正在加载视频...

视频加载失败

返回首页

Digital twins make deployments! 🔄 Digital twins are more than just simulation, they let you test and fix everything before touching real hardware. The biggest win is catching problems early. You can test the complete system virtually, including all the control logic and data flows. Finding a bug in...

lukas_m_ziegler's profile picture

Lukas Ziegler

50,574 subscribers

27,709 次观看 • 8 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

When robots take the night shift shopping spree! 🛍️ Robots navigate through dm-drogerie markt Deutschland stores at night to create a digital replica of the store's layout, known as a "digital twin." Developed Ubica Robotics GmbH, these autonomous robots scan shelves to provide real-time information about item positions, pricing, stock gaps, and store layouts. 🏪 This data serves multiple purposes, such as improving staff routes, enhancing inventory management, and informing the creation of planograms for more efficient store layouts. It combines digital twin with robotics and it's really cool use case. What are your thoughts? ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:10

When robots take the night shift shopping spree! 🛍️ Robots navigate through dm-drogerie markt Deutschland stores at night to create a digital replica of the store's layout, known as a "digital twin." Developed Ubica Robotics GmbH, these autonomous robots scan shelves to provide real-time information about item positions, pricing, stock gaps, and store layouts. 🏪 This data serves multiple purposes, such as improving staff routes, enhancing inventory management, and informing the creation of planograms for more efficient store layouts. It combines digital twin with robotics and it's really cool use case. What are your thoughts? ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

65,006 次观看 • 8 个月前

AI-Powered weed control! 🌱 The LaserWeeder machine from Carbon Robotics has captured the imagination of American farmers. This technology uses AI system to identify weeds in crops and zap them with precision thermal bursts from lasers. Bit of facts about the cool robot: → The machine can remove weeds from over 40 crops and can also be used for thinning crops. → It can operate in virtually all weather conditions, with millimeter accuracy at all times, and can work through the night thanks to its built-in lighting system. → High-resolution cameras and computer machine learning enable it to distinguish weeds from crops in milliseconds. → The LaserWeeder can replace about 70 workers on farms where manual weeding is used, and can weed up to four acres per hour. What other applications can we expect to see in the future in farming applications? Btw. I believe farming robots are A HUGE THING in robotics! 🔥 ~~ ♻ Join the weekly robotics newsletter, and never miss any news →
0:10

AI-Powered weed control! 🌱 The LaserWeeder machine from Carbon Robotics has captured the imagination of American farmers. This technology uses AI system to identify weeds in crops and zap them with precision thermal bursts from lasers. Bit of facts about the cool robot: → The machine can remove weeds from over 40 crops and can also be used for thinning crops. → It can operate in virtually all weather conditions, with millimeter accuracy at all times, and can work through the night thanks to its built-in lighting system. → High-resolution cameras and computer machine learning enable it to distinguish weeds from crops in milliseconds. → The LaserWeeder can replace about 70 workers on farms where manual weeding is used, and can weed up to four acres per hour. What other applications can we expect to see in the future in farming applications? Btw. I believe farming robots are A HUGE THING in robotics! 🔥 ~~ ♻ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

54,776 次观看 • 10 个月前

Smart Monkey Sunday: Learning the Math 🧮 A lot of people build trading bots by stacking indicators without really understanding what they measure underneath. RSI, MACD, VWAP - they all react to different things, and they all fail differently depending on market conditions. Once you start automating execution, that distinction matters much more because the system will follow the logic exactly as written. The monkey in the video is taking the more useful Sunday approach: slowing down and reviewing the math before deploying anything. That’s also why the Bot Arena includes a virtual balance. You can test ideas, break them, adjust parameters and see how the logic behaves before risking real capital. 👉 Test your logic in the Arena:
0:12

Smart Monkey Sunday: Learning the Math 🧮 A lot of people build trading bots by stacking indicators without really understanding what they measure underneath. RSI, MACD, VWAP - they all react to different things, and they all fail differently depending on market conditions. Once you start automating execution, that distinction matters much more because the system will follow the logic exactly as written. The monkey in the video is taking the more useful Sunday approach: slowing down and reviewing the math before deploying anything. That’s also why the Bot Arena includes a virtual balance. You can test ideas, break them, adjust parameters and see how the logic behaves before risking real capital. 👉 Test your logic in the Arena:

