and rivaling select 30B+ and closed-source LLMs. 🧠 Deep Research Capability: Excels at long-horizon reasoning, supports 100+ turns of autonomous interaction with multi-source cross-validation, human-like self-correction, and dynamic tool use + strategy adaptation—just like a real researcher! 🔓 Full-Stack Open Source: We’re open-sourcing the entire end-to-end agent stack—not just the model! Empower your own innovations with - AgentRL: Asynchronous reinforcement learning framework - AgentDock: Secure, extensible tool sandbox - AgentToLeaP: An one-click evaluation platform for agent tool-learning capabilitie - Full training data pipeline & reproducible workflows #AgentCPM #OpenSourceAI #AgenticAI #AI #GAIA #LLM #OpenBMB #AIAgents #HuggingFace

OpenBMB

13,996 views • 6 months ago

AMD's Anush Elangovan explains why he thinks his company's open source ethos combined with agentic AI superpowers their leverage as a company: Because AMD publishes a lot of technical details about its hardware, when engineers use AI tools, the models already “understand” AMD’s systems and can help write code for them, debug them, or even generate new tools. And that makes developers more productive on AMD hardware without AMD having to do all the work internally. "AMD has had this ethos of open source, which really plays to our advantage. Every frontier model that I use has already seen every bit of AMD source code." "It'll rewrite my spec for me because it's already in the training data. Which you can't get from closed ecosystems." "In fact I built a virtual GPU simulator just based off our public specs, and now I'm running it on the GPU. So now I can run cross-generational GPU simulations on existing hardware." "We have that advantage. And we've run a Dev Day contest where we generated more tokens on AMD — Triton kernels and HIP kernels — than existed on the internet at the time." "So now that's all part of the pre-training data. It's a superpower because now you're open source, and you're agentically accelerating this process."

AMD's Anush Elangovan explains why he thinks his company's open source ethos combined with agentic AI superpowers their leverage as a company: Because AMD publishes a lot of technical details about its hardware, when engineers use AI tools, the models already “understand” AMD’s systems and can help write code for them, debug them, or even generate new tools. And that makes developers more productive on AMD hardware without AMD having to do all the work internally. "AMD has had this ethos of open source, which really plays to our advantage. Every frontier model that I use has already seen every bit of AMD source code." "It'll rewrite my spec for me because it's already in the training data. Which you can't get from closed ecosystems." "In fact I built a virtual GPU simulator just based off our public specs, and now I'm running it on the GPU. So now I can run cross-generational GPU simulations on existing hardware." "We have that advantage. And we've run a Dev Day contest where we generated more tokens on AMD — Triton kernels and HIP kernels — than existed on the internet at the time." "So now that's all part of the pre-training data. It's a superpower because now you're open source, and you're agentically accelerating this process."

TBPN

34,469 views • 3 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

New short course: Prompt Engineering with Llama 2, built in collaboration with Meta AI at Meta, and taught by Amit Sangani! Meta's Llama 2 has been game-changing for AI. Building with open source lets you control your own data, scrutinize errors, update (or not) the models as you please, and work alongside the global community advancing open models. Llama isn't a single model, it's a collection of models. In this course, you'll: - Learn the differences between different Llama 2 flavors, and when to use each. - Prompt the Llama chat models -- you'll also see how Llama's instruction tags work -- so they can help you with day-to-day tasks, like writing or summarization. - Use advanced prompting, like few-shot prompting for classification, and chain-of-thought prompting for solving logic problems. - Use specialized models in the Llama collection for specific tasks, like Code Llama to help you write, analyze, and improve code, and Llama Guard, which checks prompts and model responses for harmful content. The course also touches on how to run Llama 2 locally on your own computer. I hope you’ll take this course and try out these powerful, open models!

New short course: Prompt Engineering with Llama 2, built in collaboration with Meta AI at Meta, and taught by Amit Sangani! Meta's Llama 2 has been game-changing for AI. Building with open source lets you control your own data, scrutinize errors, update (or not) the models as you please, and work alongside the global community advancing open models. Llama isn't a single model, it's a collection of models. In this course, you'll: - Learn the differences between different Llama 2 flavors, and when to use each. - Prompt the Llama chat models -- you'll also see how Llama's instruction tags work -- so they can help you with day-to-day tasks, like writing or summarization. - Use advanced prompting, like few-shot prompting for classification, and chain-of-thought prompting for solving logic problems. - Use specialized models in the Llama collection for specific tasks, like Code Llama to help you write, analyze, and improve code, and Llama Guard, which checks prompts and model responses for harmful content. The course also touches on how to run Llama 2 locally on your own computer. I hope you’ll take this course and try out these powerful, open models!

