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。

Codex survives compaction quite well. Which means for massive refactors or "pass test suite" kind of situations looping can work. I tried it for the MiniJinja port over night and it works. Basically /loop tells pi a) continue until "condition" and b) tweak compaction while loop is active.

Armin Ronacher ⇌

82,032 subscribers

17,362 次观看 • 7 个月前 •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

Did you know Cursor can watch output from terminals and take action? It's very extensible. I used it to make a /loop skill, which wakes the agent up on a schedule. Try "/loop until this PR merges" or "/loop 1h check #infra-logs for anything critical". Should I do /goal next?

Did you know Cursor can watch output from terminals and take action? It's very extensible. I used it to make a /loop skill, which wakes the agent up on a schedule. Try "/loop until this PR merges" or "/loop 1h check #infra-logs for anything critical". Should I do /goal next?

Jediah Katz

30,434 次观看 • 2 个月前

The future of vibecoding is looping. ( my recent app cnvs has done $5.7k in 5 days and was made primarily with design looping ) you can easily break free from ai slop and create designs that feel artisan and worth paying for. im begging you to bookmark this 10 min beginner guide and start setting up loops, it will change everything for you. Timestamps : 0:27 – The ultra-simple looping diagram explained 1:18 – The best loop to start with: the design loop 1:38 – Using Codex + GPT Image Gen for the mockup 3:57 – Handing the mockup to Claude Code 4:45 – Loop starts (screenshot → compare → iterate) 7:31 – Loop finished : reviewing the result

The future of vibecoding is looping. ( my recent app cnvs has done $5.7k in 5 days and was made primarily with design looping ) you can easily break free from ai slop and create designs that feel artisan and worth paying for. im begging you to bookmark this 10 min beginner guide and start setting up loops, it will change everything for you. Timestamps : 0:27 – The ultra-simple looping diagram explained 1:18 – The best loop to start with: the design loop 1:38 – Using Codex + GPT Image Gen for the mockup 3:57 – Handing the mockup to Claude Code 4:45 – Loop starts (screenshot → compare → iterate) 7:31 – Loop finished : reviewing the result

Max Blade

22,493 次观看 • 2 个月前

i'm a little sick of chatgpt giving me obviously broken code i've found a "micro agent" approach to LLM code generation can work much better the LLM first generates a *test*, and then enters a loop where it generates and iterates on the code until the tests pass source below

i'm a little sick of chatgpt giving me obviously broken code i've found a "micro agent" approach to LLM code generation can work much better the LLM first generates a test, and then enters a loop where it generates and iterates on the code until the tests pass source below

Steve (Builder.io)

544,212 次观看 • 2 年前

HOW TO USE AI LOOPS TO RUN YOUR BUSINESS 24/7 A lot has been written about loop engineering for building products. Almost nothing about using loops to run the business itself. That's the bigger idea. A loop is when you give an agent a goal, a way to check its own work, and permission to keep trying until it hits that goal. Build. Verify. Repeat. Stop when the condition is met. Here's what it looks like in practice: 1/SEO loop You're position 30 for a term you want. The loop runs once a month, makes changes, checks where you rank, and keeps pushing until you're on page one. This is running in production right now on Inbox Zero. 2/Ads loop You're spending $100 a day and losing money. The loop tests creative, checks profitability, kills what fails, and keeps going until the account is in the black. 3/Eval loop Your AI feature is only 88% accurate. The loop keeps adjusting the prompt and swapping the model until it passes 90%. 4/LLM visibility loop People search in ChatGPT now, not just Google. Same loop, new scoreboard. Are we the answer or not? The whole thing hinges on one thing: a metric that comes back black and white. Where do I rank? Did it hit profitability? Did the evals pass? Give an agent that scoreboard and it runs for months. Loops used to run for 30 minutes. These run for a year. Take a step, sleep, wake up next month, take another one. You're basically hiring an agency that never sleeps, gets paid in tokens instead of invoices, and undoes its own mistakes when the number goes down. Full episode on The Startup Ideas Podcast (SIP) 🧃 watch

