正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

A simple MPC controller for path tracking implemented in python. Few resources actually teach it without assuming a PhD first. This open-source project does exactly that: An iterative MPC tracking controller (built with CVXPY and MuJoCo) that shows how to make a robot (or autonomous vehicle) follow a path... and avoid obstacles in real time. → Autonomous logistics, robot navigation, vehicle control; there's a path-following algorithm behind all of it. → Most implementations are black boxes. This one shows you what's actually happening. → It uses convex optimization (no non-linear solver), and still handles real vehicle physics through iterative linearization. What makes it practical is that you can run it with the mushr car model in MuJoCo, or headless without any physics simulation if you just want to understand the logic. If you're making the jump from classical control to real-time optimisation, this is a very good starting point. 📌 Repository: ——- Weekly robotics and AI insights. Subscribe free:show more

Ilir Aliu

55,492 subscribers

16,064 次观看 • 3 天前 •via X (Twitter)

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

Train a TensorFlow object detection model – then deploy it on a robot 🤖 Iulia Feroli (Iulia Feroli) shows how to turn a notebook into a real-time object detection app. This tutorial works for any project – though we demonstrate the deployment on (and assisted by!) the #ReachyMini, an open-source robot from Pollen Robotics. Built with PyCharm + Claude Code. 👉 Watch it in action:

Train a TensorFlow object detection model – then deploy it on a robot 🤖 Iulia Feroli (Iulia Feroli) shows how to turn a notebook into a real-time object detection app. This tutorial works for any project – though we demonstrate the deployment on (and assisted by!) the #ReachyMini, an open-source robot from Pollen Robotics. Built with PyCharm + Claude Code. 👉 Watch it in action:

PyCharm, a JetBrains IDE

34,908 次观看 • 4 个月前

High school students built an autonomous ball-collecting robot! 🎾 A group of high school students built a robot that picks up balls and shoots them into a bin while moving without stopping, with impressive speed and accuracy. It combines mechanical design, sensors, and software making constant adjustments in real time while the robot is driving. When teenagers can build systems this sophisticated, the talent pipeline for the robotics industry is accelerating! ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

High school students built an autonomous ball-collecting robot! 🎾 A group of high school students built a robot that picks up balls and shoots them into a bin while moving without stopping, with impressive speed and accuracy. It combines mechanical design, sensors, and software making constant adjustments in real time while the robot is driving. When teenagers can build systems this sophisticated, the talent pipeline for the robotics industry is accelerating! ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

1,200,467 次观看 • 5 个月前

If you think this is just another silly demo made with AI, read this post. You might change your mind, because this demo is about MATH. What you see on the screen is not a render from Blender (obviously, it’s not that good). It’s a three.js app built with Toolcraft. Available on the web and rendered in real time(link in the comments). But Blender still has a lot to do with it. Blender has Geometry Nodes - a powerful node-based system for creating and manipulating procedural geometry. In other words, it’s math. And math is a universal language. And who do you think is pretty good at math? >>> AI. Now you can download or buy Blender files from marketplaces, and when they contain Geometry Nodes for procedural animations, objects, surfaces, or effects, you can transfer that logic to the web. Make it real-time, make it interactive. Materials are a separate story, of course. They can still suck unless you use the right tricks: PBR, HDRIs, material blending, displacement, and faked surface relief. So why is Blender important here? Blender is open source, and many tools around it are open source too. An AI trained on their code. That means it can translate the math from one environment to another quite accurately. If you’ve been struggling to reproduce some idea with AI that you had in your head or seen in some references, and it has something to do with Geometry Nodes, and you can find that idea or a close one in the Blender ecosystem - it means you can transfer it to the web. Thank me later.