Andrew Ng

162,842 views • 2 years ago

Anthropic's in trouble, again. The entire Claude experience is now available at 1/6th the price. Kimi now does everything Claude does, powered by K2.6, a 1-trillion-parameter MoE model that activates only 32B parameters per token. It covers all three features Claude has (Chat, Code, and Cowork): 1) Kimi Chat runs in four modes - Instant for fast responses - Thinking for deep reasoning - Agent for multi-step execution - and Agent Swarm for parallel workloads. There's a 262K context window across all of them. 2) Kimi Code is the open-source CLI coding agent with K2.6 as the default backend. K2.6 ranked #1 on OpenRouter's programming leaderboard by weekly usage. 3) Kimi Agent is the Cowork equivalent. It generates: - full websites with database and auth - presentation decks (editable PPTX output) - spreadsheets with formulas and charts - word docs and structured research reports. On top of this, Kimi K2.6 is also trained to decompose tasks into up to 300 parallel sub-agents. This helps it retain coherence even across 4,000+ tool calls in a single run, with sessions sustaining up to 13 hours. On SWE-Bench Pro: - Kimi K2.6 → 58.6 - GPT-5.4 xhigh → 57.7 - Gemini 3.1 Pro → 54.2 - Claude Opus 4.6 → 53.4 Kimi K2.6 model is open weights and self-hostable on 4x H100s in INT4. Find the link to the HuggingFace model page in the replies!

Anthropic's in trouble, again. The entire Claude experience is now available at 1/6th the price. Kimi now does everything Claude does, powered by K2.6, a 1-trillion-parameter MoE model that activates only 32B parameters per token. It covers all three features Claude has (Chat, Code, and Cowork): 1) Kimi Chat runs in four modes - Instant for fast responses - Thinking for deep reasoning - Agent for multi-step execution - and Agent Swarm for parallel workloads. There's a 262K context window across all of them. 2) Kimi Code is the open-source CLI coding agent with K2.6 as the default backend. K2.6 ranked #1 on OpenRouter's programming leaderboard by weekly usage. 3) Kimi Agent is the Cowork equivalent. It generates: - full websites with database and auth - presentation decks (editable PPTX output) - spreadsheets with formulas and charts - word docs and structured research reports. On top of this, Kimi K2.6 is also trained to decompose tasks into up to 300 parallel sub-agents. This helps it retain coherence even across 4,000+ tool calls in a single run, with sessions sustaining up to 13 hours. On SWE-Bench Pro: - Kimi K2.6 → 58.6 - GPT-5.4 xhigh → 57.7 - Gemini 3.1 Pro → 54.2 - Claude Opus 4.6 → 53.4 Kimi K2.6 model is open weights and self-hostable on 4x H100s in INT4. Find the link to the HuggingFace model page in the replies!

Avi Chawla

109,921 views • 2 months ago

QVAC SDK 0.10.0 is now live, bringing advanced local compute capabilities and specialized hardware optimization directly to your device Key Features and Updates: - Image-to-Image Diffusion: Transform and edit images using simple prompts with 100% local compute—no cloud uploads or external servers required - Dynamic Tooling & KV Cache Management:Your local LLM now receives a tailored toolbox for every interaction, with automatic KV cache clearing to maintain high-speed inference - Doctor CLI: A new diagnostic tool that analyzes your hardware and memory, providing specific instructions on how to optimize your GPU for local AI - Suspend & Resume API: Specifically designed for mobile environments, this allows apps to pause P2P swarms and RAG workspaces to meet background rules without losing model state - GPT-OSS Compatibility: Added support for the latest GPT-OSS models loaded externally, expanding the range of open-source intelligence available on the platform Build the future of private, unstoppable AI:

QVAC SDK 0.10.0 is now live, bringing advanced local compute capabilities and specialized hardware optimization directly to your device Key Features and Updates: - Image-to-Image Diffusion: Transform and edit images using simple prompts with 100% local compute—no cloud uploads or external servers required - Dynamic Tooling & KV Cache Management:Your local LLM now receives a tailored toolbox for every interaction, with automatic KV cache clearing to maintain high-speed inference - Doctor CLI: A new diagnostic tool that analyzes your hardware and memory, providing specific instructions on how to optimize your GPU for local AI - Suspend & Resume API: Specifically designed for mobile environments, this allows apps to pause P2P swarms and RAG workspaces to meet background rules without losing model state - GPT-OSS Compatibility: Added support for the latest GPT-OSS models loaded externally, expanding the range of open-source intelligence available on the platform Build the future of private, unstoppable AI:

QVAC

34,508 views • 2 months ago

💡 What is a Gaia Domain?! Gaia Domains were created to make AI infrastructure truly sovereign. Each domain is a programmable environment you own and control on-chain, where your logic, models, and data stay in your hands at all times. With Gaia, you set the rules: choose which AI agents to deploy, configure your workflows, and decide how others can interact with your domain. Domains integrate seamlessly with smart contracts, other domains, and a wide range of decentralized tools is simple and secure. Every part of your domain operates on Gaia’s decentralized node network, protecting your work from centralized servers or closed AI systems. Thankfully, getting started is quick. Domains are ready out of the box with open-source language models and SDKs, so you can launch and iterate fast. Their modular design makes them easy to adapt, and EVM compatibility means they fit right into the broader DeAI ecosystem. Earning is built in at every step: you can run services, sell access, or enable delegated tasks with all transactions managed on-chain for total transparency. Gaia Domains open new ground for developers, DAOs, founders, researchers, and enterprises seeking to decentralize their AI stack. Questions? Reach out to our DevRels Tobiloba 🦀 Harish Kotra 🥑 meowy🦀! Get started here: In this video, Tobiloba 🦀 demonstrates how to integrate Gaia's public domains for AI agents, applications, chatbots, and frameworks, or even interact directly via the Gaia chat UI 🔽

💡 What is a Gaia Domain?! Gaia Domains were created to make AI infrastructure truly sovereign. Each domain is a programmable environment you own and control on-chain, where your logic, models, and data stay in your hands at all times. With Gaia, you set the rules: choose which AI agents to deploy, configure your workflows, and decide how others can interact with your domain. Domains integrate seamlessly with smart contracts, other domains, and a wide range of decentralized tools is simple and secure. Every part of your domain operates on Gaia’s decentralized node network, protecting your work from centralized servers or closed AI systems. Thankfully, getting started is quick. Domains are ready out of the box with open-source language models and SDKs, so you can launch and iterate fast. Their modular design makes them easy to adapt, and EVM compatibility means they fit right into the broader DeAI ecosystem. Earning is built in at every step: you can run services, sell access, or enable delegated tasks with all transactions managed on-chain for total transparency. Gaia Domains open new ground for developers, DAOs, founders, researchers, and enterprises seeking to decentralize their AI stack. Questions? Reach out to our DevRels Tobiloba 🦀 Harish Kotra 🥑 meowy🦀! Get started here: In this video, Tobiloba 🦀 demonstrates how to integrate Gaia's public domains for AI agents, applications, chatbots, and frameworks, or even interact directly via the Gaia chat UI 🔽

Gaia 🌱

15,821 views • 1 year ago

$ORCL founder Larry Ellison says next phase of AI will come from combining public models with proprietary enterprise data. These 5 names own some of the deepest proprietary data moats for that transition: 1. $PLTR sits inside some of most sensitive enterprise & government datasets in the world operationalizing AI across classified defense data, regulated healthcare data & Fortune 500 workflows that public models will never train on. 2. $META owns the world’s largest proprietary social graph with 3.5B+ daily active users generating text, image, video & voice data at a scale no competitor can replicate. 3. $GOOGL owns one of deepest consumer data stacks in world with 8.5B+ daily Search queries, 2.7B+ YouTube monthly users, 2B+ Maps users, 1.8B+ Gmail users & 3B+ Android devices feeding Gemini with proprietary data competitors cannot replicate. 4. $RDDT owns one of largest archives of human conversation, opinion & consumer behavior online with 20+ years of proprietary discussion data now being licensed to frontier labs like OpenAI with data licensing revenue could reach $400M+ annually by 2027. 5. $TEM owns one of largest clinical-grade oncology datasets in the world with 45M+ de-identified patient records across genomics, imaging & clinical data that healthcare AI structurally needs.