HOW TO USE AI LOOPS TO RUN YOUR BUSINESS 24/7 A lot has been written about loop engineering for building products. Almost nothing about using loops to run the business itself. That's the bigger idea. A loop is when you give an agent a goal, a way to check its own work, and permission to keep trying until it hits that goal. Build. Verify. Repeat. Stop when the condition is met. Here's what it looks like in practice: 1/SEO loop You're position 30 for a term you want. The loop runs once a month, makes changes, checks where you rank, and keeps pushing until you're on page one. This is running in production right now on Inbox Zero. 2/Ads loop You're spending $100 a day and losing money. The loop tests creative, checks profitability, kills what fails, and keeps going until the account is in the black. 3/Eval loop Your AI feature is only 88% accurate. The loop keeps adjusting the prompt and swapping the model until it passes 90%. 4/LLM visibility loop People search in ChatGPT now, not just Google. Same loop, new scoreboard. Are we the answer or not? The whole thing hinges on one thing: a metric that comes back black and white. Where do I rank? Did it hit profitability? Did the evals pass? Give an agent that scoreboard and it runs for months. Loops used to run for 30 minutes. These run for a year. Take a step, sleep, wake up next month, take another one. You're basically hiring an agency that never sleeps, gets paid in tokens instead of invoices, and undoes its own mistakes when the number goes down. Full episode on The Startup Ideas Podcast (SIP) 🧃 watch

GREG ISENBERG

82,960 次观看 • 1 个月前

ChatGPT can write you a thousand trading strategies from one sentence. 999 will quietly bleed your account dry. Every single one of them looks like a winner. One method pulls the real one out. Quant desks have run it for years. It's called loop engineering. It's not a smarter prompt. It's a loop: generate a strategy, test it, score why it failed, feed that back, and run it again until one survives data it has never seen. Man Group runs $150 billion. They built an AI that writes and tests hundreds of strategies a week. And second agent whose only job is to hunt the ones that secretly overfit and kill them before a cent goes live. > describe an idea -> backtest 5 years in 12 seconds > read why it died -> feed that back in > run it again until one survives data it never saw AI can write a thousand strategies. Loop engineering is the only thing that tells you which one was ever real. 89% of retail lost money in 2025. Almost none of it from bad ideas. All of it from trading the first guess and never running it through backtest loop. Horizon just put the whole thing in a chat box, free while the beta's open: You're not losing to smarter traders. You're losing to the ones who opened the tab. Anyone can generate a strategy now. Almost no one runs the loop that proves it. That gap is the whole edge. You'll mean to check it later. Later is a "waitlist closed" page.

ChatGPT can write you a thousand trading strategies from one sentence. 999 will quietly bleed your account dry. Every single one of them looks like a winner. One method pulls the real one out. Quant desks have run it for years. It's called loop engineering. It's not a smarter prompt. It's a loop: generate a strategy, test it, score why it failed, feed that back, and run it again until one survives data it has never seen. Man Group runs $150 billion. They built an AI that writes and tests hundreds of strategies a week. And second agent whose only job is to hunt the ones that secretly overfit and kill them before a cent goes live. > describe an idea -> backtest 5 years in 12 seconds > read why it died -> feed that back in > run it again until one survives data it never saw AI can write a thousand strategies. Loop engineering is the only thing that tells you which one was ever real. 89% of retail lost money in 2025. Almost none of it from bad ideas. All of it from trading the first guess and never running it through backtest loop. Horizon just put the whole thing in a chat box, free while the beta's open: You're not losing to smarter traders. You're losing to the ones who opened the tab. Anyone can generate a strategy now. Almost no one runs the loop that proves it. That gap is the whole edge. You'll mean to check it later. Later is a "waitlist closed" page.

cvxv666

174,585 次观看 • 2 个月前

ANTHROPIC LEAD ENGINEER MAKING $2.3M/YEAR JUST LEAKED A 12-PAGE DOCUMENT - AND GOT FIRED 15 MINUTES AFTER PUBLISHING most developers build loops - but almost every loop breaks in one of five ways, and each failure has a symptom visible from the outside without reading a single line of code > Blind loop - the agent waits for a human to hand it work every morning - automating execution but not discovery > Tangled loop - parallel agents share one directory and overwrite each other parallelism that destroys instead of multiplies > Nodding loop - the agent grades its own work and approves it every time a loop that has never said no to itself is broken > Amnesiac loop - results live only in the context window every morning the system wakes up with no memory of yesterday > Manual loop - no trigger a human presses the button to start it that is not a loop that is a script waiting for a person a real loop finds its own work - remembers what it did has something that can say no never lets two agents touch the same file and fires itself on a timer remove any one of the five - and the loop either breaks or never starts 12 pages that changed how I build agentic systems today

