Loading video...

Video Failed to Load

Go Home

HydraFusion Explained. Part I: How does the Copilot engine know what to optimize for? Your prompt is evaluated across 4 dimensions: ➡ Does it require deep reasoning? (aka. reasoning depth) ➡ Is it a sophisticated problem? (aka. code generation complexity) ➡ Is it untangling a complicated mess? (aka. debugging...

juliamuiruri4's profile picture

Julia Muiruri

2,019 subscribers

13,000 views • 1 month ago •via X (Twitter)

Science & TechnologyEducation
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Fable 5 comes back！It can now build playable game prototypes. I think it is actually a signal for where AI coding is going. Making a game is not just “write some code.” Even a small browser game needs: game loop；character movement；collision logic；scoring system；UI states；physics tuning；visual feedback；bug fixing；playtesting This is why game prototyping is a great test for AI models. A model cannot fake it with a pretty answer. Either the game runs, or it does not. What impressed me about Fable 5 is that it is useful for the messy middle: turning an idea into mechanics, turning mechanics into code, debugging broken interactions, and iterating until the prototype feels playable. But here is the practical part: I would not use the strongest model for every step. For game building, I would split the workflow: 1. Fable 5 for game design + architecture 2. a fast coding model for routine implementation 3. a vision-capable model for screenshot/UI feedback 4. a cheaper model for docs, test cases, and small fixes 5. fallback when latency, cost, or output quality becomes a problem That is the real AI coding stack. Not “one magic model does everything.” More like: the right model, for the right task, at the right cost, with fallback when things break. This is why I’ve been looking at ZenMux ZenMux. ZenMux gives developers one gateway to access multiple leading AI models, with OpenAI / Anthropic / Google Vertex compatible APIs, cost tracking, quality benchmarks, auto-routing, and compensation when output quality, latency, or throughput falls short. If AI can now make games, the next question is not just “which model is strongest?” It is:how do we manage the whole model workflow Fable 5 shows the creative ceiling. ZenMux is closer to the infrastructure layer you need when AI coding becomes a real production habit.
0:12

Fable 5 comes back！It can now build playable game prototypes. I think it is actually a signal for where AI coding is going. Making a game is not just “write some code.” Even a small browser game needs: game loop；character movement；collision logic；scoring system；UI states；physics tuning；visual feedback；bug fixing；playtesting This is why game prototyping is a great test for AI models. A model cannot fake it with a pretty answer. Either the game runs, or it does not. What impressed me about Fable 5 is that it is useful for the messy middle: turning an idea into mechanics, turning mechanics into code, debugging broken interactions, and iterating until the prototype feels playable. But here is the practical part: I would not use the strongest model for every step. For game building, I would split the workflow: 1. Fable 5 for game design + architecture 2. a fast coding model for routine implementation 3. a vision-capable model for screenshot/UI feedback 4. a cheaper model for docs, test cases, and small fixes 5. fallback when latency, cost, or output quality becomes a problem That is the real AI coding stack. Not “one magic model does everything.” More like: the right model, for the right task, at the right cost, with fallback when things break. This is why I’ve been looking at ZenMux ZenMux. ZenMux gives developers one gateway to access multiple leading AI models, with OpenAI / Anthropic / Google Vertex compatible APIs, cost tracking, quality benchmarks, auto-routing, and compensation when output quality, latency, or throughput falls short. If AI can now make games, the next question is not just “which model is strongest?” It is:how do we manage the whole model workflow Fable 5 shows the creative ceiling. ZenMux is closer to the infrastructure layer you need when AI coding becomes a real production habit.

Rachel🥥

62,268 views • 4 months ago

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 views • 1 month ago

i gave Ox Alpha the main menu from ECHO and asked it to recreate it only ONE (1) prompt was enough to build this, using the reference this is one of the most beautiful output i've ever had from any model the fact that it's from a stealth model is mindblowing
0:18

i gave Ox Alpha the main menu from ECHO and asked it to recreate it only ONE (1) prompt was enough to build this, using the reference this is one of the most beautiful output i've ever had from any model the fact that it's from a stealth model is mindblowing

filipe

31,171 views • 2 months ago

Routing for long-horizon coding agents is a big deal. Not Diamond just announced a model router that works natively with Claude Code. This is huge. It picks the model and reasoning effort before each turn in a session, runs through a privacy-preserving local proxy, and your requests still execute through your own gateway. In their benchmarks, it approximates Opus 4.8 Xhigh quality at 39 to 61 percent lower cost.
0:16

