正在加载视频...

视频加载失败

返回首页

INSID3 segments objects across domains using ONLY ONE annotated example it works entirely without a segmentation decoder, task-specific fine-tuning, or external mask generators like SAM CVPR 2026 paper with enormous practical potential

skalskip92's profile picture

SkalskiP

47,420 subscribers

54,552 次观看 • 1 个月前 •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Robotics keeps hitting the same wall. Single task RL works, but... it does not scale to hundreds of tasks or new embodiments. This new paper looks like a real step toward fixing that. The team introduces MMBench, a benchmark with 200 tasks across many domains and robots, and Newt, a language conditioned world model trained online across all 200 tasks at once. The simple idea behind Newt: The model learns from demos to get the right priors It trains across many tasks through online interaction It uses language to ground the goal It adapts fast when a new task shows up What stood out to me: ✅ One model trained on 200 tasks at the same time ✅ Language conditioned control for both states and RGB ✅ Better data efficiency than strong baselines ✅ Strong open loop control ✅ Fast adaptation to new tasks and embodiments ✅ Full release of 200 checkpoints, 4000 demos, code, and benchmark This is a good push toward general control instead of one model per task. If you want the full paper: Project page: —- Weekly robotics and AI insights. Subscribe free:
0:11

Robotics keeps hitting the same wall. Single task RL works, but... it does not scale to hundreds of tasks or new embodiments. This new paper looks like a real step toward fixing that. The team introduces MMBench, a benchmark with 200 tasks across many domains and robots, and Newt, a language conditioned world model trained online across all 200 tasks at once. The simple idea behind Newt: The model learns from demos to get the right priors It trains across many tasks through online interaction It uses language to ground the goal It adapts fast when a new task shows up What stood out to me: ✅ One model trained on 200 tasks at the same time ✅ Language conditioned control for both states and RGB ✅ Better data efficiency than strong baselines ✅ Strong open loop control ✅ Fast adaptation to new tasks and embodiments ✅ Full release of 200 checkpoints, 4000 demos, code, and benchmark This is a good push toward general control instead of one model per task. If you want the full paper: Project page: —- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

70,090 次观看 • 7 个月前

We’re excited to introduce Text-to-LoRA: a Hypernetwork that generates task-specific LLM adapters (LoRAs) based on a text description of the task. Catch our presentation at #ICML2025! Paper: Code: Biological systems are capable of rapid adaptation, given limited sensory cues. For example, our human visual system can quickly adapt and tune its light sensitivity to our surroundings. While modern LLMs exhibit a wide variety of capabilities and knowledge, they remain rigid when adding task-specific capabilities. Traditionally, customizing these models requires gathering large datasets and performing often expensive, time-consuming fine-tuning for specific applications. To bypass these limitations, Text-to-LoRA (T2L) meta-learns a “hypernetwork” that takes in a text description of a desired task, as a prompt, and generates a task-specific LoRA that performs well on the task. In our experiments, we show that T2L can encode hundreds of existing LoRA adapters. While the compression is lossy, T2L maintains the performance of task-specifically tuned LoRA adapters. We also show that T2L can even generalize to unseen tasks given a natural language description of the tasks. Importantly, Text-to-LoRA is parameter-efficient. It generates LoRAs in a single, inexpensive step, based solely on a simple text description of the task. This approach is a step towards dramatically lowering the technical and computational barriers, allowing non-technical users to specialize foundation models using plain language, rather than needing deep technical expertise or large compute resources.
0:18

We’re excited to introduce Text-to-LoRA: a Hypernetwork that generates task-specific LLM adapters (LoRAs) based on a text description of the task. Catch our presentation at #ICML2025! Paper: Code: Biological systems are capable of rapid adaptation, given limited sensory cues. For example, our human visual system can quickly adapt and tune its light sensitivity to our surroundings. While modern LLMs exhibit a wide variety of capabilities and knowledge, they remain rigid when adding task-specific capabilities. Traditionally, customizing these models requires gathering large datasets and performing often expensive, time-consuming fine-tuning for specific applications. To bypass these limitations, Text-to-LoRA (T2L) meta-learns a “hypernetwork” that takes in a text description of a desired task, as a prompt, and generates a task-specific LoRA that performs well on the task. In our experiments, we show that T2L can encode hundreds of existing LoRA adapters. While the compression is lossy, T2L maintains the performance of task-specifically tuned LoRA adapters. We also show that T2L can even generalize to unseen tasks given a natural language description of the tasks. Importantly, Text-to-LoRA is parameter-efficient. It generates LoRAs in a single, inexpensive step, based solely on a simple text description of the task. This approach is a step towards dramatically lowering the technical and computational barriers, allowing non-technical users to specialize foundation models using plain language, rather than needing deep technical expertise or large compute resources.

Sakana AI

403,159 次观看 • 1 年前

AI in robotics gets all the attention right now, but sometimes the most interesting work is very practical. Viet built a small vision system that counts potatoes on a conveyor belt. No giant dataset. No huge model. Just a clear problem and a smart setup. He used Ultralytics’ ObjectCounter, trained a tiny YOLO11 nano model, and because there was no potato dataset, he annotated a single frame with SAM 2 and trained from that. One frame. Still works across the whole video. It is a good reminder that useful AI in industry often looks like this. Focused. Lightweight. Solves a real task. If you work in manufacturing or robotics, these small systems are usually the fastest wins. They save time, reduce errors, and do not need massive infrastructure. Nice work, Viet. His projects: —- Weekly robotics and AI insights. Subscribe free:
0:13

AI in robotics gets all the attention right now, but sometimes the most interesting work is very practical. Viet built a small vision system that counts potatoes on a conveyor belt. No giant dataset. No huge model. Just a clear problem and a smart setup. He used Ultralytics’ ObjectCounter, trained a tiny YOLO11 nano model, and because there was no potato dataset, he annotated a single frame with SAM 2 and trained from that. One frame. Still works across the whole video. It is a good reminder that useful AI in industry often looks like this. Focused. Lightweight. Solves a real task. If you work in manufacturing or robotics, these small systems are usually the fastest wins. They save time, reduce errors, and do not need massive infrastructure. Nice work, Viet. His projects: —- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

1,674,988 次观看 • 8 个月前

🚀 The Segment Anything Model (SAM) has been upgraded to SAM2, featuring an efficient image encoder for segmenting images and videos. But does SAM2 outperform SAM1 in medical image and video segmentation? We're thrilled to present our paper "Segment Anything in Medical Images and Videos: Benchmark and Deployment"! We comprehensively benchmark SAM2 across 11 medical image modalities and videos. 📄 Paper: 💻 Code: **Highlights:** 1. SAM2 doesn’t always outperform SAM1 in 2D medical images, but excels in video segmentation, making it more accurate and efficient for 3D images, such as CT and MR scans. 2. MedSAM still outperforms SAM2 on most 2D modalities, but SAM2 surpasses MedSAM for 3D image segmentation in a slice-by-slice approach. 3. Segmentation performance varies with model size; sometimes the smallest model outperforms larger ones. 4. Fine-tuning SAM2 significantly boosts its performance for medical image segmentation. While SAM2 may struggle with challenging objects that have unclear boundaries or low contrast, it excels in generating good initial segmentation masks for common medical images and videos. However, the official interface doesn’t support medical data formats and has limitations on video length. To address this, we've developed a 3D Slicer Plugin and Gradio API for efficient 3D medical image and video segmentation. We invite you to try them out and provide feedback! 🔧 Deployment: - 3D Slicer Plugin: - Gradio API: (Note: Due to GPU limitations, the online API is available for only 12 hours and may be slow. We highly recommend deploying the Gradio API with your own computing resources: A big shoutout to Jun Ma (JunMa) who recently joined our UHN AI hub (UHN AI Hub) as Machine Learning Lead, and kudos to all co-authors: Sumin Kim, Feifei Li, Mohammed Baharoon (Mohammed Baharoon), Reza Asakereh, and Hongwei Lyu! This is true teamwork! Looking forward to collaborating with the community to advance 3D medical image and video segmentation foundation models! University Health Network U of T Department of Computer Science Department of Laboratory Medicine & Pathobiology Temerty Centre for AI in Medicine (T-CAIREM) Vector Institute #MedTech #AIinHealthcare #DeepLearning #MedicalImaging #SAM2 #MedSAM #AIResearch
0:22