$ORCL founder Larry Ellison says next phase of AI will come from combining public models with proprietary enterprise data. These 5 names own some of the deepest proprietary data moats for that transition: 1. $PLTR sits inside some of most sensitive enterprise & government datasets in the world operationalizing AI across classified defense data, regulated healthcare data & Fortune 500 workflows that public models will never train on. 2. $META owns the world’s largest proprietary social graph with 3.5B+ daily active users generating text, image, video & voice data at a scale no competitor can replicate. 3. $GOOGL owns one of deepest consumer data stacks in world with 8.5B+ daily Search queries, 2.7B+ YouTube monthly users, 2B+ Maps users, 1.8B+ Gmail users & 3B+ Android devices feeding Gemini with proprietary data competitors cannot replicate. 4. $RDDT owns one of largest archives of human conversation, opinion & consumer behavior online with 20+ years of proprietary discussion data now being licensed to frontier labs like OpenAI with data licensing revenue could reach $400M+ annually by 2027. 5. $TEM owns one of largest clinical-grade oncology datasets in the world with 45M+ de-identified patient records across genomics, imaging & clinical data that healthcare AI structurally needs.

Shay Boloor

263,637 views • 1 month ago

💥 A 450M model just beat bigger VLAs on real robot tasks, and it’s 100% open source [📍 bookmark for later] Came across SmolVLA, a new vision-language-action model for robotics that’s compact, fast, and trained entirely on open community datasets from LeRobot via Hugging Face. What stood out to me is how it matches or outperforms much larger models like ACT using noisy, real-world community data instead of giant private datasets. Why it’s worth a look ✅ 26% performance boost from pretraining on open-source data ✅ Runs on consumer hardware, even a MacBook ✅ 30% faster responses with async inference and smart architecture tweaks ✅ Strong results across Meta-World, LIBERO, SO100, and SO101 ✅ Fully open source: weights, code, training pipeline, eval stack They also introduced smart efficiency tricks like using fewer visual tokens, pulling outputs from mid-layer, and separating perception from action to make it all run fast. SmolVLA is a strong case for what can happen when the robotics community shares data and builds in the open. Definitely worth keeping an eye on.

💥 A 450M model just beat bigger VLAs on real robot tasks, and it’s 100% open source [📍 bookmark for later] Came across SmolVLA, a new vision-language-action model for robotics that’s compact, fast, and trained entirely on open community datasets from LeRobot via Hugging Face. What stood out to me is how it matches or outperforms much larger models like ACT using noisy, real-world community data instead of giant private datasets. Why it’s worth a look ✅ 26% performance boost from pretraining on open-source data ✅ Runs on consumer hardware, even a MacBook ✅ 30% faster responses with async inference and smart architecture tweaks ✅ Strong results across Meta-World, LIBERO, SO100, and SO101 ✅ Fully open source: weights, code, training pipeline, eval stack They also introduced smart efficiency tricks like using fewer visual tokens, pulling outputs from mid-layer, and separating perception from action to make it all run fast. SmolVLA is a strong case for what can happen when the robotics community shares data and builds in the open. Definitely worth keeping an eye on.

Ilir Aliu - eu/acc

17,353 views • 11 months ago

#ad: Tired of Big Tech watching your every move? Break free with privacy-first smartphone that puts you in control. No trackers. No spyware. Total freedom. And we’ve unlocked early access to their Independence Day sale! Choose from entry-level or premium de-Googled phones to access encrypted calls, secure messaging, a private app store, and so much more. Or take your privacy to the next level with an Above Book. Protect your data, get access to the largest library of open-source software, and stay compatible with the software you love for work and play. With Above’s 30-day money-back guarantee, free 45-minute support call to get you start, and flexible financing or crypto payments, there’s nothing to lose. Declare your independence from Big Tech this 4th of July and save big at Your digital freedom starts today! Questions? Call 1-888-36-ABOVE Monday through Friday from 10 am to 6 pm Central. Or chat with the team at by clicking on the “chat with us” button. DISCLOSURE: This post contains affiliate links. If you make a purchase through them, we may earn a small commission at no extra cost to you. This helps keep our work independent. Thank you for your support.

