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。

Okay... this is actually insane. OpenCodex feels like the open-source breakthrough I've been waiting for. The best part : You can plug multiple providers into the same OpenAI Codex harness and switch between models depending on the task. Running low on tokens? No problem. Use another provider. OpenRouter free... show more

CHOI

12,624 subscribers

42,771 次观看 • 18 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

It's over. OpenAI just crushed it. We have their o3-level open-source model running on Groq Inc at 500 tokens per second. Watch it build an entire SaaS app in just a few seconds. This is the new standard. Why the hell would you use anything else??

It's over. OpenAI just crushed it. We have their o3-level open-source model running on Groq Inc at 500 tokens per second. Watch it build an entire SaaS app in just a few seconds. This is the new standard. Why the hell would you use anything else??

Matt Shumer

498,675 次观看 • 1 年前

Big win for open-source LLMs! DeepSeek V4 Pro holds the top open-weights score on SWE-bench Verified, in the GPT-5.5 range. GLM 5.2 leads the open-weight intelligence index and sits near the closed frontier on long-horizon coding. But this leaderboard number is a weak proxy for real performance. It comes from one task set, run through one harness, served at one precision. The same weights can even score differently across providers, since many hosts quantize activations to fp8 and drift the model off its reference weights. Real performance is determined based on whether a model can read a repo, make coordinated edits across files, run the tests, and recover when one breaks. By that measure, the top open models hold up, but only inside the right harness. The teams that actually put DeepSeek V4 into production pipelines as a frontier substitute got there through the harness they built around the model, not by picking a stronger model. If you want to see this in practice, Cline (64k+ stars) has actually built that harness around open models, tuned so they run at production quality. And it's tuned so that these LLMs can run at production quality, with plan and act modes, checkpoints, and terminal feedback. ClinePass is the new access layer on top of it. It runs a curated set of those models inside Cline, narrowed to the ones tested for coding-agent use, with 2 to 5x the standard rate limits and no separate provider accounts, keys, or billing to track. The video below shows the setup, and I worked with the team to put this together. It runs alongside custom keys and local models as well, not in place of them.

Big win for open-source LLMs! DeepSeek V4 Pro holds the top open-weights score on SWE-bench Verified, in the GPT-5.5 range. GLM 5.2 leads the open-weight intelligence index and sits near the closed frontier on long-horizon coding. But this leaderboard number is a weak proxy for real performance. It comes from one task set, run through one harness, served at one precision. The same weights can even score differently across providers, since many hosts quantize activations to fp8 and drift the model off its reference weights. Real performance is determined based on whether a model can read a repo, make coordinated edits across files, run the tests, and recover when one breaks. By that measure, the top open models hold up, but only inside the right harness. The teams that actually put DeepSeek V4 into production pipelines as a frontier substitute got there through the harness they built around the model, not by picking a stronger model. If you want to see this in practice, Cline (64k+ stars) has actually built that harness around open models, tuned so they run at production quality. And it's tuned so that these LLMs can run at production quality, with plan and act modes, checkpoints, and terminal feedback. ClinePass is the new access layer on top of it. It runs a curated set of those models inside Cline, narrowed to the ones tested for coding-agent use, with 2 to 5x the standard rate limits and no separate provider accounts, keys, or billing to track. The video below shows the setup, and I worked with the team to put this together. It runs alongside custom keys and local models as well, not in place of them.

Avi Chawla

44,124 次观看 • 1 个月前

This free model just beat every closed-source AI on coding benchmarks. Open weights. 6x cheaper than Opus. The labs don't want you to know it exists. > GLM-5.2 from Zai just topped Code Arena - the first open-weights model to ever hold the #1 coding spot. Not a leaked weight, not a fine-tune. A fully open model beating GPT and Claude on their own turf. It's live on Hugging Face Inference API right now. 5 providers: Novita, Together AI, Fireworks, Deepinfra, Zai. OpenAI-compatible client. → Go to huggingface(.)co → grab HF_TOKEN from account settings → plug into any OpenAI-compatible client 6x cheaper than Opus. Companies bleeding on AI bills are already routing to this for orchestration, caching, and token optimization. The smart money moved before the headline dropped. > Now you know. huggingface(.)co/zai-org/GLM-5.2 Bookmark this before everyone else figures it out.