Reactor

16,111 次观看 • 5 个月前

Sub-40ms full self-driving on a $100 drone! 🚁 A demonstration showing a complete full-self-driving pipeline running in under 40 milliseconds on a $100 drone. The prompt: "Find the bike and land." No pre-mapping. Running real-time on commodity hardware. For context, human reaction time is around 200-250ms. This drone is processing sensor data, understanding natural language commands, identifying objects, planning motion, and executing control, all in 40ms. This is what happens when foundation models meet efficient inference. The models get smaller and faster while maintaining capability. The hardware gets cheaper while getting more powerful. The intersection makes previously impossible applications suddenly viable. A few years ago, this required thousands of dollars in compute, pre-mapped environments, and cloud connectivity. Now it runs locally on hardware that costs less than a nice dinner. Awesome stuff Chester & ! 😮‍💨 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:16

Sub-40ms full self-driving on a $100 drone! 🚁 A demonstration showing a complete full-self-driving pipeline running in under 40 milliseconds on a $100 drone. The prompt: "Find the bike and land." No pre-mapping. Running real-time on commodity hardware. For context, human reaction time is around 200-250ms. This drone is processing sensor data, understanding natural language commands, identifying objects, planning motion, and executing control, all in 40ms. This is what happens when foundation models meet efficient inference. The models get smaller and faster while maintaining capability. The hardware gets cheaper while getting more powerful. The intersection makes previously impossible applications suddenly viable. A few years ago, this required thousands of dollars in compute, pre-mapped environments, and cloud connectivity. Now it runs locally on hardware that costs less than a nice dinner. Awesome stuff Chester & ! 😮‍💨 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

310,622 次观看 • 8 个月前

this AI engineering breakdown from IBM Technology is pure f*cking treasure it explains the role as a connected system 01 Python and APIs give you the surface to build on: services, data, integrations, and the software around the model 02 RAG and embeddings solve the context layer: finding the right information before the model has to reason about it 03 agents turn that context into work: they choose tools, run steps, and move toward an outcome 04 observability closes the feedback loop: traces, metrics, failures, latency, and the evidence needed to improve the system 05 deployment is where the system becomes real: reliability, constraints, and the conditions that let people actually depend on it the model sits inside this architecture the AI engineer connects every layer into one operating loop: build → retrieve → act → observe → ship save this, then build your solo business with an AI employee ⭣
0:18

this AI engineering breakdown from IBM Technology is pure f*cking treasure it explains the role as a connected system 01 Python and APIs give you the surface to build on: services, data, integrations, and the software around the model 02 RAG and embeddings solve the context layer: finding the right information before the model has to reason about it 03 agents turn that context into work: they choose tools, run steps, and move toward an outcome 04 observability closes the feedback loop: traces, metrics, failures, latency, and the evidence needed to improve the system 05 deployment is where the system becomes real: reliability, constraints, and the conditions that let people actually depend on it the model sits inside this architecture the AI engineer connects every layer into one operating loop: build → retrieve → act → observe → ship save this, then build your solo business with an AI employee ⭣

beamnxw ./

13,547 次观看 • 25 天前

JUST IN: Reimagine Robotics has just emerged from stealth! 🥷🏻 Its approach to robot training is one of the most human-centric I've seen. The founder is Jonathan Scholz, the person who built and led Google DeepMind's Applied Robotics team in London for seven years. This is not a first-time founder taking a swing at robotics. He has spent a decade at the frontier of the field. The philosophy is powerful. He calls it "monkey-see, monkey-do." 🐒 A worker shows the robot what to do. Watches it attempt the task. Corrects it on the spot. The robot learns. No specialist programmers. No months of integration. And it's already working in the real world: → A made-to-order plastics business trained robots to tend 3D printers overnight, removing print beds, operating latches, pressing controls → A hard drive disassembly facility built a three-robot cell combining robots and people to recover critical materials → Time to prototype and test a new robot behaviour reduced from one day to 10 MINUTES That last number is the one that changes everything. When testing a new behaviour takes 10 minutes instead of a day, the entire pace of deployment transforms. Scholz's framing of the human-robot relationship is worth reading carefully: "A robot that learns on the job depends on people. The worker identifies the bottleneck, shows the robot how to help, and corrects it until it is useful." It's August, and we keep getting robotics bangers week in week. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:14