If you think this is just another silly demo made with AI, read this post. You might change your mind, because this demo is about MATH. What you see on the screen is not a render from Blender (obviously, it’s not that good). It’s a three.js app built with Toolcraft. Available on the web and rendered in real time(link in the comments). But Blender still has a lot to do with it. Blender has Geometry Nodes - a powerful node-based system for creating and manipulating procedural geometry. In other words, it’s math. And math is a universal language. And who do you think is pretty good at math? >>> AI. Now you can download or buy Blender files from marketplaces, and when they contain Geometry Nodes for procedural animations, objects, surfaces, or effects, you can transfer that logic to the web. Make it real-time, make it interactive. Materials are a separate story, of course. They can still suck unless you use the right tricks: PBR, HDRIs, material blending, displacement, and faked surface relief. So why is Blender important here? Blender is open source, and many tools around it are open source too. An AI trained on their code. That means it can translate the math from one environment to another quite accurately. If you’ve been struggling to reproduce some idea with AI that you had in your head or seen in some references, and it has something to do with Geometry Nodes, and you can find that idea or a close one in the Blender ecosystem - it means you can transfer it to the web. Thank me later.

Alex Barashkov

28,300 次观看 • 1 个月前

$Imagine you have a point dancing in space, following three simple rules. You’d think it would eventually settle down or repeat itself, right? Nature isn't always that predictable. This is the Rössler Attractor. It’s a beautiful piece of "organized chaos." By just tweaking a few non-linear equations, we get this marvelous fractal shape, a curve that weaves and loops, forever exploring new ground without ever retracing its exact same path. Most people try to solve this with standard linear tools, but that's like trying to understand a symphony by looking at a single note. To see the real "magic" the bifurcations and the patterns, you have to embrace the non-linearity. It shows us how the smallest nudge at the start can lead to a completely different, stunningly complex world. It’s a simple set of rules, yet it generates infinite complexity. Isn't that just the kick in the head? (📹Credit; equationsinmotion / IG)$

Imagine you have a point dancing in space, following three simple rules. You’d think it would eventually settle down or repeat itself, right? Nature isn't always that predictable. This is the Rössler Attractor. It’s a beautiful piece of "organized chaos." By just tweaking a few non-linear equations, we get this marvelous fractal shape, a curve that weaves and loops, forever exploring new ground without ever retracing its exact same path. Most people try to solve this with standard linear tools, but that's like trying to understand a symphony by looking at a single note. To see the real "magic" the bifurcations and the patterns, you have to embrace the non-linearity. It shows us how the smallest nudge at the start can lead to a completely different, stunningly complex world. It’s a simple set of rules, yet it generates infinite complexity. Isn't that just the kick in the head? (📹Credit; equationsinmotion / IG)

Philosophy Of Physics

40,168 次观看 • 4 个月前

WIRED magazine just gave a 10/10 rating to a piece of hardware for the first time in a decade. It is a robot vacuum. Meet Matic. You do not use an app to control it. You literally treat it like a pet. You can point at a coffee spill and say "Hey Matic, clean this." You can even tell it to "follow me" and it walks behind you. It spent 9 years in development to solve the biggest smart home problem: privacy. It has 5 cameras, but it processes everything locally on an Nvidia chip. Your data is deleted in real-time. Hardware is finally getting fun again.

WIRED magazine just gave a 10/10 rating to a piece of hardware for the first time in a decade. It is a robot vacuum. Meet Matic. You do not use an app to control it. You literally treat it like a pet. You can point at a coffee spill and say "Hey Matic, clean this." You can even tell it to "follow me" and it walks behind you. It spent 9 years in development to solve the biggest smart home problem: privacy. It has 5 cameras, but it processes everything locally on an Nvidia chip. Your data is deleted in real-time. Hardware is finally getting fun again.