🚀 The Segment Anything Model (SAM) has been upgraded to SAM2, featuring an efficient image encoder for segmenting images and videos. But does SAM2 outperform SAM1 in medical image and video segmentation? We're thrilled to present our paper "Segment Anything in Medical Images and Videos: Benchmark and Deployment"! We comprehensively benchmark SAM2 across 11 medical image modalities and videos. 📄 Paper: 💻 Code: **Highlights:** 1. SAM2 doesn’t always outperform SAM1 in 2D medical images, but excels in video segmentation, making it more accurate and efficient for 3D images, such as CT and MR scans. 2. MedSAM still outperforms SAM2 on most 2D modalities, but SAM2 surpasses MedSAM for 3D image segmentation in a slice-by-slice approach. 3. Segmentation performance varies with model size; sometimes the smallest model outperforms larger ones. 4. Fine-tuning SAM2 significantly boosts its performance for medical image segmentation. While SAM2 may struggle with challenging objects that have unclear boundaries or low contrast, it excels in generating good initial segmentation masks for common medical images and videos. However, the official interface doesn’t support medical data formats and has limitations on video length. To address this, we've developed a 3D Slicer Plugin and Gradio API for efficient 3D medical image and video segmentation. We invite you to try them out and provide feedback! 🔧 Deployment: - 3D Slicer Plugin: - Gradio API: (Note: Due to GPU limitations, the online API is available for only 12 hours and may be slow. We highly recommend deploying the Gradio API with your own computing resources: A big shoutout to Jun Ma (JunMa) who recently joined our UHN AI hub (UHN AI Hub) as Machine Learning Lead, and kudos to all co-authors: Sumin Kim, Feifei Li, Mohammed Baharoon (Mohammed Baharoon), Reza Asakereh, and Hongwei Lyu! This is true teamwork! Looking forward to collaborating with the community to advance 3D medical image and video segmentation foundation models! University Health Network U of T Department of Computer Science Department of Laboratory Medicine & Pathobiology Temerty Centre for AI in Medicine (T-CAIREM) Vector Institute #MedTech #AIinHealthcare #DeepLearning #MedicalImaging #SAM2 #MedSAM #AIResearch

Bo Wang

178,481 次观看 • 1 年前

Full Fine-tuning vs. Freezing Layers. Interact 👉 and == Full Fine-tuning == A real network has many — three layers in this example, billions of parameters in a production model. What does fine-tuning look like when you update all of them? That’s full fine-tuning: continue training every weight in the pretrained network on your new task. Every layer’s W gets its own ΔW. Nothing is frozen — every parameter is in play. Think of an MLP as a chain of prerequisites leading to an advanced course. Layer 1 might be Linear Algebra, layer 2 Probability, layer 3 Advanced Machine Learning — each one building on what came before. Fine-tuning is what happens during graduate study: the foundations are already there from undergrad, so you’re not re-learning. Full fine-tuning is reviewing every prerequisite to see what new topics have appeared and what discoveries the field has made since the last time you sat through them. Effective — but exhausting. This diagram shows the same three-layer MLP twice, side by side. On the left, the pretrained network runs on input X: three weight matrices W₁, W₂, W₃, each followed by a ReLU activation. Full fine-tuning gives the model the most freedom to specialize. Every parameter can move — and every parameter that can move must be stored. But not every prerequisite needs revisiting. The further you go back in the chain, the less the material has changed since pretraining — the linear-algebra basics under your computer-vision course are largely the same as they ever were. The next page does exactly that: freeze the prerequisites that haven’t moved, and only refresh the advanced one closest to your specialization. == Freezing Layers == Full fine-tuning reviewed every prerequisite — Linear Algebra, Probability, Advanced ML — to refresh each subject with the latest topics. Effective, but exhausting. Then you realize something. The prerequisites haven’t actually changed that much. Linear Algebra is still Linear Algebra; the matrix decompositions you learned still hold. Probability is still Probability; the distributions and Bayes’ rule haven’t moved. Almost all the new material — the new ideas, the recent discoveries — lives in the advanced layer at the top. That’s freezing layers: keep the prerequisite layers fixed at their pretrained state, and only update the advanced one. In the diagram below, W1​ and W2​ — the foundational prerequisites — stay frozen. Only W3​ — the layer closest to your task-specific output — gets a ΔW.
0:16

Full Fine-tuning vs. Freezing Layers. Interact 👉 and == Full Fine-tuning == A real network has many — three layers in this example, billions of parameters in a production model. What does fine-tuning look like when you update all of them? That’s full fine-tuning: continue training every weight in the pretrained network on your new task. Every layer’s W gets its own ΔW. Nothing is frozen — every parameter is in play. Think of an MLP as a chain of prerequisites leading to an advanced course. Layer 1 might be Linear Algebra, layer 2 Probability, layer 3 Advanced Machine Learning — each one building on what came before. Fine-tuning is what happens during graduate study: the foundations are already there from undergrad, so you’re not re-learning. Full fine-tuning is reviewing every prerequisite to see what new topics have appeared and what discoveries the field has made since the last time you sat through them. Effective — but exhausting. This diagram shows the same three-layer MLP twice, side by side. On the left, the pretrained network runs on input X: three weight matrices W₁, W₂, W₃, each followed by a ReLU activation. Full fine-tuning gives the model the most freedom to specialize. Every parameter can move — and every parameter that can move must be stored. But not every prerequisite needs revisiting. The further you go back in the chain, the less the material has changed since pretraining — the linear-algebra basics under your computer-vision course are largely the same as they ever were. The next page does exactly that: freeze the prerequisites that haven’t moved, and only refresh the advanced one closest to your specialization. == Freezing Layers == Full fine-tuning reviewed every prerequisite — Linear Algebra, Probability, Advanced ML — to refresh each subject with the latest topics. Effective, but exhausting. Then you realize something. The prerequisites haven’t actually changed that much. Linear Algebra is still Linear Algebra; the matrix decompositions you learned still hold. Probability is still Probability; the distributions and Bayes’ rule haven’t moved. Almost all the new material — the new ideas, the recent discoveries — lives in the advanced layer at the top. That’s freezing layers: keep the prerequisite layers fixed at their pretrained state, and only update the advanced one. In the diagram below, W1​ and W2​ — the foundational prerequisites — stay frozen. Only W3​ — the layer closest to your task-specific output — gets a ΔW.

Tom Yeh

27,587 次观看 • 3 个月前

Boom! Grok Tasks Make It One Of The Most POWERFUL Real-Time AI Systems In The World. — My How to Use Grok Tasks With Hidden Tools For Powerful Daily Output. Grok Tasks are customizable AI workflows that integrate a variety of tools to streamline daily activities, from research and analysis to creative planning and problem-solving. I have been using them for quite sometime and because of the vital heartbeat of news and first person data on X, it is the most powerful AI platform available. By combining Tasks with tools like web searches, X platform interactions, code execution, and media viewers, you can build efficient, automated processes. These tasks work by prompting Grok with a clear description of what you want to achieve, and Grok will intelligently call the necessary tools in sequence or parallel to deliver results. Here's a step-by-step guide to creating and using Grok Tasks: Step 1: Define Your Task Start by clearly outlining the daily activity or goal. Consider what inputs you have (e.g., a URL, a query, or an attachment) and what output you need (e.g., a summary, calculation, or visual analysis). Break it down into subtasks to identify tool needs. For example, if your task involves researching current events, note that you'll need search and browsing capabilities. Step 2: Review Available Tools Familiarize yourself with the tools Grok can access. Here's a quick overview: - Code Execution: Run Python code for calculations, data processing, or simulations using libraries like numpy, pandas, or sympy. - Browse Page: Fetch and summarize content from any website URL with custom instructions. - Web Search: Perform general internet searches, returning results with optional operators like site:. - Web Search With Snippets: Get quick, detailed excerpts from search results for fact-checking. - X Keyword Search: Advanced search for X posts using operators like from:, since:, or filter:. - X Semantic Search: Find semantically related X posts based on a query, with filters for dates or users. - X User Search: Locate X users by name or handle. - X Thread Fetch: Retrieve a full X post thread, including context like replies and parents. - View Image: Analyze an image from a URL or conversation ID. - View X Video: Extract frames and subtitles from an X-hosted video. - Search PDF Attachment: Query a PDF file for relevant pages using keyword or regex modes. - Browse PDF Attachment: View specific pages of a PDF with text and screenshots. Select tools that align with your task. Aim for a mix to handle data gathering, processing, and visualization. Step 3: Craft Your Prompt Write a detailed prompt to Grok describing the task. Include: - The overall goal. - Specific steps or subtasks. - References to tools if you want to guide the process (e.g., "Use web_search to find sources, then code_execution to analyze data"). - Any constraints, like dates or limits. Example prompt: "Create a Grok Task for my morning routine: Search recent X posts about tech news using x_keyword_search, fetch a key thread with x_thread_fetch, and summarize with browse_page on linked articles." Step 4: Submit and Interact Send your prompt to Grok. It will process the task by calling tools as needed, often in parallel for efficiency. Review the output and refine with follow-up prompts if required (e.g., "Expand on that using view_image for visuals"). Iterate to fine-tune the workflow for reuse. Step 5: Save and Reuse Once refined, note the prompt as a template for future use. You can adapt it for similar tasks, making Grok Tasks a habitual part of your day. Finding Grok Tasks To discover existing Grok Tasks or inspiration for new ones, use X searches with tools like x_keyword_search or x_semantic_search (e.g., query: "Grok Tasks examples" with mode: Latest). Browse community-shared threads via x_thread_fetch, or web_search for tutorials on xAI features. Prompt Grok directly: "Show me popular Grok Tasks for productivity." 1 of 3
0:12