Routing for long-horizon coding agents is a big deal. Not Diamond just announced a model router that works natively with Claude Code. This is huge. It picks the model and reasoning effort before each turn in a session, runs through a privacy-preserving local proxy, and your requests still execute through your own gateway. In their benchmarks, it approximates Opus 4.8 Xhigh quality at 39 to 61 percent lower cost.

elvis

13,699 views • 3 months ago

Don't train the model, evolve the harness. I read a brilliant blog post from Hugging Face where they took a frozen open model scoring 0% on a hard legal agent benchmark, left its weights alone, and let an automated loop rewrite only the code around it. That code layer is the harness, the runtime wrapper that feeds the model context, runs its tool calls, and decides when a run ends. By the time the loop finished, the system had essentially matched Sonnet 4.6 on the benchmark's headline metric, at roughly 7x lower cost per task. Zero weights changed. The gain existed because of where the model was failing. The judge only grades files saved in the right place under the exact requested filename, and the model kept doing the legal analysis correctly, then saving it under the wrong name, dropping it in a scratch folder, or never writing it at all. So the 0% was never measuring legal reasoning. It was measuring the harness. Hand-tuning that layer is slow and model-specific, so they automated it. A Claude proposer adds exactly one mechanism per iteration, and an outer loop keeps it only if it clearly beats the current best, so accepted mechanisms compound. What the loop discovered says a lot about where agents actually fail. → The biggest single gain was file handling, not intelligence. An automatic step that lands the deliverable exactly where the judge expects it beat every prompt change, with zero extra model tokens. → Code fixes transferred across models, prompt playbooks did not. The same harness lifted a smaller model from the same family by 14 points, but the tuned prompts hurt a different model family on tasks it could already finish. → The harness mattered more than anything else. Same model, same judge, same tasks, and five different harnesses scored anywhere between 3.5% and 80.1%. The gains do eventually flatten, and the remaining misses look like real capability gaps. At some point the wrapper runs out of tricks and the model has to carry the work. But the lesson holds. A benchmark score measures the model and its harness together, and until the harness is fixed, it's impossible to know which one failed. I highly recommend reading this: I also wrote a deep dive on agent harness engineering a while back, covering the orchestration loop, tools, memory, context management, and everything that turns a stateless LLM into a capable agent. The article is quoted below.
0:18

Don't train the model, evolve the harness. I read a brilliant blog post from Hugging Face where they took a frozen open model scoring 0% on a hard legal agent benchmark, left its weights alone, and let an automated loop rewrite only the code around it. That code layer is the harness, the runtime wrapper that feeds the model context, runs its tool calls, and decides when a run ends. By the time the loop finished, the system had essentially matched Sonnet 4.6 on the benchmark's headline metric, at roughly 7x lower cost per task. Zero weights changed. The gain existed because of where the model was failing. The judge only grades files saved in the right place under the exact requested filename, and the model kept doing the legal analysis correctly, then saving it under the wrong name, dropping it in a scratch folder, or never writing it at all. So the 0% was never measuring legal reasoning. It was measuring the harness. Hand-tuning that layer is slow and model-specific, so they automated it. A Claude proposer adds exactly one mechanism per iteration, and an outer loop keeps it only if it clearly beats the current best, so accepted mechanisms compound. What the loop discovered says a lot about where agents actually fail. → The biggest single gain was file handling, not intelligence. An automatic step that lands the deliverable exactly where the judge expects it beat every prompt change, with zero extra model tokens. → Code fixes transferred across models, prompt playbooks did not. The same harness lifted a smaller model from the same family by 14 points, but the tuned prompts hurt a different model family on tasks it could already finish. → The harness mattered more than anything else. Same model, same judge, same tasks, and five different harnesses scored anywhere between 3.5% and 80.1%. The gains do eventually flatten, and the remaining misses look like real capability gaps. At some point the wrapper runs out of tricks and the model has to carry the work. But the lesson holds. A benchmark score measures the model and its harness together, and until the harness is fixed, it's impossible to know which one failed. I highly recommend reading this: I also wrote a deep dive on agent harness engineering a while back, covering the orchestration loop, tools, memory, context management, and everything that turns a stateless LLM into a capable agent. The article is quoted below.