JUST IN: Reimagine Robotics has just emerged from stealth! 🥷🏻 Its approach to robot training is one of the most human-centric I've seen. The founder is Jonathan Scholz, the person who built and led Google DeepMind's Applied Robotics team in London for seven years. This is not a first-time founder taking a swing at robotics. He has spent a decade at the frontier of the field. The philosophy is powerful. He calls it "monkey-see, monkey-do." 🐒 A worker shows the robot what to do. Watches it attempt the task. Corrects it on the spot. The robot learns. No specialist programmers. No months of integration. And it's already working in the real world: → A made-to-order plastics business trained robots to tend 3D printers overnight, removing print beds, operating latches, pressing controls → A hard drive disassembly facility built a three-robot cell combining robots and people to recover critical materials → Time to prototype and test a new robot behaviour reduced from one day to 10 MINUTES That last number is the one that changes everything. When testing a new behaviour takes 10 minutes instead of a day, the entire pace of deployment transforms. Scholz's framing of the human-robot relationship is worth reading carefully: "A robot that learns on the job depends on people. The worker identifies the bottleneck, shows the robot how to help, and corrects it until it is useful." It's August, and we keep getting robotics bangers week in week. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

23,404 次观看 • 2 个月前

A Letter to Our Community: The Road Ahead for Robotics To our Community and Partners, As we step into 2026, our mission at Axis is clearer than ever: Constructing the definitive End-to-End Scaling Layer for Robotics. Our goal is to accelerate the transfer of diverse human intelligence into Robotics General Intelligence (RGI). By owning the critical path of intelligence creation, we are turning the physical limitations of robotics into a scalable, software-driven future. Here is our strategic outlook and roadmap for the year ahead. The Core Thesis: Simulation is the Only Way Out The path to RGI is currently blocked by Data Scarcity, Generalization Fragility, and Hardware Fragmentation. At Axis, we believe Simulation is the only way out. Our Simulation Data Platform and Data Augmentation Engine transform raw data into "Synthetic Gold". Backed by academic milestones like Roboverse, Skill Blending, and GraspVLA, we have proven that pure simulation can achieve the generalization required for the real world. We don’t just collect data; we architect it. The Engine: Why Crypto? We believe RGI should come from all, not a few. Crypto is not just a feature; it is the primitive that powers our entire ecosystem flywheel: - Incentive Mechanism: Democratizing contribution and rewarding the trainers and developers. - Assetization: Turning proprietary data and refined models into liquid, ownable assets. - Verifiable Workflow: We are opening the "Black Box" of AI. By bringing total transparency to the Task Generation → Data Collection → Model Training pipeline, we ensure every byte of intelligence is verifiable, traceable, and secure. 2026 Strategic Deliverables This year, we are committed to delivering three foundational pillars: - The World's Largest Training Dataset for Robots: A robot training set—diverse, high-quality interaction data at an unprecedented scale. - A Robotics Foundation Model: A universal robotic brain trained on our pure simulation and synthetic data, capable of robust cross-embodiment transfer and open-world adaptability. - Evolvable Robot Hardware: Robots deployed with Axis models that autonomously evolve through continuous interaction, turning every deployment into a self-improving node within our RGI network. The Ultimate Vision We are building more than models; we are architecting the Distributed Machine Economy. A future where every dataset, model, and robotic embodiment is a verifiable asset in a global, autonomous network. Thank you for building the future of intelligence with us✌️📷
0:13

A Letter to Our Community: The Road Ahead for Robotics To our Community and Partners, As we step into 2026, our mission at Axis is clearer than ever: Constructing the definitive End-to-End Scaling Layer for Robotics. Our goal is to accelerate the transfer of diverse human intelligence into Robotics General Intelligence (RGI). By owning the critical path of intelligence creation, we are turning the physical limitations of robotics into a scalable, software-driven future. Here is our strategic outlook and roadmap for the year ahead. The Core Thesis: Simulation is the Only Way Out The path to RGI is currently blocked by Data Scarcity, Generalization Fragility, and Hardware Fragmentation. At Axis, we believe Simulation is the only way out. Our Simulation Data Platform and Data Augmentation Engine transform raw data into "Synthetic Gold". Backed by academic milestones like Roboverse, Skill Blending, and GraspVLA, we have proven that pure simulation can achieve the generalization required for the real world. We don’t just collect data; we architect it. The Engine: Why Crypto? We believe RGI should come from all, not a few. Crypto is not just a feature; it is the primitive that powers our entire ecosystem flywheel: - Incentive Mechanism: Democratizing contribution and rewarding the trainers and developers. - Assetization: Turning proprietary data and refined models into liquid, ownable assets. - Verifiable Workflow: We are opening the "Black Box" of AI. By bringing total transparency to the Task Generation → Data Collection → Model Training pipeline, we ensure every byte of intelligence is verifiable, traceable, and secure. 2026 Strategic Deliverables This year, we are committed to delivering three foundational pillars: - The World's Largest Training Dataset for Robots: A robot training set—diverse, high-quality interaction data at an unprecedented scale. - A Robotics Foundation Model: A universal robotic brain trained on our pure simulation and synthetic data, capable of robust cross-embodiment transfer and open-world adaptability. - Evolvable Robot Hardware: Robots deployed with Axis models that autonomously evolve through continuous interaction, turning every deployment into a self-improving node within our RGI network. The Ultimate Vision We are building more than models; we are architecting the Distributed Machine Economy. A future where every dataset, model, and robotic embodiment is a verifiable asset in a global, autonomous network. Thank you for building the future of intelligence with us✌️📷