Boom! Grok Tasks Make It One Of The Most POWERFUL Real-Time AI Systems In The World. — My How to Use Grok Tasks With Hidden Tools For Powerful Daily Output. Grok Tasks are customizable AI workflows that integrate a variety of tools to streamline daily activities, from research and analysis to creative planning and problem-solving. I have been using them for quite sometime and because of the vital heartbeat of news and first person data on X, it is the most powerful AI platform available. By combining Tasks with tools like web searches, X platform interactions, code execution, and media viewers, you can build efficient, automated processes. These tasks work by prompting Grok with a clear description of what you want to achieve, and Grok will intelligently call the necessary tools in sequence or parallel to deliver results. Here's a step-by-step guide to creating and using Grok Tasks: Step 1: Define Your Task Start by clearly outlining the daily activity or goal. Consider what inputs you have (e.g., a URL, a query, or an attachment) and what output you need (e.g., a summary, calculation, or visual analysis). Break it down into subtasks to identify tool needs. For example, if your task involves researching current events, note that you'll need search and browsing capabilities. Step 2: Review Available Tools Familiarize yourself with the tools Grok can access. Here's a quick overview: - Code Execution: Run Python code for calculations, data processing, or simulations using libraries like numpy, pandas, or sympy. - Browse Page: Fetch and summarize content from any website URL with custom instructions. - Web Search: Perform general internet searches, returning results with optional operators like site:. - Web Search With Snippets: Get quick, detailed excerpts from search results for fact-checking. - X Keyword Search: Advanced search for X posts using operators like from:, since:, or filter:. - X Semantic Search: Find semantically related X posts based on a query, with filters for dates or users. - X User Search: Locate X users by name or handle. - X Thread Fetch: Retrieve a full X post thread, including context like replies and parents. - View Image: Analyze an image from a URL or conversation ID. - View X Video: Extract frames and subtitles from an X-hosted video. - Search PDF Attachment: Query a PDF file for relevant pages using keyword or regex modes. - Browse PDF Attachment: View specific pages of a PDF with text and screenshots. Select tools that align with your task. Aim for a mix to handle data gathering, processing, and visualization. Step 3: Craft Your Prompt Write a detailed prompt to Grok describing the task. Include: - The overall goal. - Specific steps or subtasks. - References to tools if you want to guide the process (e.g., "Use web_search to find sources, then code_execution to analyze data"). - Any constraints, like dates or limits. Example prompt: "Create a Grok Task for my morning routine: Search recent X posts about tech news using x_keyword_search, fetch a key thread with x_thread_fetch, and summarize with browse_page on linked articles." Step 4: Submit and Interact Send your prompt to Grok. It will process the task by calling tools as needed, often in parallel for efficiency. Review the output and refine with follow-up prompts if required (e.g., "Expand on that using view_image for visuals"). Iterate to fine-tune the workflow for reuse. Step 5: Save and Reuse Once refined, note the prompt as a template for future use. You can adapt it for similar tasks, making Grok Tasks a habitual part of your day. Finding Grok Tasks To discover existing Grok Tasks or inspiration for new ones, use X searches with tools like x_keyword_search or x_semantic_search (e.g., query: "Grok Tasks examples" with mode: Latest). Browse community-shared threads via x_thread_fetch, or web_search for tutorials on xAI features. Prompt Grok directly: "Show me popular Grok Tasks for productivity." 1 of 3

Brian Roemmele

152,242 次观看 • 6 个月前

Right now, you may not have access to models like GPT‑5.6 Sol, GPT‑4.6 Terra, GPT‑5.6 Luna, Claude Mythos 5, or Claude Fable 5. But you can run something surprisingly powerful today, locally, and completely free. in the next 10 mins on your 8 GB VRAM gaming laptop. Gemma 4 26B A4B QAT (MoE) delivers strong performance on a standard 8 GB VRAM GPU using Ollama, with no API, no usage limits, and no external dependencies. Out of the box, it reaches around 20 tokens per second without any optimizations. Only one command in your terminal: Ollama run gemma4:26b This means: Full offline capability (privacy by default) Zero recurring cost Competitive performance for many real world tasks Fast enough for interactive use on cheap consumer hardware If you're waiting for cutting edge cloud models, you're missing what is already practical today: a capable, local LLM that runs entirely on your own machine.
0:19

Right now, you may not have access to models like GPT‑5.6 Sol, GPT‑4.6 Terra, GPT‑5.6 Luna, Claude Mythos 5, or Claude Fable 5. But you can run something surprisingly powerful today, locally, and completely free. in the next 10 mins on your 8 GB VRAM gaming laptop. Gemma 4 26B A4B QAT (MoE) delivers strong performance on a standard 8 GB VRAM GPU using Ollama, with no API, no usage limits, and no external dependencies. Out of the box, it reaches around 20 tokens per second without any optimizations. Only one command in your terminal: Ollama run gemma4:26b This means: Full offline capability (privacy by default) Zero recurring cost Competitive performance for many real world tasks Fast enough for interactive use on cheap consumer hardware If you're waiting for cutting edge cloud models, you're missing what is already practical today: a capable, local LLM that runs entirely on your own machine.

Alok

65,094 次观看 • 28 天前

🚨 JUST IN: CHINA just released an AI EMPLOYEE that works 24X7 on its own. 100% OPEN SOURCE. It researches, codes, builds websites, creates slide decks, and generates videos. All by itself. All on your computer. It's called DeerFlow. You give it a task. It makes a plan, spins up its own team of sub-agents, and gets to work. You come back and there's a finished deliverable waiting. Not a draft. Not a summary. The actual thing. Not a chatbot. Not a research assistant. An AI with its own computer that works while you sleep. Here's what it does on its own: → Spawns multiple sub-agents in parallel, each tackling a different piece of your task, then combines everything into one finished output → Writes real code, runs it, reads the results, and fixes its own mistakes without asking you once → Builds slide decks, websites, full research reports, and data dashboards from scratch → Remembers you across sessions. Your writing style. Your tech stack. Your preferences. Gets better every time. → Reads files you upload, works with them inside its own filesystem, hands you clean finished outputs → Searches the web, runs commands, calls any tool you plug in Here's how it thinks: You give one instruction. The lead agent makes a plan. Sub-agents fan out and work in parallel. Results come back. Everything gets synthesized. You get a deliverable. A single research task might split into a dozen sub-agents, each exploring a different angle, then converge into one finished website with generated visuals. Here's the wildest part: DeerFlow 2.0 launched on February 28th 2026 and hit number 1 on all of GitHub Trending the same day. Version 2.0 was a complete rewrite. Zero shared code with version 1. Because users kept using it for things the team never intended. Data pipelines. Dashboards. Entire content workflows. The community told them what it needed to become. So they burned it down and rebuilt it. 22.7K GitHub stars. 2.7K forks. Built by ByteDance 100% Open Source. MIT License.
0:17

🚨 JUST IN: CHINA just released an AI EMPLOYEE that works 24X7 on its own. 100% OPEN SOURCE. It researches, codes, builds websites, creates slide decks, and generates videos. All by itself. All on your computer. It's called DeerFlow. You give it a task. It makes a plan, spins up its own team of sub-agents, and gets to work. You come back and there's a finished deliverable waiting. Not a draft. Not a summary. The actual thing. Not a chatbot. Not a research assistant. An AI with its own computer that works while you sleep. Here's what it does on its own: → Spawns multiple sub-agents in parallel, each tackling a different piece of your task, then combines everything into one finished output → Writes real code, runs it, reads the results, and fixes its own mistakes without asking you once → Builds slide decks, websites, full research reports, and data dashboards from scratch → Remembers you across sessions. Your writing style. Your tech stack. Your preferences. Gets better every time. → Reads files you upload, works with them inside its own filesystem, hands you clean finished outputs → Searches the web, runs commands, calls any tool you plug in Here's how it thinks: You give one instruction. The lead agent makes a plan. Sub-agents fan out and work in parallel. Results come back. Everything gets synthesized. You get a deliverable. A single research task might split into a dozen sub-agents, each exploring a different angle, then converge into one finished website with generated visuals. Here's the wildest part: DeerFlow 2.0 launched on February 28th 2026 and hit number 1 on all of GitHub Trending the same day. Version 2.0 was a complete rewrite. Zero shared code with version 1. Because users kept using it for things the team never intended. Data pipelines. Dashboards. Entire content workflows. The community told them what it needed to become. So they burned it down and rebuilt it. 22.7K GitHub stars. 2.7K forks. Built by ByteDance 100% Open Source. MIT License.