Akshay 🚀

245,724 views • 4 months ago

You can now use Jev right inside Claude Code 🤯 It's called jev-model-router, an early access mod built on Claude Code's new function hooks. Before every turn, it checks in with Jev and asks: > how mechanical the task is > how much reasoning it needs > whether it's risky Then it routes: → it'll move up to a stronger model on weak evidence, and only drops to a cheaper one when it's confident the task is simple → every decision gets logged in your transcript → if the call fails, your request runs untouched Setup: 1. copy the install command: npx claude-code-templates@latest --mod productivity/jev-model-router 2. paste it inside Claude Code 3. run claude with CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1 set 4. accept the trust prompt on first launch Link: Also works with no api key, it just falls back to a built-in classifier with no confidence score. For real jev routing, add your typesafeApiKey or gatewayApiKey to ~/.claude/settings.json. Follow me for more AI workflows and tutorials.
0:15

You can now use Jev right inside Claude Code 🤯 It's called jev-model-router, an early access mod built on Claude Code's new function hooks. Before every turn, it checks in with Jev and asks: > how mechanical the task is > how much reasoning it needs > whether it's risky Then it routes: → it'll move up to a stronger model on weak evidence, and only drops to a cheaper one when it's confident the task is simple → every decision gets logged in your transcript → if the call fails, your request runs untouched Setup: 1. copy the install command: npx claude-code-templates@latest --mod productivity/jev-model-router 2. paste it inside Claude Code 3. run claude with CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1 set 4. accept the trust prompt on first launch Link: Also works with no api key, it just falls back to a built-in classifier with no confidence score. For real jev routing, add your typesafeApiKey or gatewayApiKey to ~/.claude/settings.json. Follow me for more AI workflows and tutorials.

Alvaro Cintas

44,575 views • 1 month ago

I have discovered the the BEST way to get 3D modeling results from LLMs The app LiDAR scans the room while taking hundreds of high quality photos. Then a workflow + skill I've created models out every item recursively checking the model against the photo at the exact spot + angle where the photo was captured The result is a a dimensionally accurate and high quality model of your room All in my latest video on how to do it
0:14

I have discovered the the BEST way to get 3D modeling results from LLMs The app LiDAR scans the room while taking hundreds of high quality photos. Then a workflow + skill I've created models out every item recursively checking the model against the photo at the exact spot + angle where the photo was captured The result is a a dimensionally accurate and high quality model of your room All in my latest video on how to do it

Wes Bos

507,521 views • 14 days ago

PAYING PER MODEL IS THE DUMBEST THING IN TECH RIGHT NOW i was paying 3x what i needed to for AI inference the grid lets you buy a quality spec instead of a specific model.. it routes every request in real time to the cheapest option that qualifies swap one url and your code keeps working exactly the same openai-compatible, one line to switch, 200M free tokens to start
0:19

PAYING PER MODEL IS THE DUMBEST THING IN TECH RIGHT NOW i was paying 3x what i needed to for AI inference the grid lets you buy a quality spec instead of a specific model.. it routes every request in real time to the cheapest option that qualifies swap one url and your code keeps working exactly the same openai-compatible, one line to switch, 200M free tokens to start

Robin Delta

15,729 views • 5 months ago

The good news: you can mid-train yourself to the frontier! At a fraction of the cost! Without distillation! What we did: We took Qwen3.5 14B and mid- and post-trained it to beat every other open model and perform as well as the very best frontier models. This is no simple toy task or format fixing, we are training the model to understand and reason over DNA sequences. Bio is the next frontier for AI and universal access will be crucial to make progress. The fun part: because we train the model on both natural language and DNA sequences you can actually 'chat to your DNA': Ask it questions, ponder the impact of mutations, or ask it to generate a small sequence. We'll soon see the frontier labs move away from math and cyber towards bio. It already started, and we believe researchers should have access to capable models. We are releasing the full recipe, so you can do it, too! Model: Blog:
0:15