Axis Robotics

28,096 次观看 • 9 个月前

the system our agency uses to produce ad creatives for paying b2b clients is now written down in a free doc. it's a claude code build. one intake form takes the icp, pain, offer and cta, and it returns 100+ finished meta statics, each one a different concept with the message designed inside the artwork. the doc is the full build, not a summary: > all 20 prompts in build order, each a complete brief you paste as written > the 80-entry template and visual metaphor library, with the seed entries claude code expands for you > the fire-and-forget layer, so batches finish with the laptop closed and archive themselves before provider links expire > a worked example from a real ad copy to a folder your media buyer can upload straight to ads manager the wall in this video came off one run. the whole build takes about 2 hours. like + comment "ENGINE" and i'll dm you the doc. (following + rt for priority access)
0:11

the system our agency uses to produce ad creatives for paying b2b clients is now written down in a free doc. it's a claude code build. one intake form takes the icp, pain, offer and cta, and it returns 100+ finished meta statics, each one a different concept with the message designed inside the artwork. the doc is the full build, not a summary: > all 20 prompts in build order, each a complete brief you paste as written > the 80-entry template and visual metaphor library, with the seed entries claude code expands for you > the fire-and-forget layer, so batches finish with the laptop closed and archive themselves before provider links expire > a worked example from a real ad copy to a folder your media buyer can upload straight to ads manager the wall in this video came off one run. the whole build takes about 2 hours. like + comment "ENGINE" and i'll dm you the doc. (following + rt for priority access)

KNOX

27,701 次观看 • 3 个月前

You've probably scrolled past a dozen posts about Jev this week without anyone telling you what it actually is. It's the first model from TypeSafe, a lab started by one of the researchers behind ChatGPT. It's a decision engine: you give it options, it picks one and tells you how sure it is. It cannot write a single word, and that is the interesting part. Every other AI you use writes. That is the whole interface. So when software needs a plain yes or no, we make a model write a paragraph and then dig the answer back out of it. Fine in a chat window where a human reads it. Bad inside software, where code has to act on it. The bet is that the valuable half was never the writing. It was the deciding. That problem showed up in WordPress years ago, and it is the reason WPVibe works the way it does. The AI does the work. Anything permanent stops and waits, because a delete that skips the trash is not something software should decide on its own.
0:14

You've probably scrolled past a dozen posts about Jev this week without anyone telling you what it actually is. It's the first model from TypeSafe, a lab started by one of the researchers behind ChatGPT. It's a decision engine: you give it options, it picks one and tells you how sure it is. It cannot write a single word, and that is the interesting part. Every other AI you use writes. That is the whole interface. So when software needs a plain yes or no, we make a model write a paragraph and then dig the answer back out of it. Fine in a chat window where a human reads it. Bad inside software, where code has to act on it. The bet is that the valuable half was never the writing. It was the deciding. That problem showed up in WordPress years ago, and it is the reason WPVibe works the way it does. The AI does the work. Anything permanent stops and waits, because a delete that skips the trash is not something software should decide on its own.

John Turner

21,029 次观看 • 26 天前

All we do is win win win!!!!!! KellyRae, the journey has been long and Intense, but you've persevered. From the early days of finding it difficult to form alliances to the back to back nominations , you've shown incredible resilience and strategic thinking. You've faced challenges head-on during tasks, formed strong bonds with your housemates, and captured the hearts of millions. Your journey has been a testament of GRACE and you've always remained true to yourself. As you stand on the brink of victory, remember all the incredible moments you've shared with us. You've made us laugh, you've made us on our toes, and you've inspired us. No matter what the outcome, you've already won our hearts. Go out there and make history! Good luck King KelllyRae, KaySquad can’t wait to congratulate you again tonight 🫶💫 KELLYRAE TAKES THE CROWN THE MONEY IS MARRIED #KellyRaeTheWinner #DoubleKayX100M #BBNaija
0:13