ANTHROPIC LEAD ENGINEER MAKING $2.3M/YEAR JUST LEAKED A 12-PAGE DOCUMENT - AND GOT FIRED 15 MINUTES AFTER PUBLISHING most developers build loops - but almost every loop breaks in one of five ways, and each failure has a symptom visible from the outside without reading a single line of code > Blind loop - the agent waits for a human to hand it work every morning - automating execution but not discovery > Tangled loop - parallel agents share one directory and overwrite each other parallelism that destroys instead of multiplies > Nodding loop - the agent grades its own work and approves it every time a loop that has never said no to itself is broken > Amnesiac loop - results live only in the context window every morning the system wakes up with no memory of yesterday > Manual loop - no trigger a human presses the button to start it that is not a loop that is a script waiting for a person a real loop finds its own work - remembers what it did has something that can say no never lets two agents touch the same file and fires itself on a timer remove any one of the five - and the loop either breaks or never starts 12 pages that changed how I build agentic systems today

Sprytix

153,690 次观看 • 1 个月前

This is not Ai. This is from years ago in Ireland. I saved it on my phone and whenever I feel down and the World is getting to me I watch this on a loop for a mind reset. Works every time. I love the fact there are people out there doing this kind of thing to give others joy. JOY! That is the word. We need more JOY. JOY up your day and watch this on a loop or download it to your phone and do what I do for that JOY refix. Or share this with your friends and give them some JOY. x #joy #bigbird #sesamestreet #love

This is not Ai. This is from years ago in Ireland. I saved it on my phone and whenever I feel down and the World is getting to me I watch this on a loop for a mind reset. Works every time. I love the fact there are people out there doing this kind of thing to give others joy. JOY! That is the word. We need more JOY. JOY up your day and watch this on a loop or download it to your phone and do what I do for that JOY refix. Or share this with your friends and give them some JOY. x #joy #bigbird #sesamestreet #love

Hifi Sean

64,837 次观看 • 4 个月前

I’ve been working on dunk. It’s a terminal diff reviewer where you mark issues inline, then let a coding agent fix them. It started as a fork of hunk, but I stripped it down to the loop I need: review → my comments → agent fixes I’m spending time reviewing code and leaving comments for agents rather than writing code myself. But in most tools, that feedback loop still feels broken. dunk is a simple way to make it work across Claude Code, Codex, Pi, etc.

I’ve been working on dunk. It’s a terminal diff reviewer where you mark issues inline, then let a coding agent fix them. It started as a fork of hunk, but I stripped it down to the loop I need: review → my comments → agent fixes I’m spending time reviewing code and leaving comments for agents rather than writing code myself. But in most tools, that feedback loop still feels broken. dunk is a simple way to make it work across Claude Code, Codex, Pi, etc.

Amir Salihefendić

13,156 次观看 • 3 个月前

This is a fun project Lakedbed, Herdr, Pi, Effect, XState prototyping a looping autonomous agent that monitors issues and clears its own backlog. The project is dogfooding an issue tracker into a durable agent that is building the issue tracker its looping over. It's an imperfect demo and the result isn't polished, but I think there's a lot fo interesting ideas to explore and expand on. The goal here is to demo a stack of tools that have been giving me consistently reliable results. Herdr and Pi make a KILLER combo for building a bespoke custom harness around your work. Lakebed is really nice to work with. Plenty of other opinions in the workshop lol - Pi as the agent harness — a minimal loop you own instead of rent, running GPT-5.5 through a Codex subscription inside a Docker workshop container - Planning before prompting: TLDraw sketches, a grilling session with Matt Pocock's Wayfinder skill, and a VISION.md to act as guardrails for the looping agent - Event sourcing with Effect v4 and Effect Schema, ports-and-adapters so the JSONL issue store can become GitHub Issues or Linear or whatever later - Multi-agent orchestration in herdr: an operator pane and an agent-loop pane, where one Pi session literally types prompts into another (fuckin LOVE this) - Enforcement that actually bites: OxLint with Ultracite, Lefthook hooks, and an agent that tries to eslint-disable its way past a complexity rule before fixing it properly 🤡 - A live issue tracker UI on Lakebed, built by the loop it tracks Workshop repo: The repo has a docker container to fire it up as a sandbox. Chapters: 0:00 Intro: Loopcraft and the workshop setup 2:25 Starting Pi inside the Docker container 4:31 Designing the looping issue resolver 10:16 Choosing XState v5 and Effect v4, prompting the starter 15:17 Why Pi: a minimal harness you own 19:35 Reviewing the generated scaffold 24:53 Architecture summary page with Lakebed 30:43 Matt Pocock skills and the vision.md concept 36:37 Grilling session: defining the vision 46:54 Daemon architecture and spec/ticket skills 55:38 Agent loop pane: one agent prompting another 1:01:22 Watching the build: compaction, tests, lint enforcement 1:07:59 Building the Loopcraft Pi extension and monitor 1:15:32 Lakebed issue tracker UI 1:21:07 Kanban board live: running the loop end to end 1:31:49 Wrap-up: bugs, next steps, takeaways