This free model just beat every closed-source AI on coding benchmarks. Open weights. 6x cheaper than Opus. The labs don't want you to know it exists. > GLM-5.2 from Zai just topped Code Arena - the first open-weights model to ever hold the #1 coding spot. Not a leaked weight, not a fine-tune. A fully open model beating GPT and Claude on their own turf. It's live on Hugging Face Inference API right now. 5 providers: Novita, Together AI, Fireworks, Deepinfra, Zai. OpenAI-compatible client. → Go to huggingface(.)co → grab HF_TOKEN from account settings → plug into any OpenAI-compatible client 6x cheaper than Opus. Companies bleeding on AI bills are already routing to this for orchestration, caching, and token optimization. The smart money moved before the headline dropped. > Now you know. huggingface(.)co/zai-org/GLM-5.2 Bookmark this before everyone else figures it out.

Atenov int.

12,395 次观看 • 1 个月前

Buzz by Jack Dorsey just killed Slack. 100% free and open-source Slack alternative powered by AI agents. Bring your own agents; free desktop app included. I think we're about to see a LOT more open-source projects like this start to launch. Ultimately, the best asset a business can have in the AI era is data, and open-source projects give companies complete oversight over their own internal data. Genius launch →

Buzz by Jack Dorsey just killed Slack. 100% free and open-source Slack alternative powered by AI agents. Bring your own agents; free desktop app included. I think we're about to see a LOT more open-source projects like this start to launch. Ultimately, the best asset a business can have in the AI era is data, and open-source projects give companies complete oversight over their own internal data. Genius launch →

Miles Deutscher

35,531 次观看 • 1 天前

🚨 NVIDIA just flipped the entire AI game… and this is NOT about gaming. DeepSeek-V4-Pro is now live on their build platform. 1.6 TRILLION parameters. Yes… the largest open-source model on the planet right now. And here’s the crazy part: They’re letting you run it FREE On Blackwell GPUs in the cloud. This is the same level of hardware companies like Google, Meta, and Microsoft fight billions to access. Now it’s just… available. No waitlist. No insane setup. Just raw power. We’re watching the shift happen in real time: → From closed AI → open domination → From GPU scarcity → free access → From Big Tech control → builders winning This isn’t an update. It’s a warning shot. Who’s already testing this? Link👇

🚨 NVIDIA just flipped the entire AI game… and this is NOT about gaming. DeepSeek-V4-Pro is now live on their build platform. 1.6 TRILLION parameters. Yes… the largest open-source model on the planet right now. And here’s the crazy part: They’re letting you run it FREE On Blackwell GPUs in the cloud. This is the same level of hardware companies like Google, Meta, and Microsoft fight billions to access. Now it’s just… available. No waitlist. No insane setup. Just raw power. We’re watching the shift happen in real time: → From closed AI → open domination → From GPU scarcity → free access → From Big Tech control → builders winning This isn’t an update. It’s a warning shot. Who’s already testing this? Link👇

divyansh tiwari

29,941 次观看 • 3 个月前

Wow. Alibaba just quietly released one of the most useful AI products of all time. It's an AI agent that you can install instantly in any browser to do tasks for you using Qwen 3.5. No setup, no token costs, 100% free and open source. Try it now:

Wow. Alibaba just quietly released one of the most useful AI products of all time. It's an AI agent that you can install instantly in any browser to do tasks for you using Qwen 3.5. No setup, no token costs, 100% free and open source. Try it now:

Mark Gadala-Maria

148,403 次观看 • 4 个月前

What if aircraft were built like open-source software? Project Caribou is an ambitious open-source effort to build a 200 kg-class heavy-lift hexacopter that anyone can study, improve, and contribute to. The long-term goal is to accelerate the development of larger open-source aircraft and eVTOL platforms. The project targets a ~200 kg maximum takeoff weight with an ~100 kg payload, uses an 18S power architecture, and is built around an ArduPilot-based flight stack. The repository includes CAD models, PCB designs, documentation, and engineering workflows that are evolving in the open. If you are interested in drones, aerospace, robotics, or embedded systems, this is one of the most exciting open-source engineering projects to follow.

What if aircraft were built like open-source software? Project Caribou is an ambitious open-source effort to build a 200 kg-class heavy-lift hexacopter that anyone can study, improve, and contribute to. The long-term goal is to accelerate the development of larger open-source aircraft and eVTOL platforms. The project targets a ~200 kg maximum takeoff weight with an ~100 kg payload, uses an 18S power architecture, and is built around an ArduPilot-based flight stack. The repository includes CAD models, PCB designs, documentation, and engineering workflows that are evolving in the open. If you are interested in drones, aerospace, robotics, or embedded systems, this is one of the most exciting open-source engineering projects to follow.