shirish

2,010,021 次观看 • 1 个月前

This work makes a humanoid robot do simple parkour moves by looking with a depth camera and choosing the right move on the fly. The big deal is that it turns lots of small human moves into long, real-time robot behavior, without hand-coding every transition or retraining for each new course. A humanoid robot is usually good at steady walking, but it often fails when it has to do fast moves like jumping up, vaulting, or rolling, and then keep going to the next obstacle. The hard part is that you cannot easily collect training data for every possible obstacle shape, distance, and mistake, so robots end up learning a few moves that only work in a narrow setup. This work starts from short clips of real human parkour moves, like stepping over, vaulting, climbing, and rolling. It uses motion matching, which is basically a smart “pick the next clip that fits best right now” search, to stitch those short clips into a long, smooth plan that looks like a human doing a whole course. Then it trains a controller with reinforcement learning (RL), which means the robot learns by trial and error to copy that plan while staying balanced and not falling. After training separate expert controllers for different moves, it compresses them into 1 controller that uses only onboard depth sensing and a simple “go this fast in this direction” command. In real tests on a Unitree G1 humanoid, it can clear multiple obstacles in a row, adapt when obstacles get moved, and climb a wall up to 1.25m.

This work makes a humanoid robot do simple parkour moves by looking with a depth camera and choosing the right move on the fly. The big deal is that it turns lots of small human moves into long, real-time robot behavior, without hand-coding every transition or retraining for each new course. A humanoid robot is usually good at steady walking, but it often fails when it has to do fast moves like jumping up, vaulting, or rolling, and then keep going to the next obstacle. The hard part is that you cannot easily collect training data for every possible obstacle shape, distance, and mistake, so robots end up learning a few moves that only work in a narrow setup. This work starts from short clips of real human parkour moves, like stepping over, vaulting, climbing, and rolling. It uses motion matching, which is basically a smart “pick the next clip that fits best right now” search, to stitch those short clips into a long, smooth plan that looks like a human doing a whole course. Then it trains a controller with reinforcement learning (RL), which means the robot learns by trial and error to copy that plan while staying balanced and not falling. After training separate expert controllers for different moves, it compresses them into 1 controller that uses only onboard depth sensing and a simple “go this fast in this direction” command. In real tests on a Unitree G1 humanoid, it can clear multiple obstacles in a row, adapt when obstacles get moved, and climb a wall up to 1.25m.

Rohan Paul

37,121 次观看 • 6 个月前

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.

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

48,347 次观看 • 5 个月前

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:

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

1,676,995 次观看 • 9 个月前

For 41 years, to find shortest paths in a graph, the Dijkstra’s algorithm, was seen as the best possible way. Not any longer: Now a team from Tsinghua University has beaten it. They created the first faster algorithm for directed shortest paths since 1984. • Faster than Dijkstra on large sparse graphs • Works with real, non-negative edge weights • Proves that sorting is not the main bottleneck anymore Shortest-path algorithms power maps, GPS, logistics, networking, and robotics. This result shows that even the most “finished” algorithms can still be improved. Thanks for sharing, Md Ismail Šojal 🕷️! 📍 Paper: —— Weekly robotics and AI insights. Subscribe free:

For 41 years, to find shortest paths in a graph, the Dijkstra’s algorithm, was seen as the best possible way. Not any longer: Now a team from Tsinghua University has beaten it. They created the first faster algorithm for directed shortest paths since 1984. • Faster than Dijkstra on large sparse graphs • Works with real, non-negative edge weights • Proves that sorting is not the main bottleneck anymore Shortest-path algorithms power maps, GPS, logistics, networking, and robotics. This result shows that even the most “finished” algorithms can still be improved. Thanks for sharing, Md Ismail Šojal 🕷️! 📍 Paper: —— Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

95,345 次观看 • 8 个月前

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:

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 • 9 个月前

The next manipulation tool may not live on your screen. It may stand in front of you look into your eyes and convince you that it understands. Would you rather face a humanoid robot strong enough to hurt you or one designed well enough to make you trust it? This robot copies blinking, eye contact, head movement and facial expressions to create the illusion of human presence. That may look impressive but it also opens a darker question. When a machine can look concerned appear friendly and imitate emotion people may start trusting signals that contain no real feeling no empathy and no moral responsibility. So which is more dangerous a robot with physical power or a robot that can manufacture trust? #HumanoidRobot #Robotics #AI