This is a fun project Lakedbed, Herdr, Pi, Effect, XState prototyping a looping autonomous agent that monitors issues and clears its own backlog. The project is dogfooding an issue tracker into a durable agent that is building the issue tracker its looping over. It's an imperfect demo and the result isn't polished, but I think there's a lot fo interesting ideas to explore and expand on. The goal here is to demo a stack of tools that have been giving me consistently reliable results. Herdr and Pi make a KILLER combo for building a bespoke custom harness around your work. Lakebed is really nice to work with. Plenty of other opinions in the workshop lol - Pi as the agent harness — a minimal loop you own instead of rent, running GPT-5.5 through a Codex subscription inside a Docker workshop container - Planning before prompting: TLDraw sketches, a grilling session with Matt Pocock's Wayfinder skill, and a VISION.md to act as guardrails for the looping agent - Event sourcing with Effect v4 and Effect Schema, ports-and-adapters so the JSONL issue store can become GitHub Issues or Linear or whatever later - Multi-agent orchestration in herdr: an operator pane and an agent-loop pane, where one Pi session literally types prompts into another (fuckin LOVE this) - Enforcement that actually bites: OxLint with Ultracite, Lefthook hooks, and an agent that tries to eslint-disable its way past a complexity rule before fixing it properly 🤡 - A live issue tracker UI on Lakebed, built by the loop it tracks Workshop repo: The repo has a docker container to fire it up as a sandbox. Chapters: 0:00 Intro: Loopcraft and the workshop setup 2:25 Starting Pi inside the Docker container 4:31 Designing the looping issue resolver 10:16 Choosing XState v5 and Effect v4, prompting the starter 15:17 Why Pi: a minimal harness you own 19:35 Reviewing the generated scaffold 24:53 Architecture summary page with Lakebed 30:43 Matt Pocock skills and the vision.md concept 36:37 Grilling session: defining the vision 46:54 Daemon architecture and spec/ticket skills 55:38 Agent loop pane: one agent prompting another 1:01:22 Watching the build: compaction, tests, lint enforcement 1:07:59 Building the Loopcraft Pi extension and monitor 1:15:32 Lakebed issue tracker UI 1:21:07 Kanban board live: running the loop end to end 1:31:49 Wrap-up: bugs, next steps, takeaways

joel ⛈️

15,610 次观看 • 1 个月前

So I created a simple Expo app for remotely connecting to an OpenCode server (running on my mac) so I can remotely control & prompt from my iPad or phone. Not very polished but it works pretty well and its kinda interesting that you can see the feedback loop live.

So I created a simple Expo app for remotely connecting to an OpenCode server (running on my mac) so I can remotely control & prompt from my iPad or phone. Not very polished but it works pretty well and its kinda interesting that you can see the feedback loop live.

ryan vogel

50,706 次观看 • 8 个月前

Former CIA analyst Julia Curlee tells Tim Miller how the Trump White House fired her for being transgender: “I just tried to do the work, and it still wasn’t enough… I just was simply the wrong kind of American to continue working.”

Former CIA analyst Julia Curlee tells Tim Miller how the Trump White House fired her for being transgender: “I just tried to do the work, and it still wasn’t enough… I just was simply the wrong kind of American to continue working.”

