Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Can you solve these agentic AI math problems by hand ✍️? Getting a bit harder now. Download PDF: Problems 11 to 15: 11. Comparing three calls: same total tokens, three different bills 12. The average call: size a sample, then scale it to the day 13. The system prompt:... show more

Tom Yeh

65,651 subscribers

41,898 views • 2 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

5 Comments

Harley Lewis Foote2 months ago

problem 11 is the whole agent economy in one question: same tokens, three different bills

Polash Khan2 months ago

This looks like a fun challenge! Let me see if I can tackle these.

Harley Lewis Foote2 months ago

These problems sit right on the frontier's teeth. Combinatorial reasoning with token-count constraints is where capability drops off non-monotonically. The jaggedness repeats even inside math, so 'harder now' might mean 'different failure mode entirely'.

Renat Lotfullin2 months ago

Any chance graph model by hand in future?

Waleed Rafi Abbasi2 months ago

Based on profit or loss

Related Videos

New chapter! Context problems. Who can solve these by hand ✍️? Download PDF: The first five: 1. Mark the context: the window as cells you can count 2. What fills the window: the system prompt, the user, the model's reply 3. Turn by turn: every turn is the same block, and most of it is the reply 4. Will it fit? Number a new message into what's left, and see it run out 5. Turns until full: how many rounds before there is no room Previously, I shared Chapter 1: Token Problems 1 ~ 20 Why am I designing these math problems? AI is making people (including me) think less. It's just too easy to ask AI a few questions about a new concept and start to believe I get it. We used to practice on a coding problem, but now AI writes the code, and solving it technically is not the same as knowing anything. So I recast each concept as a simple math problem you have to work with pen and paper. Using our hands is one way to motivate ourselves to start thinking again. ✍️ If you solve them by hand, leave a comment to let me know. I will give you a shout out in my next post. Download, print, solve, and learn. ✍️ ~ Prof. Tom Yeh

New chapter! Context problems. Who can solve these by hand ✍️? Download PDF: The first five: 1. Mark the context: the window as cells you can count 2. What fills the window: the system prompt, the user, the model's reply 3. Turn by turn: every turn is the same block, and most of it is the reply 4. Will it fit? Number a new message into what's left, and see it run out 5. Turns until full: how many rounds before there is no room Previously, I shared Chapter 1: Token Problems 1 ~ 20 Why am I designing these math problems? AI is making people (including me) think less. It's just too easy to ask AI a few questions about a new concept and start to believe I get it. We used to practice on a coding problem, but now AI writes the code, and solving it technically is not the same as knowing anything. So I recast each concept as a simple math problem you have to work with pen and paper. Using our hands is one way to motivate ourselves to start thinking again. ✍️ If you solve them by hand, leave a comment to let me know. I will give you a shout out in my next post. Download, print, solve, and learn. ✍️ ~ Prof. Tom Yeh

Tom Yeh

11,651 views • 2 months ago

Can you solve these 20 agentic AI problems? Download this problem set I designed 👉

Can you solve these 20 agentic AI problems? Download this problem set I designed 👉

Tom Yeh

20,543 views • 10 months ago

Can you follow the math of a Transformer model by hand ✍️? Download PDF 👉 I hope this hand-drawn animation makes it easier. p.s., This has one error. Can you can spot it and tell me in the comment?

Can you follow the math of a Transformer model by hand ✍️? Download PDF 👉 I hope this hand-drawn animation makes it easier. p.s., This has one error. Can you can spot it and tell me in the comment?

Tom Yeh

14,578 views • 1 year ago

Grok is quietly turning into an agentic OS. Agents are processes you give custom system prompts to. Connectors are the system services that plug it into Gmail, GitHub, Notion, and whatever else you wire in. Skills are executables that fire from prompts, call connectors, and call other skills. Four built in the video. Grok Imagine Cinematic. Single video idea in, multi-scene prompt set out, ready to drop into Grok Imagine Agent mode. YouTube to cheat sheet. Lecture link in, polished LaTeX PDF out. Under the hood it calls a LaTeX specialist skill and a graph generator skill. Keep each one atomic. Treat Grok Skills like Unix tools.

Grok is quietly turning into an agentic OS. Agents are processes you give custom system prompts to. Connectors are the system services that plug it into Gmail, GitHub, Notion, and whatever else you wire in. Skills are executables that fire from prompts, call connectors, and call other skills. Four built in the video. Grok Imagine Cinematic. Single video idea in, multi-scene prompt set out, ready to drop into Grok Imagine Agent mode. YouTube to cheat sheet. Lecture link in, polished LaTeX PDF out. Under the hood it calls a LaTeX specialist skill and a graph generator skill. Keep each one atomic. Treat Grok Skills like Unix tools.

tetsuo

123,795 views • 5 months ago

Caitlin told the ref to call the first foul then hit a fuck you three lmfaooo

Caitlin told the ref to call the first foul then hit a fuck you three lmfaooo

correlation

3,164,645 views • 5 months ago

God doesn’t call the solar system a masterpiece. He doesn’t call the magnificent sunset a masterpiece. He calls you a masterpiece. Now the question is what are you calling yourself? Tune into Joel’s message today! "Recognize Who You Are":

God doesn’t call the solar system a masterpiece. He doesn’t call the magnificent sunset a masterpiece. He calls you a masterpiece. Now the question is what are you calling yourself? Tune into Joel’s message today! "Recognize Who You Are":

Joel Osteen

185,143 views • 3 years ago

Democrat Socialist Melat Kiros: "Every single issue that I looked at…we already figured out the solution a long time ago." "You solve homelessness by giving people housing." "You solve hunger by giving people food." "You solve health care by going to a single payer system." “It is common sense, right?" These are the people about to occupy seats in the US congress.