The next manipulation tool may not live on your screen. It may stand in front of you look into your eyes and convince you that it understands. Would you rather face a humanoid robot strong enough to hurt you or one designed well enough to make you trust it? This robot copies blinking, eye contact, head movement and facial expressions to create the illusion of human presence. That may look impressive but it also opens a darker question. When a machine can look concerned appear friendly and imitate emotion people may start trusting signals that contain no real feeling no empathy and no moral responsibility. So which is more dangerous a robot with physical power or a robot that can manufacture trust? #HumanoidRobot #Robotics #AI

Techniahqrobot | humanoid robots

11,650 次观看 • 1 个月前

even so, I trust that any new watcher will be able to pick up what's going on. The people who made the OVAs shown from time and time again that they have faith in their viewers that they'll be able to understand the world building that culminated to this point. You can start the other shows prior to this, either before or after this OVA and it will still feel like a proper climax leading up to this. The story beats in this show are pretty good in the sense that anyone can understand it, it's not universally profound but it does a good job in highlighting perspectives of every side and have a glimpse at what happened that lead up to it.

even so, I trust that any new watcher will be able to pick up what's going on. The people who made the OVAs shown from time and time again that they have faith in their viewers that they'll be able to understand the world building that culminated to this point. You can start the other shows prior to this, either before or after this OVA and it will still feel like a proper climax leading up to this. The story beats in this show are pretty good in the sense that anyone can understand it, it's not universally profound but it does a good job in highlighting perspectives of every side and have a glimpse at what happened that lead up to it.

delty

41,473 次观看 • 1 年前

Topic: Science and the Fullness of Life. Quote 1: Rejecting science is easy. Understanding it is hard. Yet only this path leads to fullness of life. Author: Zafar Mirzo. Rejecting science is easy. It requires no effort, no study, and no discomfort. You can simply dismiss it and stay within familiar beliefs. Understanding science, however, is hard work. It demands time, intellectual honesty, and the willingness to change your mind when evidence shows you were wrong. Yet the author insists this harder path is the only one that leads to a full life. Science is not just a collection of facts. It is the most reliable way we have to understand reality, our origins, our world, our possibilities. Embracing it opens the door to wonder, clearer thinking, and better decisions. It frees us from illusion and gives us the tools to solve real problems. A life lived in deliberate ignorance stays small. A life guided by scientific understanding expands. The choice, though difficult, is clear. Quote 2: Science is hard to understand, yet without it there is no fullness of life. Author: Zafar Mirzo. Science is hard to understand. It takes real effort, patience, and the courage to question old beliefs. Many prefer to avoid that struggle. Yet the author is clear: without science, there is no fullness of life. Rejecting it or staying ignorant leaves a person trapped in a smaller, less accurate picture of reality. Understanding it, however difficult, brings clarity, wonder, and the ability to engage with the world as it truly is. A life shaped by scientific knowledge is richer. It sharpens thinking, solves real problems, and deepens appreciation for existence. The path is demanding, but the alternative is a diminished existence, one cut off from truth and possibility. Science may be hard, but it is the only road to a complete and meaningful life.

Topic: Science and the Fullness of Life. Quote 1: Rejecting science is easy. Understanding it is hard. Yet only this path leads to fullness of life. Author: Zafar Mirzo. Rejecting science is easy. It requires no effort, no study, and no discomfort. You can simply dismiss it and stay within familiar beliefs. Understanding science, however, is hard work. It demands time, intellectual honesty, and the willingness to change your mind when evidence shows you were wrong. Yet the author insists this harder path is the only one that leads to a full life. Science is not just a collection of facts. It is the most reliable way we have to understand reality, our origins, our world, our possibilities. Embracing it opens the door to wonder, clearer thinking, and better decisions. It frees us from illusion and gives us the tools to solve real problems. A life lived in deliberate ignorance stays small. A life guided by scientific understanding expands. The choice, though difficult, is clear. Quote 2: Science is hard to understand, yet without it there is no fullness of life. Author: Zafar Mirzo. Science is hard to understand. It takes real effort, patience, and the courage to question old beliefs. Many prefer to avoid that struggle. Yet the author is clear: without science, there is no fullness of life. Rejecting it or staying ignorant leaves a person trapped in a smaller, less accurate picture of reality. Understanding it, however difficult, brings clarity, wonder, and the ability to engage with the world as it truly is. A life shaped by scientific knowledge is richer. It sharpens thinking, solves real problems, and deepens appreciation for existence. The path is demanding, but the alternative is a diminished existence, one cut off from truth and possibility. Science may be hard, but it is the only road to a complete and meaningful life.