Kanika

737,284 次观看 • 4 个月前

ByteDance just open sourced an AI SuperAgent that can research, code, build websites, create slide decks, and generate videos. All by itself. DeerFlow 2.0 (27K+ GitHub stars ⭐️), an AI system acting like an autonomous employee with its own computer workspace to research and code. Standard chatbots only generate text and forget your preferences. DeerFlow solves this by giving the AI an isolated virtual computer environment where it safely runs programs. When given a massive task, the main program creates several smaller AI assistants to work simultaneously. It also saves your past workflows so it gets smarter about your needs. DeerFlow is model-agnostic — it works with any LLM that implements the OpenAI-compatible API. Fully supports running local models on your own computer using tools like Ollama. An example - you ask for research on the top 10 AI startups in 2026 for a presentation, the lead agent in DeerFlow breaks that big job into smaller sub-tasks. It assigns one sub-agent to look into each company, another to find funding details, and a third to handle competitor analysis. These agents do all their work in parallel. Everything eventually converges, and a final agent pulls the results into a slide deck complete with custom visuals.
0:17

ByteDance just open sourced an AI SuperAgent that can research, code, build websites, create slide decks, and generate videos. All by itself. DeerFlow 2.0 (27K+ GitHub stars ⭐️), an AI system acting like an autonomous employee with its own computer workspace to research and code. Standard chatbots only generate text and forget your preferences. DeerFlow solves this by giving the AI an isolated virtual computer environment where it safely runs programs. When given a massive task, the main program creates several smaller AI assistants to work simultaneously. It also saves your past workflows so it gets smarter about your needs. DeerFlow is model-agnostic — it works with any LLM that implements the OpenAI-compatible API. Fully supports running local models on your own computer using tools like Ollama. An example - you ask for research on the top 10 AI startups in 2026 for a presentation, the lead agent in DeerFlow breaks that big job into smaller sub-tasks. It assigns one sub-agent to look into each company, another to find funding details, and a third to handle competitor analysis. These agents do all their work in parallel. Everything eventually converges, and a final agent pulls the results into a slide deck complete with custom visuals.

Rohan Paul

50,097 次观看 • 4 个月前

Sitting here watching my Cybertruck charge with the mountains of Utah in the background, it hit me again… I really believe this is the most beautiful Tesla ever made. Every angle is different. It looks futuristic without trying too hard, and it fits just as well in the middle of a city as it does surrounded by nature like this. What makes this truck special is so much more than just the stainless steel or design. For me it’s how capable and practical it is. Long road trips, hauling gear, camping, tough weather, and FSD… it feels like THE one vehicle built to do almost everything. I’ve owned and driven many Teslas over the years, and every one has been amazing in their own unique way, but the Cybertruck is the first one that genuinely makes me stop and look back every time I park it. Driving across the U.S. in this beast has only reinforced that feeling. And to me, the Cybertruck is the best vehicle Tesla has ever built.
0:14

Sitting here watching my Cybertruck charge with the mountains of Utah in the background, it hit me again… I really believe this is the most beautiful Tesla ever made. Every angle is different. It looks futuristic without trying too hard, and it fits just as well in the middle of a city as it does surrounded by nature like this. What makes this truck special is so much more than just the stainless steel or design. For me it’s how capable and practical it is. Long road trips, hauling gear, camping, tough weather, and FSD… it feels like THE one vehicle built to do almost everything. I’ve owned and driven many Teslas over the years, and every one has been amazing in their own unique way, but the Cybertruck is the first one that genuinely makes me stop and look back every time I park it. Driving across the U.S. in this beast has only reinforced that feeling. And to me, the Cybertruck is the best vehicle Tesla has ever built.

Teslaconomics

27,021 次观看 • 29 天前

🚨 COULD A PASSING DWARF PLANET CAUSE A MASS EXTINCTION WITHOUT EVER HITTING EARTH? Physicist Daniele Fargion proposes that close passages of planetary-mass objects from the outer Solar System could have generated powerful, long-lasting tidal forces on Earth. These flybys may have caused: • Massive, persistent tsunamis lasting years • Sudden sea level changes and coastal flooding • Crustal deformation triggering large volcanic episodes • Climate disruption • And even the diversion of asteroids or comets toward Earth The idea is that these events could help explain several major extinctions over the past 600 million years including some where conventional causes (like the Chicxulub impact for the dinosaurs) don’t fully account for the geological record. Why this matters: Most mass extinctions show complex, multi-factor signatures. A single flyby could simultaneously produce several of the observed effects (tidal waves + volcanism + climate shift), offering a potential unifying mechanism that current explanations sometimes lack. The deeper implication: If correct, it would mean Earth’s biosphere has been periodically “reset” or heavily stressed by gravitational interactions with objects we’re only now beginning to catalog in the outer Solar System. It also offers one possible answer to the Fermi Paradox: advanced civilizations may be rare because life on habitable worlds is repeatedly interrupted by such cosmic events. This remains a hypothesis presented in conference proceedings. The correlations are intriguing, but direct geological proof of specific flybys is still lacking. Could repeated gravitational “visits” from the outer Solar System be one of the hidden drivers of Earth’s evolutionary resets? Follow for more frontier planetary science and cosmic threat hypotheses.
0:10

🚨 COULD A PASSING DWARF PLANET CAUSE A MASS EXTINCTION WITHOUT EVER HITTING EARTH? Physicist Daniele Fargion proposes that close passages of planetary-mass objects from the outer Solar System could have generated powerful, long-lasting tidal forces on Earth. These flybys may have caused: • Massive, persistent tsunamis lasting years • Sudden sea level changes and coastal flooding • Crustal deformation triggering large volcanic episodes • Climate disruption • And even the diversion of asteroids or comets toward Earth The idea is that these events could help explain several major extinctions over the past 600 million years including some where conventional causes (like the Chicxulub impact for the dinosaurs) don’t fully account for the geological record. Why this matters: Most mass extinctions show complex, multi-factor signatures. A single flyby could simultaneously produce several of the observed effects (tidal waves + volcanism + climate shift), offering a potential unifying mechanism that current explanations sometimes lack. The deeper implication: If correct, it would mean Earth’s biosphere has been periodically “reset” or heavily stressed by gravitational interactions with objects we’re only now beginning to catalog in the outer Solar System. It also offers one possible answer to the Fermi Paradox: advanced civilizations may be rare because life on habitable worlds is repeatedly interrupted by such cosmic events. This remains a hypothesis presented in conference proceedings. The correlations are intriguing, but direct geological proof of specific flybys is still lacking. Could repeated gravitational “visits” from the outer Solar System be one of the hidden drivers of Earth’s evolutionary resets? Follow for more frontier planetary science and cosmic threat hypotheses.

TheNewPhysics

42,024 次观看 • 1 个月前

i think it’s been enough time & we can finally address this particular discourse, and i think there’s a healthy discussion we can have about it. i genuinely think a fully traditional rendition in 2026, by artists operating at a global pop level, would have changed how the project was received internationally. there’s a very real possibility it would’ve been boxed into “world music,” treated more like cultural exhibition than a modern musical statement, keeping in mind that Arirang Album is not for 'aesthetics' nor is it a history lesson. using 808s, trap production, pop structures, and english hooks while still centering Arirang was actually a significant artistic choice. historically, Arirang was the song of ordinary people. in today’s world, pop culture/pop music is the common language. using contemporary pop to carry that sentiment to millions of listeners across countries feels very aligned with the spirit of what Arirang represented in its own time. and ‘unapologetically korean’ does not have to mean “only in korean” or “frozen in tradition.” it can also mean Korean artists having full control over how their culture is presented, modernized, exported, and understood. i also think if they had leaned entirely into historical styling and traditional presentation, western media may have reduced it to a “cultural curiosity” instead of engaging with it as a current, competitive pop release. critics likely would’ve framed it as heritage performance before artistry. i am glad they chose this route for the album.
0:18

i think it’s been enough time & we can finally address this particular discourse, and i think there’s a healthy discussion we can have about it. i genuinely think a fully traditional rendition in 2026, by artists operating at a global pop level, would have changed how the project was received internationally. there’s a very real possibility it would’ve been boxed into “world music,” treated more like cultural exhibition than a modern musical statement, keeping in mind that Arirang Album is not for 'aesthetics' nor is it a history lesson. using 808s, trap production, pop structures, and english hooks while still centering Arirang was actually a significant artistic choice. historically, Arirang was the song of ordinary people. in today’s world, pop culture/pop music is the common language. using contemporary pop to carry that sentiment to millions of listeners across countries feels very aligned with the spirit of what Arirang represented in its own time. and ‘unapologetically korean’ does not have to mean “only in korean” or “frozen in tradition.” it can also mean Korean artists having full control over how their culture is presented, modernized, exported, and understood. i also think if they had leaned entirely into historical styling and traditional presentation, western media may have reduced it to a “cultural curiosity” instead of engaging with it as a current, competitive pop release. critics likely would’ve framed it as heritage performance before artistry. i am glad they chose this route for the album.