All we do is win win win!!!!!! KellyRae, the journey has been long and Intense, but you've persevered. From the early days of finding it difficult to form alliances to the back to back nominations , you've shown incredible resilience and strategic thinking. You've faced challenges head-on during tasks, formed strong bonds with your housemates, and captured the hearts of millions. Your journey has been a testament of GRACE and you've always remained true to yourself. As you stand on the brink of victory, remember all the incredible moments you've shared with us. You've made us laugh, you've made us on our toes, and you've inspired us. No matter what the outcome, you've already won our hearts. Go out there and make history! Good luck King KelllyRae, KaySquad can’t wait to congratulate you again tonight 🫶💫 KELLYRAE TAKES THE CROWN THE MONEY IS MARRIED #KellyRaeTheWinner #DoubleKayX100M #BBNaija

Kellyrae

166,807 次观看 • 2 年前

Robots don’t just need better brains. They need WAY more real-world data. 🤖 And collecting high-quality dexterous robot data at scale is one of the hardest problems in physical AI. A fascinating approach is emerging: Wearable human demonstrations + structurally matched dexterous robots. Instead of humans directly teleoperating a robot, Chinese embodied AI startup X Square Robot's TwinDEX system captures the motion, contact, and visual information needed to train the robot — while keeping the data closer to the hardware that will actually execute the task. Early results show promising performance on tool use, fine manipulation, and complex contact-rich tasks. If this approach scales, it could change how we build real-world robotics datasets. The next frontier of physical AI might not be bigger models. It might be better data.
0:16

Robots don’t just need better brains. They need WAY more real-world data. 🤖 And collecting high-quality dexterous robot data at scale is one of the hardest problems in physical AI. A fascinating approach is emerging: Wearable human demonstrations + structurally matched dexterous robots. Instead of humans directly teleoperating a robot, Chinese embodied AI startup X Square Robot's TwinDEX system captures the motion, contact, and visual information needed to train the robot — while keeping the data closer to the hardware that will actually execute the task. Early results show promising performance on tool use, fine manipulation, and complex contact-rich tasks. If this approach scales, it could change how we build real-world robotics datasets. The next frontier of physical AI might not be bigger models. It might be better data.

The Daily Ai

33,341 次观看 • 1 个月前

Autonomous excavator building a wall! 🪨 This will blow your mind! 🤯 Researchers from ETH Zürich and Robotic Systems Lab have used an autonomous excavator to build a 65-meter-long, six-meter-high dry-stone wall. The autonomous system, called "Heap," precisely firstly scanned and then placed stones, forming a wall. Through computer-aided design and control, the robot was able to handle and position over 900 individual elements, some weighing over 1000 kilograms. Can we call it the Great Wall of Switzerland?! 🇨🇭 Here's the page of the project that was on from 2016 to 2025: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:17

Autonomous excavator building a wall! 🪨 This will blow your mind! 🤯 Researchers from ETH Zürich and Robotic Systems Lab have used an autonomous excavator to build a 65-meter-long, six-meter-high dry-stone wall. The autonomous system, called "Heap," precisely firstly scanned and then placed stones, forming a wall. Through computer-aided design and control, the robot was able to handle and position over 900 individual elements, some weighing over 1000 kilograms. Can we call it the Great Wall of Switzerland?! 🇨🇭 Here's the page of the project that was on from 2016 to 2025: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

57,163 次观看 • 29 天前

System identification (sysid) is the process of finding the physical parameters that make a simulation match reality. If you're training an RL locomotion policy in simulation, the accuracy of your motor model directly affects how well the policy transfers to the real robot. A recent git commit by Kevin Zakka added a sysid toolbox to MuJoCo which automates this process: you provide recorded motor data and a MuJoCo model, and it optimizes the model parameters to minimize the difference between simulated and real trajectories. For my RobStride Dynamics RS02 QDD motors (17 Nm peak, 7.75:1 gear), I built a Rust tool that sends multi-sine torque excitation at 1 kHz and records position/velocity feedback. I then feed this data into MuJoCo's sysid optimizer.
0:11

System identification (sysid) is the process of finding the physical parameters that make a simulation match reality. If you're training an RL locomotion policy in simulation, the accuracy of your motor model directly affects how well the policy transfers to the real robot. A recent git commit by Kevin Zakka added a sysid toolbox to MuJoCo which automates this process: you provide recorded motor data and a MuJoCo model, and it optimizes the model parameters to minimize the difference between simulated and real trajectories. For my RobStride Dynamics RS02 QDD motors (17 Nm peak, 7.75:1 gear), I built a Rust tool that sends multi-sine torque excitation at 1 kHz and records position/velocity feedback. I then feed this data into MuJoCo's sysid optimizer.