Praveen Kumar Verma

32,163 次观看 • 6 天前

OpenClaw, but built for normal people. Sim is an open-source platform that lets you build AI agent workflows on a drag-and-drop canvas. Connect them to channels like Telegram and WhatsApp and deploy without writing a single line of code. They also have a built-in Copilot that generates entire workflows from plain English, which you can then tweak and customize in the UI. Key features: - Free and open-source (Apache 2.0) - Vector store integration for RAG-grounded agents - Self-host with one command (`npx simstudio`) - Run fully local with Ollama, no API keys needed - Supports vLLM for production-grade self-hosted inference The thing I really like about Sim is the level of control you get. You can add conditional branching, parallel execution, human-in-the-loop approval gates, and even nest workflows inside other workflows. Everything is visible on the canvas, so you know exactly what your agent is doing at every step. And you can build a workflow in Sim, deploy it as an MCP server, and plug it into any agent, including OpenClaw. I've shared the link to Sim's GitHub repo in the next tweet.

OpenClaw, but built for normal people. Sim is an open-source platform that lets you build AI agent workflows on a drag-and-drop canvas. Connect them to channels like Telegram and WhatsApp and deploy without writing a single line of code. They also have a built-in Copilot that generates entire workflows from plain English, which you can then tweak and customize in the UI. Key features: - Free and open-source (Apache 2.0) - Vector store integration for RAG-grounded agents - Self-host with one command (`npx simstudio`) - Run fully local with Ollama, no API keys needed - Supports vLLM for production-grade self-hosted inference The thing I really like about Sim is the level of control you get. You can add conditional branching, parallel execution, human-in-the-loop approval gates, and even nest workflows inside other workflows. Everything is visible on the canvas, so you know exactly what your agent is doing at every step. And you can build a workflow in Sim, deploy it as an MCP server, and plug it into any agent, including OpenClaw. I've shared the link to Sim's GitHub repo in the next tweet.

Akshay 🚀

52,426 次观看 • 5 个月前

$🇨🇳 CHINA IS ALMOST READY TO UNDERCUT THE WORLD'S BEST AI MODELS. Six months ago, that sounded impossible. Today GLM-5.2 is open source and costs a fraction of frontier models. Zhipu's co-founder says Fable-class Chinese AI comes even sooner than people think. This is the same playbook China ran on solar, on steel, on EVs. Build it cheaper. Give it away. Take the market. If China delivers frontier AI at a fraction of the price, the economics holding up the U.S. AI market start to crack.$

🇨🇳 CHINA IS ALMOST READY TO UNDERCUT THE WORLD'S BEST AI MODELS. Six months ago, that sounded impossible. Today GLM-5.2 is open source and costs a fraction of frontier models. Zhipu's co-founder says Fable-class Chinese AI comes even sooner than people think. This is the same playbook China ran on solar, on steel, on EVs. Build it cheaper. Give it away. Take the market. If China delivers frontier AI at a fraction of the price, the economics holding up the U.S. AI market start to crack.

CryptoGoos

46,766 次观看 • 1 个月前

Introducing: OpenGranola 🔥 I built an open source meeting copilot for macOS. It transcribes both sides of your call on-device, searches your own notes in real time, and hands you talking points right when the conversation needs them. No audio leaves your Mac. Point it at a folder of markdown files, pick any LLM through OpenRouter (Claude, GPT-4o, Gemini, Llama), and it just works. It's invisible to screen share too — nobody knows you have it. The whole thing is open source. Link below

Introducing: OpenGranola 🔥 I built an open source meeting copilot for macOS. It transcribes both sides of your call on-device, searches your own notes in real time, and hands you talking points right when the conversation needs them. No audio leaves your Mac. Point it at a folder of markdown files, pick any LLM through OpenRouter (Claude, GPT-4o, Gemini, Llama), and it just works. It's invisible to screen share too — nobody knows you have it. The whole thing is open source. Link below

yazin

293,055 次观看 • 4 个月前

This completely changes how apps are built. Now, even we can build apps on cell phones. Just describe the requirements in chat, and this AI gradually turns them into a fully functional app. Here’s how you can use it (demo + details) 👇

This completely changes how apps are built. Now, even we can build apps on cell phones. Just describe the requirements in chat, and this AI gradually turns them into a fully functional app. Here’s how you can use it (demo + details) 👇

ZOYA ✪

23,774 次观看 • 7 个月前

so, i might have been wrong.... i've been looking into AI UGC a little bit more and it's actually kind of insane the video you see below took $2 to make and the only visible problem (might) be the audio i know ecom brands using ai ugc for there organic and paid doing over $1M/mo i'm still bullish on real human clipping and ai content but considering how much ai ugc has improved over the last few months... it's going to be interesting to see how the content marketing world changes this year

so, i might have been wrong.... i've been looking into AI UGC a little bit more and it's actually kind of insane the video you see below took $2 to make and the only visible problem (might) be the audio i know ecom brands using ai ugc for there organic and paid doing over $1M/mo i'm still bullish on real human clipping and ai content but considering how much ai ugc has improved over the last few months... it's going to be interesting to see how the content marketing world changes this year