ruz 𓍯

26,131 次观看 • 2 个月前

China's central bank has now bought gold for 19 months straight, the largest official buyer on earth. And this week, as gold broke 4,000 dollars, China's biggest banks moved to push ordinary Chinese out of leveraged gold trading, with at least one warning it will liquidate any position not closed by month-end. Both are true at once, and together they explain what this crash really is. Start with what is being banned, because the words matter. ICBC and a string of other banks are shutting down retail trading in what the Chinese themselves call paper gold, the margined, leveraged contracts where you bet on the price without ever owning a bar. Some banks lifted the margin requirement to 140 percent to choke the leverage off before closing the products outright. Physical gold, meanwhile, stays wide open. Coins, bars, savings plans, ETFs, all fine. It is only the paper, the leverage, the casino, that is being shut, the last step in a five-year retreat that the crash just finished. Officially this is about protecting small investors, and that part is real. The same kind of leverage wiped out a wave of Chinese retail in a 2020 commodity blowup. But set the ban beside what the state is doing and something larger comes into view. While its citizens are pushed out of the paper, the People's Bank of China has spent those same 19 months buying the physical metal, more than two thousand three hundred tonnes of it now, accumulating straight through a 28 percent crash that scared everyone else out. Beijing is not trading gold. It is hoarding it. That is the strategy in one frame. China looked at the two things both called gold, the paper bet and the physical bar, and made a choice no Western government would make. It is taking the metal for the state and closing the casino for everyone else. The reason sits in a single date. 2022, when Russia's reserves were frozen with a keystroke. That taught every country outside the Western system one lesson: dollars in an account can be switched off, gold in your own vault cannot. So China is building its monetary independence out of the one asset nobody can freeze, and it does not want that foundation in the hands of leveraged traders who panic-sell in a crash, or priced by a paper market it does not control. Watch this month and the two worlds split in real time. Western investors were forced out of their gold by margin calls and a rate scare. China's central bank bought that exact dip with both hands. One side treats gold as a trade. The other treats it as the floor under a currency. The West is selling paper gold and calling it a crash. China is buying physical gold and calling it a foundation. In ten years, only one of them will look like it understood what gold was for. The metal is already moving to that side.
0:10

China's central bank has now bought gold for 19 months straight, the largest official buyer on earth. And this week, as gold broke 4,000 dollars, China's biggest banks moved to push ordinary Chinese out of leveraged gold trading, with at least one warning it will liquidate any position not closed by month-end. Both are true at once, and together they explain what this crash really is. Start with what is being banned, because the words matter. ICBC and a string of other banks are shutting down retail trading in what the Chinese themselves call paper gold, the margined, leveraged contracts where you bet on the price without ever owning a bar. Some banks lifted the margin requirement to 140 percent to choke the leverage off before closing the products outright. Physical gold, meanwhile, stays wide open. Coins, bars, savings plans, ETFs, all fine. It is only the paper, the leverage, the casino, that is being shut, the last step in a five-year retreat that the crash just finished. Officially this is about protecting small investors, and that part is real. The same kind of leverage wiped out a wave of Chinese retail in a 2020 commodity blowup. But set the ban beside what the state is doing and something larger comes into view. While its citizens are pushed out of the paper, the People's Bank of China has spent those same 19 months buying the physical metal, more than two thousand three hundred tonnes of it now, accumulating straight through a 28 percent crash that scared everyone else out. Beijing is not trading gold. It is hoarding it. That is the strategy in one frame. China looked at the two things both called gold, the paper bet and the physical bar, and made a choice no Western government would make. It is taking the metal for the state and closing the casino for everyone else. The reason sits in a single date. 2022, when Russia's reserves were frozen with a keystroke. That taught every country outside the Western system one lesson: dollars in an account can be switched off, gold in your own vault cannot. So China is building its monetary independence out of the one asset nobody can freeze, and it does not want that foundation in the hands of leveraged traders who panic-sell in a crash, or priced by a paper market it does not control. Watch this month and the two worlds split in real time. Western investors were forced out of their gold by margin calls and a rate scare. China's central bank bought that exact dip with both hands. One side treats gold as a trade. The other treats it as the floor under a currency. The West is selling paper gold and calling it a crash. China is buying physical gold and calling it a foundation. In ten years, only one of them will look like it understood what gold was for. The metal is already moving to that side.

Shanaka Anslem Perera ⚡

326,333 次观看 • 29 天前

Claude Code + Higgsfield MCP is f*cking cracked 🤯 I built an entire DTC ad campaign inside Claude Code using the new Higgsfield MCP. One product URL → hero static, animated hero shot, 2 UGC clips with a creator wearing the product. 5 assets. One Claude conversation. 3 Higgsfield models. All inside Claude Code. Perfect for DTC brands and agencies who need full campaign packages without booking a shoot or briefing a designer. If you're spending hours every week generating statics in one tool, briefing a motion designer for the hero clip, then chasing a UGC creator for the talking-head shots — this MCP eliminates the entire pipeline: → Drop a product URL into Claude Code → Claude pulls the brand brief — voice, hero SKUs, visual style, target customer → Generates the hero static with ChatGPT Images 2.0 → Animates it into a 5-second cinematic opener with Seedance 2.0 → Generates a UGC creator with GPT Image 2 → Drops her in the product and generates 2 native UGC video clips with Seedance 2.0 No tab-switching between tools. No copy-pasting prompts between platforms. No briefing 3 different vendors for one campaign. What you get: → A complete campaign package — static, animation, UGC — from one product URL → Brand-specific outputs that pull from a real brief, not generic AI slop → Claude making creative decisions between every step (which variation wins, which creator fits the persona, which clip needs a re-spin) → A repeatable pipeline you can run for any product in your catalog Built 100% in Claude Code with the Higgsfield MCP. I recorded a full walkthrough showing exactly how this works: the MCP setup, every prompt, every model, the full campaign output. Want the full video walkthrough? > Like this post > Comment "MCP" And I'll send it over (must be following so I can DM)
0:12

Claude Code + Higgsfield MCP is f*cking cracked 🤯 I built an entire DTC ad campaign inside Claude Code using the new Higgsfield MCP. One product URL → hero static, animated hero shot, 2 UGC clips with a creator wearing the product. 5 assets. One Claude conversation. 3 Higgsfield models. All inside Claude Code. Perfect for DTC brands and agencies who need full campaign packages without booking a shoot or briefing a designer. If you're spending hours every week generating statics in one tool, briefing a motion designer for the hero clip, then chasing a UGC creator for the talking-head shots — this MCP eliminates the entire pipeline: → Drop a product URL into Claude Code → Claude pulls the brand brief — voice, hero SKUs, visual style, target customer → Generates the hero static with ChatGPT Images 2.0 → Animates it into a 5-second cinematic opener with Seedance 2.0 → Generates a UGC creator with GPT Image 2 → Drops her in the product and generates 2 native UGC video clips with Seedance 2.0 No tab-switching between tools. No copy-pasting prompts between platforms. No briefing 3 different vendors for one campaign. What you get: → A complete campaign package — static, animation, UGC — from one product URL → Brand-specific outputs that pull from a real brief, not generic AI slop → Claude making creative decisions between every step (which variation wins, which creator fits the persona, which clip needs a re-spin) → A repeatable pipeline you can run for any product in your catalog Built 100% in Claude Code with the Higgsfield MCP. I recorded a full walkthrough showing exactly how this works: the MCP setup, every prompt, every model, the full campaign output. Want the full video walkthrough? > Like this post > Comment "MCP" And I'll send it over (must be following so I can DM)

Mike Futia

29,480 次观看 • 2 个月前

OpenAI's AgentKit will be so insane, build every step of agents on one platform. These visual agent builders make the whole process of iterating and launching agents far more efficient. It sits on top of the Responses API and unifies the tools that were previously scattered across SDKs and custom orchestration. It lets developers create agent workflows visually, connect data sources securely, and measure performance automatically without coding every layer by hand. The core of AgentKit is the Agent Builder, a drag-and-drop canvas where each node represents an action, guardrail, or decision branch. Developers can link these nodes into multi-agent workflows, preview results instantly, and version each setup. It supports inline evaluation so that developers can see how changes affect output before deploying. The Connector Registry is a single admin panel that manages how data and tools connect across the OpenAI ecosystem. It centralizes integrations like Google Drive, SharePoint, Dropbox, and Microsoft Teams. Large organizations can govern access and flow of data between agents securely under one global console. ChatKit provides a ready-to-use chat interface for embedding agents inside apps or websites. It manages streaming, message threads, and model reasoning displays automatically. Developers can skin the interface to match their product without writing custom front-end code. Under the hood, all these blocks use the same execution core that runs agent reasoning through OpenAI’s APIs. Workflows in Agent Builder compile down to structured instructions for the Responses API, which handles model calls, tool use, and context passing. Connector Registry handles authentication and routing for external tools, while Evals and RFT provide feedback loops that improve agents over time. This integration means developers no longer need to handle orchestration logic, model evaluation pipelines, or safety layers separately. Everything runs natively within OpenAI’s control plane with managed security, automatic versioning, and built-in testing. In short, AgentKit standardizes the entire life cycle of an AI agent—from visual design to deployment and performance tuning—inside a single unified system.
0:10