Zafar Mirzo | Quotes

1,848,868 次观看 • 1 个月前

You point at the mess and say "clean this." That is the whole manual. Matic just shipped this. No app, no map to draw, no menu. The robot listens in more than 70 languages, watches where your hand points, and drives to that spot. Say "follow me" and it trails you into the next room. All of it runs on the robot itself, so it works with the WiFi off. Nine years of work for one thing: a machine you talk to like a dog that actually listens. Matic Robots

You point at the mess and say "clean this." That is the whole manual. Matic just shipped this. No app, no map to draw, no menu. The robot listens in more than 70 languages, watches where your hand points, and drives to that spot. Say "follow me" and it trails you into the next room. All of it runs on the robot itself, so it works with the WiFi off. Nine years of work for one thing: a machine you talk to like a dog that actually listens. Matic Robots

Chubby♨️

495,322 次观看 • 27 天前

Alright this is starting to become a ridiculous problem. Second time in 24 hours on V14.3.7. This isn’t a native 14.3.7 problem, it has been happening to me (though rarely) since 14.2. I’m ok with nav thinking roads are closed and re-routing. 95% of the time it does this it is wrong, but that’s beside the point. It’s the fact that it does it at the very last minute when it literally already started a turning maneuver. It is so startling and tries to whip it out of a maneuver like it’s avoiding a crash. And the worst part is that the roads it’s trying to avoid are almost never actually closed. Please fix this Tesla AI

Alright this is starting to become a ridiculous problem. Second time in 24 hours on V14.3.7. This isn’t a native 14.3.7 problem, it has been happening to me (though rarely) since 14.2. I’m ok with nav thinking roads are closed and re-routing. 95% of the time it does this it is wrong, but that’s beside the point. It’s the fact that it does it at the very last minute when it literally already started a turning maneuver. It is so startling and tries to whip it out of a maneuver like it’s avoiding a crash. And the worst part is that the roads it’s trying to avoid are almost never actually closed. Please fix this Tesla AI

Mike P

38,425 次观看 • 1 个月前

AI is not accelerating nearly fast enough to cure cancer. That is the problem. And it literally cannot without actually seeing what’s happening inside the cell. There’s this new project claiming their models will “solve” cancer by predicting drug responses at scale. Cool story. Except their entire approach still treats the cell like a black box. They’re optimizing for binding affinity while having zero idea what the drug actually does once it’s inside a real, living cell. Meanwhile we’re over here building the tools to watch the cell in real time. No staining or sequencing. Just direct observation of mechanism. You can simulate all you want. But if you can’t see the actual cellular response, you’re just making very confident guesses about something you’ve never actually looked at. We’ve spent two years proving this. The data is there. The difference is night and day. AI is a tool. It’s not the microscope. If your model can’t tell you why a drug is killing the wrong cells or why resistance is forming in real time… it’s not ready to cure cancer. It’s ready to waste another billion dollars. We’re not competing with AI. We’re giving it eyes. Goodbye.

AI is not accelerating nearly fast enough to cure cancer. That is the problem. And it literally cannot without actually seeing what’s happening inside the cell. There’s this new project claiming their models will “solve” cancer by predicting drug responses at scale. Cool story. Except their entire approach still treats the cell like a black box. They’re optimizing for binding affinity while having zero idea what the drug actually does once it’s inside a real, living cell. Meanwhile we’re over here building the tools to watch the cell in real time. No staining or sequencing. Just direct observation of mechanism. You can simulate all you want. But if you can’t see the actual cellular response, you’re just making very confident guesses about something you’ve never actually looked at. We’ve spent two years proving this. The data is there. The difference is night and day. AI is a tool. It’s not the microscope. If your model can’t tell you why a drug is killing the wrong cells or why resistance is forming in real time… it’s not ready to cure cancer. It’s ready to waste another billion dollars. We’re not competing with AI. We’re giving it eyes. Goodbye.