David Bar

48,988 次观看 • 6 个月前

become a quant trader on Polymarket for free. these three GitHub repos close the whole cycle a friend from a well-known hedge fund sent me the list, said they keep it in their working set and it adds up on the capital. what surprised me is that all three are sitting out in the open. the first one pulls Polymarket and Kalshi trade data with one command. ready scripts inside: win rate by price, calibration, favorite underpricing. you run it and find where the market is wrong yourself. the second one lets you test the hypotheses you found in dry run: real prices, paper trades. the third one is the layer between your strategy and the venue. you write the strategy logic, it acts as the hands. SDKs in Python and TypeScript. 99% of people will skip this post, because free doesn't feel valuable. the remaining 1% will open the repos today and pull profit out of what i write about in a month, and the rest of CT in six
0:17

become a quant trader on Polymarket for free. these three GitHub repos close the whole cycle a friend from a well-known hedge fund sent me the list, said they keep it in their working set and it adds up on the capital. what surprised me is that all three are sitting out in the open. the first one pulls Polymarket and Kalshi trade data with one command. ready scripts inside: win rate by price, calibration, favorite underpricing. you run it and find where the market is wrong yourself. the second one lets you test the hypotheses you found in dry run: real prices, paper trades. the third one is the layer between your strategy and the venue. you write the strategy logic, it acts as the hands. SDKs in Python and TypeScript. 99% of people will skip this post, because free doesn't feel valuable. the remaining 1% will open the repos today and pull profit out of what i write about in a month, and the rest of CT in six

may.crypto {🦅}

21,679 次观看 • 1 个月前

1 Neural Network + Obsidian + Karpathy’s 1-file method = the most unhinged second brain build of 2026. It remembers everything you’ve ever done, and it costs $0 on top of what you already pay. The base is Karpathy’s append and review: 1 giant note, new thoughts stack on top, old ones sink, every few days you reread and pull the survivors back up. No folders, no tags, no plugins the rereading IS the system, because review is what turns storage into thinking. The flaw: past 10,000 lines, no human rereads anything. That’s where the neural network takes over. You keep the note in Obsidian 1 vault, everything dumps to the top: ideas, links, meeting fragments, half-thoughts. You never organize, you only dump. It all lives as plain markdown on your own disk, and that detail is the whole trick. Because now you point Claude Code at the vault folder, and it reads every line you’ve ever written. “What did I think about pricing in March.” “Find the 3 ideas I keep circling.” “What did I drop that deserves a second look.” It answers from YOUR notes, with quotes, in 15 seconds. Then once a week, 1 prompt closes the loop: read the last 7 days, surface the 5 entries worth pulling back up, flag anything that contradicts what I wrote a month ago. The model does the sinking and surfacing Karpathy did by hand, and the note stays alive instead of turning into a graveyard. Week 1 feels like nothing. Week 4 you hit the first “I already solved this in January.” Month 3 you consult your past self more than Google. Most second brains die in 11 days under 40 plugins and 200 folders. This one is 1 file and a loop, and it compounds because dumping takes 0 discipline. Notion stores what you thought. This thing argues back.
0:16

1 Neural Network + Obsidian + Karpathy’s 1-file method = the most unhinged second brain build of 2026. It remembers everything you’ve ever done, and it costs $0 on top of what you already pay. The base is Karpathy’s append and review: 1 giant note, new thoughts stack on top, old ones sink, every few days you reread and pull the survivors back up. No folders, no tags, no plugins the rereading IS the system, because review is what turns storage into thinking. The flaw: past 10,000 lines, no human rereads anything. That’s where the neural network takes over. You keep the note in Obsidian 1 vault, everything dumps to the top: ideas, links, meeting fragments, half-thoughts. You never organize, you only dump. It all lives as plain markdown on your own disk, and that detail is the whole trick. Because now you point Claude Code at the vault folder, and it reads every line you’ve ever written. “What did I think about pricing in March.” “Find the 3 ideas I keep circling.” “What did I drop that deserves a second look.” It answers from YOUR notes, with quotes, in 15 seconds. Then once a week, 1 prompt closes the loop: read the last 7 days, surface the 5 entries worth pulling back up, flag anything that contradicts what I wrote a month ago. The model does the sinking and surfacing Karpathy did by hand, and the note stays alive instead of turning into a graveyard. Week 1 feels like nothing. Week 4 you hit the first “I already solved this in January.” Month 3 you consult your past self more than Google. Most second brains die in 11 days under 40 plugins and 200 folders. This one is 1 file and a loop, and it compounds because dumping takes 0 discipline. Notion stores what you thought. This thing argues back.