OpenAI's AgentKit will be so insane, build every step of agents on one platform. These visual agent builders make the whole process of iterating and launching agents far more efficient. It sits on top of the Responses API and unifies the tools that were previously scattered across SDKs and custom orchestration. It lets developers create agent workflows visually, connect data sources securely, and measure performance automatically without coding every layer by hand. The core of AgentKit is the Agent Builder, a drag-and-drop canvas where each node represents an action, guardrail, or decision branch. Developers can link these nodes into multi-agent workflows, preview results instantly, and version each setup. It supports inline evaluation so that developers can see how changes affect output before deploying. The Connector Registry is a single admin panel that manages how data and tools connect across the OpenAI ecosystem. It centralizes integrations like Google Drive, SharePoint, Dropbox, and Microsoft Teams. Large organizations can govern access and flow of data between agents securely under one global console. ChatKit provides a ready-to-use chat interface for embedding agents inside apps or websites. It manages streaming, message threads, and model reasoning displays automatically. Developers can skin the interface to match their product without writing custom front-end code. Under the hood, all these blocks use the same execution core that runs agent reasoning through OpenAI’s APIs. Workflows in Agent Builder compile down to structured instructions for the Responses API, which handles model calls, tool use, and context passing. Connector Registry handles authentication and routing for external tools, while Evals and RFT provide feedback loops that improve agents over time. This integration means developers no longer need to handle orchestration logic, model evaluation pipelines, or safety layers separately. Everything runs natively within OpenAI’s control plane with managed security, automatic versioning, and built-in testing. In short, AgentKit standardizes the entire life cycle of an AI agent—from visual design to deployment and performance tuning—inside a single unified system.

Rohan Paul

178,460 次观看 • 9 个月前

Introducing Pods Hyperspace Pods lets a small group of people - a family, a startup, a few friends, to pool their laptops and desktops into one AI cluster. Everyone installs the CLI, someone creates a pod, shares an invite link, and the machines form a mesh. Models like Qwen 3.5 32B or GLM-5 Turbo that need more memory than any single laptop has get automatically sharded across the group's devices - layers split proportionally, inference pipelined through the ring. From the outside it looks like one OpenAI-compatible API endpoint with a pk_* key that drops straight into your AI tools and products. No configuration beyond pasting the key and changing the base URL. A team of five paying for cloud AI burns $500–2,000 a month on API calls. The same team's existing machines can serve Qwen 3.5 (competitive on SWE-bench) and GLM-5 Turbo (#1 on BrowseComp for tool-calling and web research) for free - the hardware is already on their desks. When a query genuinely needs a frontier model nobody has locally, the pod falls back to cloud at wholesale rates from a shared treasury. But for the daily work - code reviews, refactors, research, drafting - local models handle it and nobody gets billed. And when it is idle, you can rent out your pod on the compute marketplace, with fine-grained permissions for access management. There's no central server involved in inference. Prompts go from your machine to your pod members' machines and back: all of this enabled by the fully peer-to-peer Hyperspace network. Pod state - who's a member, which API keys are valid, how much treasury is left - is replicated across members with consensus, so the whole thing works on a local network. Members behind home routers don't need port forwarding either. The practical setup for most pods is three models covering different jobs: Qwen 3.5 32B for code and reasoning, GLM-5 Turbo for browsing and research, Gemma 4 for fast lightweight tasks. All running on hardware you already own. Pods ship today in Hyperspace v5.19. Model sharding, API keys, treasury, and Raft coordinator are all live. What Makes This Different - No middleman. Your prompts travel from your IDE to your pod members' hardware and back. There is no server in between reading your data. - No vendor lock-in. Pod membership, API keys, and treasury are replicated across your own machines using Raft consensus. If the internet goes down, your local network keeps working. There is no database in someone else's cloud that your pod depends on. - Automatic sharding. You don't configure layer ranges or calculate VRAM budgets. Tell the pod which model you want. It figures out how to split it across whatever hardware is online. - Real NAT traversal. Your friend behind a home router with a dynamic IP? Works. No VPN, no Tailscale, no port forwarding. The nodes handle it. - Free when local. This is the part that matters most. Cloud AI bills scale with usage. Pod inference on local hardware scales with nothing. The marginal cost of your 10,000th prompt is the electricity your laptop was already using. Coming soon: - Pod federation: pods form alliances with other pods. - Marketplace: pods with spare capacity can sell inference to other pods.
0:19

Introducing Pods Hyperspace Pods lets a small group of people - a family, a startup, a few friends, to pool their laptops and desktops into one AI cluster. Everyone installs the CLI, someone creates a pod, shares an invite link, and the machines form a mesh. Models like Qwen 3.5 32B or GLM-5 Turbo that need more memory than any single laptop has get automatically sharded across the group's devices - layers split proportionally, inference pipelined through the ring. From the outside it looks like one OpenAI-compatible API endpoint with a pk_* key that drops straight into your AI tools and products. No configuration beyond pasting the key and changing the base URL. A team of five paying for cloud AI burns $500–2,000 a month on API calls. The same team's existing machines can serve Qwen 3.5 (competitive on SWE-bench) and GLM-5 Turbo (#1 on BrowseComp for tool-calling and web research) for free - the hardware is already on their desks. When a query genuinely needs a frontier model nobody has locally, the pod falls back to cloud at wholesale rates from a shared treasury. But for the daily work - code reviews, refactors, research, drafting - local models handle it and nobody gets billed. And when it is idle, you can rent out your pod on the compute marketplace, with fine-grained permissions for access management. There's no central server involved in inference. Prompts go from your machine to your pod members' machines and back: all of this enabled by the fully peer-to-peer Hyperspace network. Pod state - who's a member, which API keys are valid, how much treasury is left - is replicated across members with consensus, so the whole thing works on a local network. Members behind home routers don't need port forwarding either. The practical setup for most pods is three models covering different jobs: Qwen 3.5 32B for code and reasoning, GLM-5 Turbo for browsing and research, Gemma 4 for fast lightweight tasks. All running on hardware you already own. Pods ship today in Hyperspace v5.19. Model sharding, API keys, treasury, and Raft coordinator are all live. What Makes This Different - No middleman. Your prompts travel from your IDE to your pod members' hardware and back. There is no server in between reading your data. - No vendor lock-in. Pod membership, API keys, and treasury are replicated across your own machines using Raft consensus. If the internet goes down, your local network keeps working. There is no database in someone else's cloud that your pod depends on. - Automatic sharding. You don't configure layer ranges or calculate VRAM budgets. Tell the pod which model you want. It figures out how to split it across whatever hardware is online. - Real NAT traversal. Your friend behind a home router with a dynamic IP? Works. No VPN, no Tailscale, no port forwarding. The nodes handle it. - Free when local. This is the part that matters most. Cloud AI bills scale with usage. Pod inference on local hardware scales with nothing. The marginal cost of your 10,000th prompt is the electricity your laptop was already using. Coming soon: - Pod federation: pods form alliances with other pods. - Marketplace: pods with spare capacity can sell inference to other pods.

Varun

308,506 次观看 • 3 个月前

When a spacecraft leaves Earth, it doesn’t just fire its engines and head straight to its destination. In many missions, especially those going beyond low Earth orbit, there’s a more subtle and elegant strategy at play, one that uses gravity itself as part of the navigation system. This is often called a gravity assist, or a slingshot maneuver. But in the case of missions like #Artemis II, what’s being used is a closely related idea known as a free-return trajectory. At first glance, it might sound simple: the spacecraft goes to the Moon, loops around it, and comes back. But the physics behind it is anything but simple. Instead of relying on continuous propulsion, the spacecraft follows a carefully calculated path through the gravitational field of the Earth–Moon system. It is launched with just the right speed and direction so that, as it approaches the Moon, the Moon’s gravity bends its trajectory. The spacecraft is effectively flung around the Moon, redirected onto a path that naturally brings it back toward Earth. No major engine burn is needed for the return. Small trajectory corrections may still be required, but gravity does the heavy lifting. That’s the key. This kind of trajectory is not just efficient, it’s also safe. If something goes wrong with the spacecraft’s engines or onboard systems, gravity itself ensures the return. It’s an inherent backup plan, built into the trajectory from the very beginning. The same fundamental idea appears in gravity assists used across the Solar System. When a spacecraft flies past a planet, it can gain or lose speed by exchanging momentum with that planet. From the spacecraft’s point of view, it’s as if it has been accelerated without using fuel. In reality, it has borrowed a tiny amount of orbital energy from the planet itself. That’s how missions like Voyager reached the outer planets, and how probes continue to explore regions far beyond what their onboard fuel alone would allow. But there’s an important distinction. An interplanetary gravity assist is typically used to change speed and direction, often increasing the spacecraft’s energy. A free-return trajectory, like the one used in Artemis II, is designed for something more specific: a path that naturally loops back to Earth without requiring additional propulsion. It’s less about gaining energy, and more about shaping a trajectory that guarantees a return. To understand why this works, it helps to stop thinking in straight lines. In space, motion follows curves defined by gravity. The spacecraft is constantly falling, first toward Earth, then toward the Moon, and then back toward Earth again. What looks like a loop is really a continuous free fall through a changing gravitational landscape. This way of navigating space reveals something deeper. We tend to think of engines as the drivers of motion, but once a spacecraft is on its way, gravity does most of the work. The art of spaceflight is not just about thrust. It’s about knowing when not to use it. #GoodLuck #Artemis NASA Artemis
0:11