#ad: Tired of Big Tech watching your every move? Break free with privacy-first smartphone that puts you in control. No trackers. No spyware. Total freedom. And we’ve unlocked early access to their Independence Day sale! Choose from entry-level or premium de-Googled phones to access encrypted calls, secure messaging, a private app store, and so much more. Or take your privacy to the next level with an Above Book. Protect your data, get access to the largest library of open-source software, and stay compatible with the software you love for work and play. With Above’s 30-day money-back guarantee, free 45-minute support call to get you start, and flexible financing or crypto payments, there’s nothing to lose. Declare your independence from Big Tech this 4th of July and save big at Your digital freedom starts today! Questions? Call 1-888-36-ABOVE Monday through Friday from 10 am to 6 pm Central. Or chat with the team at by clicking on the “chat with us” button. DISCLOSURE: This post contains affiliate links. If you make a purchase through them, we may earn a small commission at no extra cost to you. This helps keep our work independent. Thank you for your support.

The Vigilant Fox 🦊

50,766 views • 1 year ago

Sam Altman recently said: “GPT-OSS has strong real-world performance comparable to o4-mini—and you can run it locally on your phone.” Many believed running a 20B-parameter model on mobile devices was still years away. At Nexa AI, we’ve built our foundation on deep on-device AI technology—turning that vision into reality. Today, GPT-OSS is running fully local on mobile devices through our app, Nexa Studio. Real performance on Snapdragon Gen 5: - 17 tokens/sec decoding speed - < 3 seconds Time-to-First-Token Developers can now use NexaSDK to build their own local AI apps powered by GPT-OSS. What this unlocks: - Real reasoning models running locally - The next wave of AI Agent use cases—without cloud limits - True data privacy: your data never leaves your device Appreciation to OpenAI Sam Altman Greg Brockman and the entire leadership team for pushing the boundaries of the open-source AI community. Thanks to Qualcomm for the partnership, and to Manoj Khilnani and Chun-Po (Jerry) Chang for the incredible collaboration.

Sam Altman recently said: “GPT-OSS has strong real-world performance comparable to o4-mini—and you can run it locally on your phone.” Many believed running a 20B-parameter model on mobile devices was still years away. At Nexa AI, we’ve built our foundation on deep on-device AI technology—turning that vision into reality. Today, GPT-OSS is running fully local on mobile devices through our app, Nexa Studio. Real performance on Snapdragon Gen 5: - 17 tokens/sec decoding speed - < 3 seconds Time-to-First-Token Developers can now use NexaSDK to build their own local AI apps powered by GPT-OSS. What this unlocks: - Real reasoning models running locally - The next wave of AI Agent use cases—without cloud limits - True data privacy: your data never leaves your device Appreciation to OpenAI Sam Altman Greg Brockman and the entire leadership team for pushing the boundaries of the open-source AI community. Thanks to Qualcomm for the partnership, and to Manoj Khilnani and Chun-Po (Jerry) Chang for the incredible collaboration.

NEXA AI

197,453 views • 9 months ago

wanted to share our first public demo of Aligned wallet as a service. our engineering team has been doing an incredible job. really proud of how fast we’re building this. this is a key product for us. it’s how we help partners like Sovra – The Identity Stack onboard millions of users in a seamless and secure way. still work to do, but we’re on the right path. here’s the demo: 1. sign in with google 2. create a wallet with touch id passkey saved to icloud 3. send usdt on chain signed with your fingerprint 4. open on a new device 5. send another tx immediately how we’re building it: - 2 of 2 multisig where user passkey and server co sign every transaction - erc 4337 account abstraction - auth via google + webauthn passkeys. - passkeys sync across devices via icloud keychain or google password manager - server guardian recovery with timelock + mfa still under development: censorship resistance allowing users to retrieve their encrypted server key independently using their device key + mfa so no one can block access to their wallet we will be sharing more demos in the future and a full blog post explaining the architecture and design decisions.

wanted to share our first public demo of Aligned wallet as a service. our engineering team has been doing an incredible job. really proud of how fast we’re building this. this is a key product for us. it’s how we help partners like Sovra – The Identity Stack onboard millions of users in a seamless and secure way. still work to do, but we’re on the right path. here’s the demo: 1. sign in with google 2. create a wallet with touch id passkey saved to icloud 3. send usdt on chain signed with your fingerprint 4. open on a new device 5. send another tx immediately how we’re building it: - 2 of 2 multisig where user passkey and server co sign every transaction - erc 4337 account abstraction - auth via google + webauthn passkeys. - passkeys sync across devices via icloud keychain or google password manager - server guardian recovery with timelock + mfa still under development: censorship resistance allowing users to retrieve their encrypted server key independently using their device key + mfa so no one can block access to their wallet we will be sharing more demos in the future and a full blog post explaining the architecture and design decisions.