Parmita Mishra

48,203 次观看 • 2 个月前

One of the best finance x AI workflows I've ever built. It helped Claude print +$19,537 completely autonomously. This is my personal market Research Desk - and it took me weeks to build. Think of this as a fully local backtesting trading engine. You pick a market, a timeframe, and a strategy, and it runs that strategy against real historical price data to show you exactly how it would've performed. • It pulls real historical candles (crypto data straight from Binance, no API key needed, or your own CSV/stock data) • You pick from 400+ built-in strategies like moving-average crossover or RSI mean reversion, or bring your own logic • It shows a full interactive equity curve • Every single trade gets logged: entry, exit, P/L • It gives you the real performance metrics If you're not using AI in your trading, you're falling behind fast, and I think everyone should be building personal internal tools like this to elevate their portfolio.

One of the best finance x AI workflows I've ever built. It helped Claude print +$19,537 completely autonomously. This is my personal market Research Desk - and it took me weeks to build. Think of this as a fully local backtesting trading engine. You pick a market, a timeframe, and a strategy, and it runs that strategy against real historical price data to show you exactly how it would've performed. • It pulls real historical candles (crypto data straight from Binance, no API key needed, or your own CSV/stock data) • You pick from 400+ built-in strategies like moving-average crossover or RSI mean reversion, or bring your own logic • It shows a full interactive equity curve • Every single trade gets logged: entry, exit, P/L • It gives you the real performance metrics If you're not using AI in your trading, you're falling behind fast, and I think everyone should be building personal internal tools like this to elevate their portfolio.

Miles Deutscher

33,676 次观看 • 1 个月前

Big moment for text-to-speech. Qwen just open-sourced a text-to-speech model that lets you clone voices, design new ones, and control speech using natural language. Let me explain what I mean: You can literally tell it "speak in a cheerful tone with slight nervousness," and it actually does that. No complex audio engineering needed. What makes this special: - 3-second voice cloning - Covers 10 languages: English, German, French, and more - Latency as low as 97ms for real-time applications - Supports both streaming and non-streaming generation The model comes in two sizes (0.6B and 1.7B parameters), so you can pick based on your hardware and quality needs. Three modes to work with: 1. Custom Voice: Use pre-built premium voices with instruction-based style control 2. Voice Design: Describe the voice you want in plain English (or Chinese), and the model creates it 3. Voice Clone: Provide a 3-second reference audio and clone that voice The best part? It integrates with vLLM for production deployment and has a simple Python package you can pip install. I've shared a link to the GitHub repo in the next tweet.

Big moment for text-to-speech. Qwen just open-sourced a text-to-speech model that lets you clone voices, design new ones, and control speech using natural language. Let me explain what I mean: You can literally tell it "speak in a cheerful tone with slight nervousness," and it actually does that. No complex audio engineering needed. What makes this special: - 3-second voice cloning - Covers 10 languages: English, German, French, and more - Latency as low as 97ms for real-time applications - Supports both streaming and non-streaming generation The model comes in two sizes (0.6B and 1.7B parameters), so you can pick based on your hardware and quality needs. Three modes to work with: 1. Custom Voice: Use pre-built premium voices with instruction-based style control 2. Voice Design: Describe the voice you want in plain English (or Chinese), and the model creates it 3. Voice Clone: Provide a 3-second reference audio and clone that voice The best part? It integrates with vLLM for production deployment and has a simple Python package you can pip install. I've shared a link to the GitHub repo in the next tweet.

Akshay 🚀

31,249 次观看 • 7 个月前