When a spacecraft leaves Earth, it doesn’t just fire its engines and head straight to its destination. In many missions, especially those going beyond low Earth orbit, there’s a more subtle and elegant strategy at play, one that uses gravity itself as part of the navigation system. This is often called a gravity assist, or a slingshot maneuver. But in the case of missions like #Artemis II, what’s being used is a closely related idea known as a free-return trajectory. At first glance, it might sound simple: the spacecraft goes to the Moon, loops around it, and comes back. But the physics behind it is anything but simple. Instead of relying on continuous propulsion, the spacecraft follows a carefully calculated path through the gravitational field of the Earth–Moon system. It is launched with just the right speed and direction so that, as it approaches the Moon, the Moon’s gravity bends its trajectory. The spacecraft is effectively flung around the Moon, redirected onto a path that naturally brings it back toward Earth. No major engine burn is needed for the return. Small trajectory corrections may still be required, but gravity does the heavy lifting. That’s the key. This kind of trajectory is not just efficient, it’s also safe. If something goes wrong with the spacecraft’s engines or onboard systems, gravity itself ensures the return. It’s an inherent backup plan, built into the trajectory from the very beginning. The same fundamental idea appears in gravity assists used across the Solar System. When a spacecraft flies past a planet, it can gain or lose speed by exchanging momentum with that planet. From the spacecraft’s point of view, it’s as if it has been accelerated without using fuel. In reality, it has borrowed a tiny amount of orbital energy from the planet itself. That’s how missions like Voyager reached the outer planets, and how probes continue to explore regions far beyond what their onboard fuel alone would allow. But there’s an important distinction. An interplanetary gravity assist is typically used to change speed and direction, often increasing the spacecraft’s energy. A free-return trajectory, like the one used in Artemis II, is designed for something more specific: a path that naturally loops back to Earth without requiring additional propulsion. It’s less about gaining energy, and more about shaping a trajectory that guarantees a return. To understand why this works, it helps to stop thinking in straight lines. In space, motion follows curves defined by gravity. The spacecraft is constantly falling, first toward Earth, then toward the Moon, and then back toward Earth again. What looks like a loop is really a continuous free fall through a changing gravitational landscape. This way of navigating space reveals something deeper. We tend to think of engines as the drivers of motion, but once a spacecraft is on its way, gravity does most of the work. The art of spaceflight is not just about thrust. It’s about knowing when not to use it. #GoodLuck #Artemis NASA Artemis

Erika 

234,886 次观看 • 3 个月前

🚨 CATL SAYS LITHIUM-AIR BATTERIES COULD ONE DAY DELIVER 1600+ KM RANGE WITH ENERGY DENSITY APPROACHING PETROL. The world’s largest battery maker is pushing a radical “breathing” battery technology that replaces heavy nickel, cobalt and manganese with lithium metal and oxygen pulled directly from the air. In early lab tests, researchers have already achieved around 1,200 Wh/kg more than four times today’s best lithium-ion cells. With further development, CATL believes the technology could theoretically reach ~12,000 Wh/kg, close to the energy density of petrol itself. Why this matters: • It could slash battery weight and cost dramatically • Small EVs might achieve 1,600+ km of real-world range • It removes dependence on scarce metals like nickel and cobalt • A 1,000-cycle prototype with 1,600 km range would theoretically last 1.6 million kilometres The deeper implication: Lithium-air represents one of the few battery chemistries that could genuinely match or exceed the convenience of petrol without massive compromises. If the enormous technical hurdles (moisture sensitivity, cycle life, and oxygen management) can be solved, it wouldn’t just improve EVs it could fundamentally change what’s possible for electric aviation, long-haul transport, and portable power. We’re still very early. Current prototypes are far from commercial, and most experts expect mass production only after 2030 at the earliest. But the fact that the company producing over half the world’s high-voltage batteries is seriously pursuing this shows how transformative the payoff could be. Would you rather see solid-state batteries win the next decade, or do you think lithium-air could leapfrog them entirely? Follow for more frontier battery technology and energy breakthroughs.
0:10

🚨 CATL SAYS LITHIUM-AIR BATTERIES COULD ONE DAY DELIVER 1600+ KM RANGE WITH ENERGY DENSITY APPROACHING PETROL. The world’s largest battery maker is pushing a radical “breathing” battery technology that replaces heavy nickel, cobalt and manganese with lithium metal and oxygen pulled directly from the air. In early lab tests, researchers have already achieved around 1,200 Wh/kg more than four times today’s best lithium-ion cells. With further development, CATL believes the technology could theoretically reach ~12,000 Wh/kg, close to the energy density of petrol itself. Why this matters: • It could slash battery weight and cost dramatically • Small EVs might achieve 1,600+ km of real-world range • It removes dependence on scarce metals like nickel and cobalt • A 1,000-cycle prototype with 1,600 km range would theoretically last 1.6 million kilometres The deeper implication: Lithium-air represents one of the few battery chemistries that could genuinely match or exceed the convenience of petrol without massive compromises. If the enormous technical hurdles (moisture sensitivity, cycle life, and oxygen management) can be solved, it wouldn’t just improve EVs it could fundamentally change what’s possible for electric aviation, long-haul transport, and portable power. We’re still very early. Current prototypes are far from commercial, and most experts expect mass production only after 2030 at the earliest. But the fact that the company producing over half the world’s high-voltage batteries is seriously pursuing this shows how transformative the payoff could be. Would you rather see solid-state batteries win the next decade, or do you think lithium-air could leapfrog them entirely? Follow for more frontier battery technology and energy breakthroughs.