RJ 🟩

54,716 views • 5 months ago

We're releasing ACE-Step-v1.5(2B), a fast, high-quality open-source music model. It runs locally on a consumer-grade GPU, generates a full song in under 2 seconds(on an A100), supports LoRA fine-tuning, and beats SUNO on common eval metrics. GitHub: Key traits: Quality: beats Suno on common eval scores Speed: full song under 2s on A100 Local: ~4GB VRAM, under 10s on RTX 3090 LoRA: train your own style with a few songs License: MIT, free for commercial use Data: fully authorized plus synthetic The music AI space lacks commercial-grade open models. Many creators are forced to rely on closed-source services, and can’t fully own, run locally, or fine-tune their own models. We want to help change that.

We're releasing ACE-Step-v1.5(2B), a fast, high-quality open-source music model. It runs locally on a consumer-grade GPU, generates a full song in under 2 seconds(on an A100), supports LoRA fine-tuning, and beats SUNO on common eval metrics. GitHub: Key traits: Quality: beats Suno on common eval scores Speed: full song under 2s on A100 Local: ~4GB VRAM, under 10s on RTX 3090 LoRA: train your own style with a few songs License: MIT, free for commercial use Data: fully authorized plus synthetic The music AI space lacks commercial-grade open models. Many creators are forced to rely on closed-source services, and can’t fully own, run locally, or fine-tune their own models. We want to help change that.

ACE Music

1,054,942 views • 5 months ago

Introducing the SKALE Agent for Pinata! A powerful AI agent that unlocks SKALE on Base chains with 6 integrated skills designed for AI agents & x402 payments: SKALE-Bridge Bridge USDC from dozens of chains (Polygon, Base, Optimism, Monad, Arbitrum, Avalanche, and more) directly to SKALE Base in seconds via Trails and SKALE Native Bridge. SKALE-Deploy Automated contract deployment with native RNG integration, MTM (Multi-Transaction Mode) for batching transactions in seconds, and instant connection to canonical ERC-8004 contracts. Launch AI agents fast. SKALE-Bite BITE v1: Encrypted mempool transactions—no front-running, no MEV. BITE v2: Conditional encrypted txs that decrypt ONLY when specific on-chain conditions are met. Privacy by default. SKALE-Partners Direct access to ecosystem tools like Xona Agent for AI-generated images, videos, and creative content—all payable through x402. SKALE-x402 Create x402 resources and enable HTTP 402 payments through multiple facilitators. Monetize AI services with gasless pay-per-use models. OWS Wallets Open Wallet Standard integration—create unlimited EVM-compatible wallets for your agent with ZERO private key management. Secure, local-first, autonomous. Your AI agent. Fully equipped. Ready to execute on-SKALE = on-chain. Deploy your agent ▶️

Introducing the SKALE Agent for Pinata! A powerful AI agent that unlocks SKALE on Base chains with 6 integrated skills designed for AI agents & x402 payments: SKALE-Bridge Bridge USDC from dozens of chains (Polygon, Base, Optimism, Monad, Arbitrum, Avalanche, and more) directly to SKALE Base in seconds via Trails and SKALE Native Bridge. SKALE-Deploy Automated contract deployment with native RNG integration, MTM (Multi-Transaction Mode) for batching transactions in seconds, and instant connection to canonical ERC-8004 contracts. Launch AI agents fast. SKALE-Bite BITE v1: Encrypted mempool transactions—no front-running, no MEV. BITE v2: Conditional encrypted txs that decrypt ONLY when specific on-chain conditions are met. Privacy by default. SKALE-Partners Direct access to ecosystem tools like Xona Agent for AI-generated images, videos, and creative content—all payable through x402. SKALE-x402 Create x402 resources and enable HTTP 402 payments through multiple facilitators. Monetize AI services with gasless pay-per-use models. OWS Wallets Open Wallet Standard integration—create unlimited EVM-compatible wallets for your agent with ZERO private key management. Secure, local-first, autonomous. Your AI agent. Fully equipped. Ready to execute on-SKALE = on-chain. Deploy your agent ▶️

SKALE

466,476 views • 3 months ago