Alex

24,711 次观看 • 3 个月前

GITHUB JUST KILLED THE WORST PART OF VIBE CODING they shipped a free tool called Spec Kit and it already crossed 120,000 stars the fix is stupidly simple instead of tossing vague prompts at an agent and praying it doesn't wreck your project Spec Kit makes the AI write a full structured spec before it touches a single line of code it works through the problem first figures out what you want to build asks about the gaps lays out the project then it starts coding you get fewer insane bugs, cleaner output and results you can predict the flow looks like this: /constitution for your rules and standards /specify for what you want to build /clarify for the open questions before you start /plan for architecture and stack /tasks for the ordered work /implement to run it it plugs into Claude Code, Cursor, Copilot, Codex, Gemini CLI and 25+ other agents 120,000 stars, 10,000 forks, open source, shipped by GitHub itself learning to drive agents like this is most of what separates people getting hired as AI engineers from everyone still fighting their prompts

GITHUB JUST KILLED THE WORST PART OF VIBE CODING they shipped a free tool called Spec Kit and it already crossed 120,000 stars the fix is stupidly simple instead of tossing vague prompts at an agent and praying it doesn't wreck your project Spec Kit makes the AI write a full structured spec before it touches a single line of code it works through the problem first figures out what you want to build asks about the gaps lays out the project then it starts coding you get fewer insane bugs, cleaner output and results you can predict the flow looks like this: /constitution for your rules and standards /specify for what you want to build /clarify for the open questions before you start /plan for architecture and stack /tasks for the ordered work /implement to run it it plugs into Claude Code, Cursor, Copilot, Codex, Gemini CLI and 25+ other agents 120,000 stars, 10,000 forks, open source, shipped by GitHub itself learning to drive agents like this is most of what separates people getting hired as AI engineers from everyone still fighting their prompts

Atlas

500,090 次观看 • 25 天前

I ran Codex, Claude, and Gemini on the same PR review. They disagreed on 4 out of 7 issues. That’s when I realized the best workflow isn’t choosing one model - it’s making them compare notes. So I built Council: an open source CLI that runs all three in parallel, surfaces disagreements, and gives you one synthesized recommendation. npx @armstrng/council review this PR

I ran Codex, Claude, and Gemini on the same PR review. They disagreed on 4 out of 7 issues. That’s when I realized the best workflow isn’t choosing one model - it’s making them compare notes. So I built Council: an open source CLI that runs all three in parallel, surfaces disagreements, and gives you one synthesized recommendation. npx @armstrng/council review this PR

Colin Armstrong

11,735 次观看 • 3 个月前

MOONSHOT JUST MADE A FREE REPLICA OF CLAUDE CODE. It’s called Kimi Code CLI. It’s open source, free to use, and built by the team behind Kimi K3. It comes with features you won’t find in Claude Code: → upload a screen recording as input → built-in coding, planning, and research agents that work in separate contexts → plan your changes before editing any files → set up MCP servers directly from the CLI with /mcp-config → works with VS Code, JetBrains, and Zed → lightweight - no Node.js setup, starts in seconds The CLI is completely free. The Kimi K3 model behind it starts at $3 per million input tokens. Grab it below 👇

MOONSHOT JUST MADE A FREE REPLICA OF CLAUDE CODE. It’s called Kimi Code CLI. It’s open source, free to use, and built by the team behind Kimi K3. It comes with features you won’t find in Claude Code: → upload a screen recording as input → built-in coding, planning, and research agents that work in separate contexts → plan your changes before editing any files → set up MCP servers directly from the CLI with /mcp-config → works with VS Code, JetBrains, and Zed → lightweight - no Node.js setup, starts in seconds The CLI is completely free. The Kimi K3 model behind it starts at $3 per million input tokens. Grab it below 👇

MIKE

45,132 次观看 • 21 天前

Unpopular opinion: Most agent evals are theatre. You run them once before the deployment. It'll take 800ms+ as another LLM would be judging your LLM. Most annoying part - no one tells where in the chain things went wrong. I wasted a lot of time in this loop. And then I came across Future AGI bringing 5 different tools under one umbrella, best part - the platform is completely open source. They open sourced their entire platform and the eval layer is noticeably different. It is multimodal - works on everything text, image, audio, pdf. Not an LLM-as-judge adding latency but an agent with memory and tools. The biggest win are learned classifiers trained on actual production failure patterns to run evals at low cost. It also runs across the full reasoning chain, not just the final response. Check out → Try it here →