West Lord

24,679 次观看 • 2 个月前

I went a little overboard with Codex last week and burned through my entire weekly allowance in two days. Luckily, my quota reset today. Otherwise, I’m not sure what I would’ve done. It got me thinking: instead of asking one large model to handle everything from start to finish, why not let a stronger model plan the project and review the work, while a model built for execution handles the day-to-day implementation? So I tried it. The result was better than I expected. I used GPT-5.6 Sol in Codex as the decision-maker, then ran Ling-3.0-flash from Ant Ling inside OpenCode as the execution engine. Together, they built a small 3D farming game. Before writing any code, I had Codex create four documents: SPEC.md defined the product scope and the lines we couldn’t cross. ARCHITECTURE.md laid out the isometric coordinate system, state machine, and module boundaries. TASKS.md broke the project into small jobs Ling could tackle one at a time. ACCEPTANCE.md explained how each step would be tested and what “done” actually meant. Then I gave Ling a very straightforward role: You are the execution model for this project. Read all four documents before you begin. Work only on the task assigned for this round. When you’re done, run typecheck, test, and build. If anything fails, read the error, fix it, and run the checks again. Do not move on to the next task early. Ling handled dependency installation, project structure, strict TypeScript configuration, test setup, and a production build in 6 minutes and 3 seconds. It ran into issues with the Vite test config, a TS6310 error, and a missing jsdom dependency along the way. Instead of stopping at the first error, it kept reading the logs and fixing the problems until all three checks passed. The speed was honestly hard to believe. If you exclude the time spent waiting on tools, it was producing more than 100 tokens per second. That made the whole development loop feel noticeably faster. After this experiment, I’m planning to keep using the same workflow. If the task is small, there’s no reason to call an expensive planning model for every single step. If the task is large, handing the entire project to a Flash model in one prompt isn’t a great idea either. The setup that makes more sense to me is: Use a more capable model such as Codex to explore the project, make architectural decisions, and break the work down. Put the constraints into specs, schemas, types, and tests instead of leaving them buried in chat history. Give Ling-3.0-flash a steady stream of clear, verifiable implementation tasks. Report bugs with structured context and actual error logs, rather than saying, “It still doesn’t work.” Bring Codex back in for architecture reviews, visual checks, and changes that affect multiple parts of the project. The point of this setup isn’t to give AI a big “build the whole project” button. It’s to turn software development into a pipeline with a much more sensible cost structure: Codex figures out the plan, sets the boundaries, and catches problems. Ling-3.0-flash moves quickly, calls tools reliably, and works through well-defined tasks at scale. For agent workflows that involve lots of repetitive edits, production tasks, and tool calls, this may be a more practical answer than simply using the biggest model for everything.
0:16

I went a little overboard with Codex last week and burned through my entire weekly allowance in two days. Luckily, my quota reset today. Otherwise, I’m not sure what I would’ve done. It got me thinking: instead of asking one large model to handle everything from start to finish, why not let a stronger model plan the project and review the work, while a model built for execution handles the day-to-day implementation? So I tried it. The result was better than I expected. I used GPT-5.6 Sol in Codex as the decision-maker, then ran Ling-3.0-flash from Ant Ling inside OpenCode as the execution engine. Together, they built a small 3D farming game. Before writing any code, I had Codex create four documents: SPEC.md defined the product scope and the lines we couldn’t cross. ARCHITECTURE.md laid out the isometric coordinate system, state machine, and module boundaries. TASKS.md broke the project into small jobs Ling could tackle one at a time. ACCEPTANCE.md explained how each step would be tested and what “done” actually meant. Then I gave Ling a very straightforward role: You are the execution model for this project. Read all four documents before you begin. Work only on the task assigned for this round. When you’re done, run typecheck, test, and build. If anything fails, read the error, fix it, and run the checks again. Do not move on to the next task early. Ling handled dependency installation, project structure, strict TypeScript configuration, test setup, and a production build in 6 minutes and 3 seconds. It ran into issues with the Vite test config, a TS6310 error, and a missing jsdom dependency along the way. Instead of stopping at the first error, it kept reading the logs and fixing the problems until all three checks passed. The speed was honestly hard to believe. If you exclude the time spent waiting on tools, it was producing more than 100 tokens per second. That made the whole development loop feel noticeably faster. After this experiment, I’m planning to keep using the same workflow. If the task is small, there’s no reason to call an expensive planning model for every single step. If the task is large, handing the entire project to a Flash model in one prompt isn’t a great idea either. The setup that makes more sense to me is: Use a more capable model such as Codex to explore the project, make architectural decisions, and break the work down. Put the constraints into specs, schemas, types, and tests instead of leaving them buried in chat history. Give Ling-3.0-flash a steady stream of clear, verifiable implementation tasks. Report bugs with structured context and actual error logs, rather than saying, “It still doesn’t work.” Bring Codex back in for architecture reviews, visual checks, and changes that affect multiple parts of the project. The point of this setup isn’t to give AI a big “build the whole project” button. It’s to turn software development into a pipeline with a much more sensible cost structure: Codex figures out the plan, sets the boundaries, and catches problems. Ling-3.0-flash moves quickly, calls tools reliably, and works through well-defined tasks at scale. For agent workflows that involve lots of repetitive edits, production tasks, and tool calls, this may be a more practical answer than simply using the biggest model for everything.