The good news: you can mid-train yourself to the frontier! At a fraction of the cost! Without distillation! What we did: We took Qwen3.5 14B and mid- and post-trained it to beat every other open model and perform as well as the very best frontier models. This is no simple toy task or format fixing, we are training the model to understand and reason over DNA sequences. Bio is the next frontier for AI and universal access will be crucial to make progress. The fun part: because we train the model on both natural language and DNA sequences you can actually 'chat to your DNA': Ask it questions, ponder the impact of mutations, or ask it to generate a small sequence. We'll soon see the frontier labs move away from math and cyber towards bio. It already started, and we believe researchers should have access to capable models. We are releasing the full recipe, so you can do it, too! Model: Blog:

Leandro von Werra

80,179 views • 14 days ago

1/ Gemini 2.5 is here, and it’s our most intelligent AI model ever. Our first 2.5 model, Gemini 2.5 Pro Experimental is a state-of-the-art thinking model, leading in a wide range of benchmarks – with impressive improvements in enhanced reasoning and coding and now #1 on Arena by a significant margin. With a model this intelligent, we wanted to get it to people as quickly as possible. Find it on Google AI Studio and in the Google Gemini for Gemini Advanced users now – and in Vertex in the coming weeks. This is the start of a new era of thinking models – and we can’t wait to see where things go from here.
0:14

1/ Gemini 2.5 is here, and it’s our most intelligent AI model ever. Our first 2.5 model, Gemini 2.5 Pro Experimental is a state-of-the-art thinking model, leading in a wide range of benchmarks – with impressive improvements in enhanced reasoning and coding and now #1 on Arena by a significant margin. With a model this intelligent, we wanted to get it to people as quickly as possible. Find it on Google AI Studio and in the Google Gemini for Gemini Advanced users now – and in Vertex in the coming weeks. This is the start of a new era of thinking models – and we can’t wait to see where things go from here.

Sundar Pichai

865,049 views • 1 year ago

Are you ready for some big magic?! Day 27 of the Smart Remesh 4 training Blind_Test_03 #blender #b3d p.s 1: “Blind test” means the engine has never seen the test high-poly 3D model before, either during training or testing. This is the first time the engine has encountered it p.s 2: This engine doesn’t remesh a model; instead, it regenerates a high-poly model to Lowpoly base on adaptive mesh generator, similar to Tripo P2. However, while Tripo generates a 3D model from an image, this engine regenerates the model based on your high-poly model.
0:18

Are you ready for some big magic?! Day 27 of the Smart Remesh 4 training Blind_Test_03 #blender #b3d p.s 1: “Blind test” means the engine has never seen the test high-poly 3D model before, either during training or testing. This is the first time the engine has encountered it p.s 2: This engine doesn’t remesh a model; instead, it regenerates a high-poly model to Lowpoly base on adaptive mesh generator, similar to Tripo P2. However, while Tripo generates a 3D model from an image, this engine regenerates the model based on your high-poly model.

milad_kambari

11,267 views • 27 days ago

Google has just launched an AI feature capable of planning, reasoning and searching the web. All this is done in a single prompt using Deep Research. This is literally the first reasoning model that has access to the internet. Game-changer. How to use it below 🧵
0:14

Google has just launched an AI feature capable of planning, reasoning and searching the web. All this is done in a single prompt using Deep Research. This is literally the first reasoning model that has access to the internet. Game-changer. How to use it below 🧵

Paul Couvert

298,330 views • 1 year ago

Your gaming gpu might be capable of more than you think 💀 NSFW Wan 1.3B is a community model for uncensored text-to-video generation, now available on Hugging Face. → 2.8GB model file → around 8GB VRAM for the base model → 480p video generation → runs locally through ComfyUI how to try it :) visit the Hugging Face model page download wan_1.3B_exp_e14 set up ComfyUI with the Wan 2.1 workflow load the model and test it locally model link: 18+ only. Check the model license and requirements before downloading.
0:18

Sensitive content

Your gaming gpu might be capable of more than you think 💀 NSFW Wan 1.3B is a community model for uncensored text-to-video generation, now available on Hugging Face. → 2.8GB model file → around 8GB VRAM for the base model → 480p video generation → runs locally through ComfyUI how to try it :) visit the Hugging Face model page download wan_1.3B_exp_e14 set up ComfyUI with the Wan 2.1 workflow load the model and test it locally model link: 18+ only. Check the model license and requirements before downloading.