Unpopular opinion: Most agent evals are theatre. You run them once before the deployment. It'll take 800ms+ as another LLM would be judging your LLM. Most annoying part - no one tells where in the chain things went wrong. I wasted a lot of time in this loop. And then I came across Future AGI bringing 5 different tools under one umbrella, best part - the platform is completely open source. They open sourced their entire platform and the eval layer is noticeably different. It is multimodal - works on everything text, image, audio, pdf. Not an LLM-as-judge adding latency but an agent with memory and tools. The biggest win are learned classifiers trained on actual production failure patterns to run evals at low cost. It also runs across the full reasoning chain, not just the final response. Check out → Try it here →

Swapna Kumar Panda

50,102 次观看 • 3 个月前

seedance 2.0 + my v2 AI UGC prompting system is giving insane results i spent the last 24 hours generating over 200 seedance 2.0 videos to figure out the best prompting framework system for AI UGC this video was made with 1 prompt and 1 tool, no editing was done to the video this was just a prompt to a video this is by far the best model i've ever used and the craziest part is that it can be fully automated this is the first time we can actually automate high quality ai ugc at this level bytedance owns tiktok so this model is trained on millions of high quality ugc videos. you just need to know how to extract that and call it in your prompt. we are so early... it's insane

seedance 2.0 + my v2 AI UGC prompting system is giving insane results i spent the last 24 hours generating over 200 seedance 2.0 videos to figure out the best prompting framework system for AI UGC this video was made with 1 prompt and 1 tool, no editing was done to the video this was just a prompt to a video this is by far the best model i've ever used and the craziest part is that it can be fully automated this is the first time we can actually automate high quality ai ugc at this level bytedance owns tiktok so this model is trained on millions of high quality ugc videos. you just need to know how to extract that and call it in your prompt. we are so early... it's insane

Miko

81,367 次观看 • 5 个月前

THIS FREE CHINESE AI MODEL RUNS LOCALLY FOREVER AND BUILDS ANYTHING YOU CAN IMAGINE - INCLUDING FULL OPEN WORLD GAMES GLM 5.2 - open, local, free forever - no bills, no limits, no subscription want an open world game with multiplayer - describe it, it builds - want business automation - builds that too - literally anything running 24/7 same as Claude and GPT at $200/month - on your own machine, forever free - saves $2,400/year in subscriptions responds in 2-3 seconds - your computer, your speed, nobody in the queue ahead of you whoever finds out about this today saves thousands and ships a real product before everyone still waiting for the perfect tool

THIS FREE CHINESE AI MODEL RUNS LOCALLY FOREVER AND BUILDS ANYTHING YOU CAN IMAGINE - INCLUDING FULL OPEN WORLD GAMES GLM 5.2 - open, local, free forever - no bills, no limits, no subscription want an open world game with multiplayer - describe it, it builds - want business automation - builds that too - literally anything running 24/7 same as Claude and GPT at $200/month - on your own machine, forever free - saves $2,400/year in subscriptions responds in 2-3 seconds - your computer, your speed, nobody in the queue ahead of you whoever finds out about this today saves thousands and ships a real product before everyone still waiting for the perfect tool

Noisy

23,473 次观看 • 1 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

28,090 次观看 • 22 天前

🚨NEW: TRUMP-BACKED WORLD LIBERTY FINANCIAL LAUNCHES AGENTPAY SDK FOR AI PAYMENTS Donald Trump-backed (Donald J. Trump) World Liberty Financial (WLFI) has introduced a new payment toolkit for AI agents. The AgentPay SDK is open-source and self-hosted. It allows AI systems to hold and transact with USD1 stablecoin. The tool targets secure and autonomous AI-driven payments. The SDK supports major AI development environments. This includes Claude Code, Codex, Cursor, and OpenClaw. Developers can plug payments directly into AI workflows. Transactions are reportedly signed locally for added security.

🚨NEW: TRUMP-BACKED WORLD LIBERTY FINANCIAL LAUNCHES AGENTPAY SDK FOR AI PAYMENTS Donald Trump-backed (Donald J. Trump) World Liberty Financial (WLFI) has introduced a new payment toolkit for AI agents. The AgentPay SDK is open-source and self-hosted. It allows AI systems to hold and transact with USD1 stablecoin. The tool targets secure and autonomous AI-driven payments. The SDK supports major AI development environments. This includes Claude Code, Codex, Cursor, and OpenClaw. Developers can plug payments directly into AI workflows. Transactions are reportedly signed locally for added security.

BSCN

20,922 次观看 • 4 个月前