The Bulwark

20,850 次观看 • 8 天前

Today, the Companion Pass becomes a reality. This is something I brought forward when I was Minister for Social Protection. It means that anyone over 70 can travel for free on the train or the bus, and they can bring a friend with them for free too!

Today, the Companion Pass becomes a reality. This is something I brought forward when I was Minister for Social Protection. It means that anyone over 70 can travel for free on the train or the bus, and they can bring a friend with them for free too!

Heather Humphreys

16,813 次观看 • 11 个月前

👤: you said “ride or die” is a song that contains an emotion i needed”. what kind of emotion is that? 🦌: the phrase “ride or die” itself basically means “i’ll be with you until the end, i’ll stay with you forever.” for me, that became a really big message. It can be a love song too, but i wrote it for my fans, and in that sense, i think it might have been the message i needed most at that time

👤: you said “ride or die” is a song that contains an emotion i needed”. what kind of emotion is that? 🦌: the phrase “ride or die” itself basically means “i’ll be with you until the end, i’ll stay with you forever.” for me, that became a really big message. It can be a love song too, but i wrote it for my fans, and in that sense, i think it might have been the message i needed most at that time

ev.

45,011 次观看 • 2 个月前

Boris Cherny, the engineer who built Claude Code: "I don't talk to an agent anymore. I talk to a loop" a prompt is one instruction you babysit. a loop is a goal the AI works toward on its own: > it plans > does the work > checks itself > fixes what's weak > and repeats until it's done you step out, the work keeps going that's the shift the best engineers quietly moved to. most people hear a line like that and have no idea what it means in practice this breaks it down without the hype: what a loop actually is, when it's worth building, when it's a money trap, and how to run one yourself today watch his clip, then read the article below

Boris Cherny, the engineer who built Claude Code: "I don't talk to an agent anymore. I talk to a loop" a prompt is one instruction you babysit. a loop is a goal the AI works toward on its own: > it plans > does the work > checks itself > fixes what's weak > and repeats until it's done you step out, the work keeps going that's the shift the best engineers quietly moved to. most people hear a line like that and have no idea what it means in practice this breaks it down without the hype: what a loop actually is, when it's worth building, when it's a money trap, and how to run one yourself today watch his clip, then read the article below

Dep

20,917 次观看 • 2 个月前

While watching Porridge last night, which I would happily watch on a loop for all time and adore almost as much as my family, I realised that I very rarely post clips of it. And so here we are. This is from an episode from the second series called Happy Release. Good day.

While watching Porridge last night, which I would happily watch on a loop for all time and adore almost as much as my family, I realised that I very rarely post clips of it. And so here we are. This is from an episode from the second series called Happy Release. Good day.

James Hogg

157,488 次观看 • 1 年前

Jane Street spent $6 billion and 4,032 GPUs on one thing: AI agents that loop through trading strategies 100x faster than any human. Generate, backtest, kill, repeat - thousands a week, until one survives data it's never seen. That loop is why they made $39.6 billion last year while 89% of retail went broke trading one idea they never stress-tested. The edge was never a smarter idea. It was volume. They test 100 strategies for every 1 you test by hand, and a second agent kills the 97 that only look good on old data before a dollar goes live. Now the entire loop fits in a chat box. Horizon takes one plain-English sentence and spins up the same two agents. One builds your strategy, one tries to kill it - backtests 5 years in seconds, and only what survives goes live on your exchange. The $150 billion setup. Free while beta open. Bookmark this & read the full breakdown below - the exact two-agent loop, step by step, and who just handed it to retail.

Jane Street spent $6 billion and 4,032 GPUs on one thing: AI agents that loop through trading strategies 100x faster than any human. Generate, backtest, kill, repeat - thousands a week, until one survives data it's never seen. That loop is why they made $39.6 billion last year while 89% of retail went broke trading one idea they never stress-tested. The edge was never a smarter idea. It was volume. They test 100 strategies for every 1 you test by hand, and a second agent kills the 97 that only look good on old data before a dollar goes live. Now the entire loop fits in a chat box. Horizon takes one plain-English sentence and spins up the same two agents. One builds your strategy, one tries to kill it - backtests 5 years in seconds, and only what survives goes live on your exchange. The $150 billion setup. Free while beta open. Bookmark this & read the full breakdown below - the exact two-agent loop, step by step, and who just handed it to retail.