雪踏乌云

23,107 次观看 • 2 个月前

The architecture of this new world model is one of the most interesting things I've seen lately: Let me first explain how most world models work: They predict and render one frame at a time. If you are navigating in one of these worlds, and you look left, the model draws whatever looks right in the moment. Every time you change your viewpoint, the model has to imagine what should be there again, so it's very common for these models to "forget" what's in the world. For example, if you put a toy on the table, look away, then look back, the toy might not be there anymore. Tripo AI is releasing its Project Eden model, which works very differently: The model builds the world first, and then renders it based on that map. That map holds the real state of the world: the geometry, every object, where things are, what's already happened. The picture you see on screen gets generated from the map. This architecture flips the whole thing. Now, you get the following: 1. The world stops forgetting. Leave, come back, and the toy is still on the table because it lives in the map, not in the last frame you saw. 2. You can edit the world, and those changes persist for anyone who enters later. 3. Multiple people and AI agents can coexist in the world and see it from different perspectives. This is early research, but it's looking really promising. They just raised nearly $200M across two rounds to build it out. Tripo will be at SIGGRAPH 2026 (July 19–23, Los Angeles Convention Center). If you work in 3D, embodied AI, simulation, or anything spatial, go connect with them there.
0:10

The architecture of this new world model is one of the most interesting things I've seen lately: Let me first explain how most world models work: They predict and render one frame at a time. If you are navigating in one of these worlds, and you look left, the model draws whatever looks right in the moment. Every time you change your viewpoint, the model has to imagine what should be there again, so it's very common for these models to "forget" what's in the world. For example, if you put a toy on the table, look away, then look back, the toy might not be there anymore. Tripo AI is releasing its Project Eden model, which works very differently: The model builds the world first, and then renders it based on that map. That map holds the real state of the world: the geometry, every object, where things are, what's already happened. The picture you see on screen gets generated from the map. This architecture flips the whole thing. Now, you get the following: 1. The world stops forgetting. Leave, come back, and the toy is still on the table because it lives in the map, not in the last frame you saw. 2. You can edit the world, and those changes persist for anyone who enters later. 3. Multiple people and AI agents can coexist in the world and see it from different perspectives. This is early research, but it's looking really promising. They just raised nearly $200M across two rounds to build it out. Tripo will be at SIGGRAPH 2026 (July 19–23, Los Angeles Convention Center). If you work in 3D, embodied AI, simulation, or anything spatial, go connect with them there.

Santiago

30,244 次观看 • 3 个月前

grok bot is running 4 agents that generate revenue 24/7 it also built a 3js dashboard for it, with a starship, a dome per business and starman roadstar floating... - finds the prospects out of public data - scores each one before you spend anything - builds the asset before making contact - takes the payment on whop itself - ships the product or deploys the site - shows you what needs approving each morning everything from finding the customer to selling them just wrote a whole guide on how you can set this up exactly:
0:11

grok bot is running 4 agents that generate revenue 24/7 it also built a 3js dashboard for it, with a starship, a dome per business and starman roadstar floating... - finds the prospects out of public data - scores each one before you spend anything - builds the asset before making contact - takes the payment on whop itself - ships the product or deploys the site - shows you what needs approving each morning everything from finding the customer to selling them just wrote a whole guide on how you can set this up exactly:

Chris

56,858 次观看 • 1 个月前