TheNewPhysics

17,944 次观看 • 1 个月前

In 2025, demand for blockchain applications with genuine real-world utility has collided with a technical barrier that leaves developers questioning what they can realistically build. Anyone building things like tokenized assets, supply chains, AI agents, or prediction markets still juggle a mess of middleware, and somehow end up spending more time stitching than innovating. How so? Every: - Bridges to move assets, - oracles to fetch data, - indexers to make that data searchable, - relayers and bots to keep everything on schedule— is necessary, but each layer also adds cost, latency, and new risks. The end result is an application that’s expensive to run, fragile under stress, and slower than the Web2 software it’s trying to replace. This is the problem Rialo says it wants to solve. Built by Subzero Labs and backed by $20 million from investors like Pantera Capital and Coinbase Ventures 🛡️, Rialo’s pitch is simple: instead of accepting the middleware tower as an unavoidable cost of doing business, compress it into the base chain itself. But Rialo doesn’t describe itself as another Layer 1, its very name, Rialo Isn’t a Layer One, makes that clear. The team frames it instead as a unified real-world network: a protocol rebuilt from the ground up with the assumption that external connectivity is not an afterthought but a core design principle. To understand what this means, consider how today’s dApps are typically assembled. A typical RWA dApp stack involves: - Oracle providers (Chainlink, Pyth, Band) for asset pricing and event settlement - Bridges (Wormhole, Multichain, custodians) for cross-chain asset movement - Indexers (The Graph, Aleph, Stacks API) for querying and preprocessing chain data - Schedulers/relayers for automated tasks and monitoring - Web2 integrations via cloud services, centralized APIs, and off-chain pipelines Each of these steps adds another vendor, another trust boundary, and another operational layer to monitor. By the time the application is live, it resembles a patchwork of loosely coupled services, each carrying its own risks. You don’t have to look far for proof: - Base went dark for 29-43 minutes in August 2025 when its sequencer misfired, freezing every DeFi app on it. - A few months earlier, an AWS outage rippled through Binance and KuCoin, stalling withdrawals because even “decentralized” systems leaned on centralized middleware. - When Infura has faltered, Ethereum dApps have gone offline in sync, not because Ethereum broke, but because the middleware holding it together did. What should feel like building an application instead feels like maintaining a fragile machine. Rialo architecture embeds the primitives that normally live in middleware directly into the protocol. Smart contracts on Rialo can: - be event-driven, able to respond not just to blockchain state changes but also to external events through built-in webhook and API triggers. - fetch data from the web natively, without relying on external oracles or relayers. - include privacy and identity management—KYC hooks and two-factor authentication, at the protocol level rather than as add-ons. - handle cross-chain communication without wrapped assets or third-party bridges. - run on a virtual machine that is compatible with ecosystems like Solana but extended with RISC-V to support modern programming concepts such as async/await and event loops. If these features work as intended, the implications are significant. Today, much of a team’s energy goes into building and maintaining infrastructure: fullnodes, indexers, monitoring scripts, oracle integrations, relayer logic, bridge infrastructure. Each requires engineering headcount and ongoing maintenance. With Rialo, much of this is absorbed by the protocol, freeing developers to concentrate on business logic. Projects can deliver production-grade dApps with smaller, leaner groups focused directly on product design and execution. Operational costs also shrink: indexing and oracle services can run into thousands of dollars a month; collapsing those into built-in functions reduces recurring expenses while simplifying onboarding for new developers. But folding middleware into the chain doesn’t erase complexity, it reshapes it. Some of the problems to be encountered include: - Scale and complexity: Rialo’s validators won’t just be securing transactions; they’ll also be securing APIs, cross-chain data, and scheduled triggers. Any failure in one subsystem could ripple across the entire network. - Performance vs. decentralization: Richer indexing, scheduling, and data ingress could make nodes heavier to run, narrowing who can realistically participate as a validator. That risks reducing the decentralization blockchains depend on for resilience. - Governance pressures: Disputes or failures involving real-world data feeds, external APIs, or cross-chain actions will arise more often, requiring not just technical fixes but robust social infrastructure, clear rules for voting, transparent arbitration, and mechanisms for community trust. Without them, Rialo risks re-centralizing decision-making around a handful of operators. Where, then, does this model make the most sense? That would be in sectors where external connectivity is indispensable and middleware bloat has consistently been a blocker: - Real-world assets: settling tokenized securities or commodities against off-chain events. - Supply chains: triggering a payment the moment a shipment clears customs, without relying on a third-party oracle. - Agent systems: AI agents interacting with real-world APIs and on-chain contracts simultaneously. - Real-time markets: prediction markets or insurance contracts that must resolve immediately against external data. For purely on-chain domains like DeFi primitives or NFTs, where composability matters more than external triggers, the advantages may be less pronounced. This shift is familiar to anyone who remembers the rise of Web2 platform services. Just as Heroku and Firebase abstracted away server maintenance so developers could focus on building products, Rialo is betting that a unified real-world network can let blockchain developers do the same. Adoption will ultimately depend on: - whether its protocol primitives mature quickly, - whether the ecosystem builds out SDKs and tooling that make them usable, - whether compliance features can adapt to changing regulations, - and whether governance proves resilient under adversarial conditions. The first applications will be the test case. If they show that Rialo can replace a fragile patchwork of middleware with a secure, auditable, and cost-effective base layer, it could set a new standard for real-world connectivity in blockchains. If not, it risks simply moving complexity from one part of the stack to another. But at a minimum, Rialo has forced the question: should real-world connectivity in blockchains continue to depend on layers of external vendors, or should it be built into the chain itself? That’s the question Rialo has put on the table — and it’s why I got interested in Rialo .
0:17

In 2025, demand for blockchain applications with genuine real-world utility has collided with a technical barrier that leaves developers questioning what they can realistically build. Anyone building things like tokenized assets, supply chains, AI agents, or prediction markets still juggle a mess of middleware, and somehow end up spending more time stitching than innovating. How so? Every: - Bridges to move assets, - oracles to fetch data, - indexers to make that data searchable, - relayers and bots to keep everything on schedule— is necessary, but each layer also adds cost, latency, and new risks. The end result is an application that’s expensive to run, fragile under stress, and slower than the Web2 software it’s trying to replace. This is the problem Rialo says it wants to solve. Built by Subzero Labs and backed by $20 million from investors like Pantera Capital and Coinbase Ventures 🛡️, Rialo’s pitch is simple: instead of accepting the middleware tower as an unavoidable cost of doing business, compress it into the base chain itself. But Rialo doesn’t describe itself as another Layer 1, its very name, Rialo Isn’t a Layer One, makes that clear. The team frames it instead as a unified real-world network: a protocol rebuilt from the ground up with the assumption that external connectivity is not an afterthought but a core design principle. To understand what this means, consider how today’s dApps are typically assembled. A typical RWA dApp stack involves: - Oracle providers (Chainlink, Pyth, Band) for asset pricing and event settlement - Bridges (Wormhole, Multichain, custodians) for cross-chain asset movement - Indexers (The Graph, Aleph, Stacks API) for querying and preprocessing chain data - Schedulers/relayers for automated tasks and monitoring - Web2 integrations via cloud services, centralized APIs, and off-chain pipelines Each of these steps adds another vendor, another trust boundary, and another operational layer to monitor. By the time the application is live, it resembles a patchwork of loosely coupled services, each carrying its own risks. You don’t have to look far for proof: - Base went dark for 29-43 minutes in August 2025 when its sequencer misfired, freezing every DeFi app on it. - A few months earlier, an AWS outage rippled through Binance and KuCoin, stalling withdrawals because even “decentralized” systems leaned on centralized middleware. - When Infura has faltered, Ethereum dApps have gone offline in sync, not because Ethereum broke, but because the middleware holding it together did. What should feel like building an application instead feels like maintaining a fragile machine. Rialo architecture embeds the primitives that normally live in middleware directly into the protocol. Smart contracts on Rialo can: - be event-driven, able to respond not just to blockchain state changes but also to external events through built-in webhook and API triggers. - fetch data from the web natively, without relying on external oracles or relayers. - include privacy and identity management—KYC hooks and two-factor authentication, at the protocol level rather than as add-ons. - handle cross-chain communication without wrapped assets or third-party bridges. - run on a virtual machine that is compatible with ecosystems like Solana but extended with RISC-V to support modern programming concepts such as async/await and event loops. If these features work as intended, the implications are significant. Today, much of a team’s energy goes into building and maintaining infrastructure: fullnodes, indexers, monitoring scripts, oracle integrations, relayer logic, bridge infrastructure. Each requires engineering headcount and ongoing maintenance. With Rialo, much of this is absorbed by the protocol, freeing developers to concentrate on business logic. Projects can deliver production-grade dApps with smaller, leaner groups focused directly on product design and execution. Operational costs also shrink: indexing and oracle services can run into thousands of dollars a month; collapsing those into built-in functions reduces recurring expenses while simplifying onboarding for new developers. But folding middleware into the chain doesn’t erase complexity, it reshapes it. Some of the problems to be encountered include: - Scale and complexity: Rialo’s validators won’t just be securing transactions; they’ll also be securing APIs, cross-chain data, and scheduled triggers. Any failure in one subsystem could ripple across the entire network. - Performance vs. decentralization: Richer indexing, scheduling, and data ingress could make nodes heavier to run, narrowing who can realistically participate as a validator. That risks reducing the decentralization blockchains depend on for resilience. - Governance pressures: Disputes or failures involving real-world data feeds, external APIs, or cross-chain actions will arise more often, requiring not just technical fixes but robust social infrastructure, clear rules for voting, transparent arbitration, and mechanisms for community trust. Without them, Rialo risks re-centralizing decision-making around a handful of operators. Where, then, does this model make the most sense? That would be in sectors where external connectivity is indispensable and middleware bloat has consistently been a blocker: - Real-world assets: settling tokenized securities or commodities against off-chain events. - Supply chains: triggering a payment the moment a shipment clears customs, without relying on a third-party oracle. - Agent systems: AI agents interacting with real-world APIs and on-chain contracts simultaneously. - Real-time markets: prediction markets or insurance contracts that must resolve immediately against external data. For purely on-chain domains like DeFi primitives or NFTs, where composability matters more than external triggers, the advantages may be less pronounced. This shift is familiar to anyone who remembers the rise of Web2 platform services. Just as Heroku and Firebase abstracted away server maintenance so developers could focus on building products, Rialo is betting that a unified real-world network can let blockchain developers do the same. Adoption will ultimately depend on: - whether its protocol primitives mature quickly, - whether the ecosystem builds out SDKs and tooling that make them usable, - whether compliance features can adapt to changing regulations, - and whether governance proves resilient under adversarial conditions. The first applications will be the test case. If they show that Rialo can replace a fragile patchwork of middleware with a secure, auditable, and cost-effective base layer, it could set a new standard for real-world connectivity in blockchains. If not, it risks simply moving complexity from one part of the stack to another. But at a minimum, Rialo has forced the question: should real-world connectivity in blockchains continue to depend on layers of external vendors, or should it be built into the chain itself? That’s the question Rialo has put on the table — and it’s why I got interested in Rialo .

Jen

12,178 次观看 • 9 个月前