DEATHLESS

39,846 views • 6 days ago

Alright, now that we know *what* an agent is, how does it actually work? When you ask for help on a task, the agent plans a series of steps and executes them directly in the application on your behalf, using the tools it has access to. Say you are booking a local service or trying to organize your inbox (which typically takes multiple steps): the AI model first plans how to achieve the task using its existing knowledge and then interacts with your inbox to execute the task. The agent will continue until it is confident the task has been successfully completed.
0:15

Alright, now that we know *what* an agent is, how does it actually work? When you ask for help on a task, the agent plans a series of steps and executes them directly in the application on your behalf, using the tools it has access to. Say you are booking a local service or trying to organize your inbox (which typically takes multiple steps): the AI model first plans how to achieve the task using its existing knowledge and then interacts with your inbox to execute the task. The agent will continue until it is confident the task has been successfully completed.

Google AI

22,487 views • 11 months ago

Super excited about Hydra-0 from Hongyu Li and team! The key idea is to use flow as a shared visual interface across embodiments/objects for controllable video generation, allowing a single generalist world model to learn from human, handheld-gripper, and robot interaction data. My favorite result is the video below: start from a real video of a human doing the task (left), extract the desired object flow, and condition the model on that flow (right). The model then hallucinates a plausible robot motion that could produce the same object motion. Very cool glimpse of how a generalist world model can bridge human demonstrations and robot control.
0:13

Super excited about Hydra-0 from Hongyu Li and team! The key idea is to use flow as a shared visual interface across embodiments/objects for controllable video generation, allowing a single generalist world model to learn from human, handheld-gripper, and robot interaction data. My favorite result is the video below: start from a real video of a human doing the task (left), extract the desired object flow, and condition the model on that flow (right). The model then hallucinates a plausible robot motion that could produce the same object motion. Very cool glimpse of how a generalist world model can bridge human demonstrations and robot control.

Yunzhu Li

10,850 views • 2 months ago

You don’t have to use one model (or one provider!) for everything. With Workshop, you can combine frontier and local models in the same workflow. For example: Opus can be the main agent, and delegate specific tasks to Gemma 4 via subagents. Better quality where it matters. Better privacy, speed, and cost where it counts. One workflow, best model for each task.
0:18

You don’t have to use one model (or one provider!) for everything. With Workshop, you can combine frontier and local models in the same workflow. For example: Opus can be the main agent, and delegate specific tasks to Gemma 4 via subagents. Better quality where it matters. Better privacy, speed, and cost where it counts. One workflow, best model for each task.

Workshop AI

1,046,048 views • 6 months ago

I just tried out the MiniMax H3 model to create this, and the result is absolutely insane. I am honestly blown away by the quality and detail it managed to produce; it is a total game changer for me!
0:15

I just tried out the MiniMax H3 model to create this, and the result is absolutely insane. I am honestly blown away by the quality and detail it managed to produce; it is a total game changer for me!

KATE

931,833 views • 3 months ago

New open-source agent harness just landed! I got early access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.
0:16

New open-source agent harness just landed! I got early access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.

elvis

11,303 views • 2 months ago

Let me explain the agent loop, simple It's the core of every agentic system, and the part most people overcomplicate It's just this: 1. Send messages to the model 2. Model responds, maybe calls a tool 3. You run the tool 4. Append the result back to messages 5. Repeat until stop_reason is end_turn Step 4 is the whole thing, the write-back is what makes it an agent The model has to see what actually happened before it decides the next move That's the entire loop... understand this cold before you reach for a framework
0:14

Let me explain the agent loop, simple It's the core of every agentic system, and the part most people overcomplicate It's just this: 1. Send messages to the model 2. Model responds, maybe calls a tool 3. You run the tool 4. Append the result back to messages 5. Repeat until stop_reason is end_turn Step 4 is the whole thing, the write-back is what makes it an agent The model has to see what actually happened before it decides the next move That's the entire loop... understand this cold before you reach for a framework

Daniel San

12,514 views • 4 months ago

kling 3.0 is crazy... this model works very different than any other model this is from giving it just 2 images and a multi prompt then it handled all the scenes by itself... now imagine what it could do if you gave it more references and an even more detailed multi prompt going to test this a lot more but kling definetly cooked on this one
0:12

kling 3.0 is crazy... this model works very different than any other model this is from giving it just 2 images and a multi prompt then it handled all the scenes by itself... now imagine what it could do if you gave it more references and an even more detailed multi prompt going to test this a lot more but kling definetly cooked on this one

Miko

96,045 views • 9 months ago