cvxv666

317,554 次观看 • 1 个月前

After creating Remodex: Codex remote control for iOS I decided to chill a bit by building a browser sidebar inside Theo - t3.gg 's T3 Code You can open it with Cmd+Shift+B This software is so easy to "manipulate" and build upon Congrats to all the guys that put the work in it because it is great I certainly will be building more things with it For this one I decided to switch from the Codex App to the Codex CLI too just to see how it works And boy it was so good

After creating Remodex: Codex remote control for iOS I decided to chill a bit by building a browser sidebar inside Theo - t3.gg 's T3 Code You can open it with Cmd+Shift+B This software is so easy to "manipulate" and build upon Congrats to all the guys that put the work in it because it is great I certainly will be building more things with it For this one I decided to switch from the Codex App to the Codex CLI too just to see how it works And boy it was so good

Emanuele Di Pietro

38,905 次观看 • 5 个月前

Boris Cherny runs Claude Code at Anthropic. His line should stop you mid-scroll: "I don't prompt Claude anymore. I have loops running that prompt Claude and figure out what to do. My job is to write loops." The skill moved. From writing prompts to building the loop around them. A loop that works has three things. Drop one and it burns money in circles. 1. A finish line it can prove. Tests pass or they fail. "Looks done" is not a finish line. 2. A checker that did not write the code. A model grading itself always says yes. 3. Brakes set before you start. A step limit. A money ceiling. A stop condition. That is the whole game. The loop does the work. You design the cage it runs in. Full breakdown below.

Boris Cherny runs Claude Code at Anthropic. His line should stop you mid-scroll: "I don't prompt Claude anymore. I have loops running that prompt Claude and figure out what to do. My job is to write loops." The skill moved. From writing prompts to building the loop around them. A loop that works has three things. Drop one and it burns money in circles. 1. A finish line it can prove. Tests pass or they fail. "Looks done" is not a finish line. 2. A checker that did not write the code. A model grading itself always says yes. 3. Brakes set before you start. A step limit. A money ceiling. A stop condition. That is the whole game. The loop does the work. You design the cage it runs in. Full breakdown below.

shmidt

16,085 次观看 • 2 个月前

sharing a pretty important primitive in my agentic engineering setup I call it "gnhf" - good night, have fun basically, every night before I go to bed, I would put my agents to work so I never wake up "empty-handed". it's done through a similar setup as geoff's famous ralph loop and Andrej Karpathy's autoresearch i just open sourced my solution as a tool at - it's a dead-simple orchestrator that can run claude code, codex, opencode and rovo dev it's particularly effective when you give a measurable goal for the agents to work towards. the agent will deterministically attempt at it, make incremental progress, keep successful results and discard failed ones - rinse and repeat until you wake up (or it reaches the caps you set) i previously ran this with a bunch of scripts but finally got time to package it as a tool - pretty fresh so will likely have rough edges, but feel free to give it a try! good night, have fun!

sharing a pretty important primitive in my agentic engineering setup I call it "gnhf" - good night, have fun basically, every night before I go to bed, I would put my agents to work so I never wake up "empty-handed". it's done through a similar setup as geoff's famous ralph loop and Andrej Karpathy's autoresearch i just open sourced my solution as a tool at - it's a dead-simple orchestrator that can run claude code, codex, opencode and rovo dev it's particularly effective when you give a measurable goal for the agents to work towards. the agent will deterministically attempt at it, make incremental progress, keep successful results and discard failed ones - rinse and repeat until you wake up (or it reaches the caps you set) i previously ran this with a bunch of scripts but finally got time to package it as a tool - pretty fresh so will likely have rough edges, but feel free to give it a try! good night, have fun!

Kun Chen

59,814 次观看 • 4 个月前

AI Art. I realize not all AI Art tools work the same way. Part of the problem is that we don’t quite understand “how” it works, and until we have a better understanding, some pause for concern is good imo. 1/3

AI Art. I realize not all AI Art tools work the same way. Part of the problem is that we don’t quite understand “how” it works, and until we have a better understanding, some pause for concern is good imo. 1/3

Watch It Played

23,161 次观看 • 2 年前