Democrat Socialist Melat Kiros: "Every single issue that I looked at…we already figured out the solution a long time ago." "You solve homelessness by giving people housing." "You solve hunger by giving people food." "You solve health care by going to a single payer system." “It is common sense, right?" These are the people about to occupy seats in the US congress.

Western Lensman

371,182 views • 3 months ago

ONE PROMPT AND ONE BUTTON NOW BUILDS A FULL SYSTEM, DATABASE, BACKEND, AND FRONTEND INCLUDED Most people still picture AI as something you ask questions to, then copy the answer into your own code by hand. A builder wired Claude into Obsidian through MCP instead, so a single written prompt becomes the actual spec for the system. Claude breaks that prompt into database schema, UI components, and API endpoints on its own, then writes, runs, and fixes the code until it actually works. MCP is what makes this possible, it lets the agent see the filesystem, installed packages, and running services before it starts building anything. The output isn't a code snippet sitting in a chat window, it's a live local app running on its own server, ready to open in a browser. What used to need a backend developer, a DevOps engineer, and two weeks now finishes in under fifteen minutes. See the full architecture and prompt structure below👇

ONE PROMPT AND ONE BUTTON NOW BUILDS A FULL SYSTEM, DATABASE, BACKEND, AND FRONTEND INCLUDED Most people still picture AI as something you ask questions to, then copy the answer into your own code by hand. A builder wired Claude into Obsidian through MCP instead, so a single written prompt becomes the actual spec for the system. Claude breaks that prompt into database schema, UI components, and API endpoints on its own, then writes, runs, and fixes the code until it actually works. MCP is what makes this possible, it lets the agent see the filesystem, installed packages, and running services before it starts building anything. The output isn't a code snippet sitting in a chat window, it's a live local app running on its own server, ready to open in a browser. What used to need a backend developer, a DevOps engineer, and two weeks now finishes in under fifteen minutes. See the full architecture and prompt structure below👇

wast3

20,348 views • 3 months ago

1. AI Call Assistant - Call Screen It will silently answer calls from unknown numbers with a more natural-sounding voice to engage the caller. It’s also smart enough to separate the calls you want from the calls you don’t. (turn on sound)

1. AI Call Assistant - Call Screen It will silently answer calls from unknown numbers with a more natural-sounding voice to engage the caller. It’s also smart enough to separate the calls you want from the calls you don’t. (turn on sound)

Roni Rahman

89,325 views • 3 years ago

The grave calls you everyday, prepare to answer the call one day....

The grave calls you everyday, prepare to answer the call one day....

Salahu

11,345 views • 1 year ago

Redis built a cache that cuts LLM costs by 90%! Production LLM apps do not receive completely new questions every time. A customer-support assistant might receive all three of these: - "Can I get a refund after buying the monthly plan?" - "Is the monthly subscription refundable?" - "Can I cancel the plan and get my money back?" The wording is different, but the underlying question and its answer remain the same. Yet LLM apps process every version as a new request. They assemble the prompt, send it to the model, and generate an answer that may have already been generated. Prefix caching reduces part of these repeated calls. When requests begin with the same system prompt or context, the model can reuse the KV states already computed for that shared prefix. But the request still hits the LLM. The new tokens must be processed, and the complete answer must still be decoded. So even with a prefix-cache hit, there's another generation call involved. To solve this, instead of only caching computation inside the model, the application can cache the generated response outside it. When another question arrives, the system embeds it and compares it with previously answered questions. If it finds a sufficiently close match, it returns the stored response without invoking the LLM again. A cache hit removes the input tokens, output tokens, and decoding time associated with another LLM call. In practice, it is important to decide which questions can safely share an answer since a production setup needs well-tuned similarity thresholds, expiration policies, data isolation, and monitoring for incorrect matches. If you want to use this in practice, Redis already implements it as a managed service called Redis LangCache. Under the hood, it generates embeddings, searches previous responses, and returns a matching answer before another model call occurs. Redis also handles access scopes, custom filtering, TTL and eviction controls, and cache monitoring through Redis Cloud. I built an interface to compare it against direct LLM inference. The video below shows this in action, and I worked with Redis on this post to put this together. For the paraphrased question in my run, direct inference took 2.232 seconds and consumed 514 input tokens plus 250 output tokens. Redis returned the earlier response in 0.37 seconds with zero LLM input or output tokens. That was roughly 6x faster in this run. Redis reports API cost savings of up to 90% and cache-hit responses up to 15x faster. The actual result depends on how much safe repetition exists in the workload. You can try Redis LangCache here: If you want to dive deeper, I have already written a detailed breakdown of KV, prefix, prompt, and semantic caching in the article quoted below. This demo builds on the final technique and shows it running in practice. Read it below.

Redis built a cache that cuts LLM costs by 90%! Production LLM apps do not receive completely new questions every time. A customer-support assistant might receive all three of these: - "Can I get a refund after buying the monthly plan?" - "Is the monthly subscription refundable?" - "Can I cancel the plan and get my money back?" The wording is different, but the underlying question and its answer remain the same. Yet LLM apps process every version as a new request. They assemble the prompt, send it to the model, and generate an answer that may have already been generated. Prefix caching reduces part of these repeated calls. When requests begin with the same system prompt or context, the model can reuse the KV states already computed for that shared prefix. But the request still hits the LLM. The new tokens must be processed, and the complete answer must still be decoded. So even with a prefix-cache hit, there's another generation call involved. To solve this, instead of only caching computation inside the model, the application can cache the generated response outside it. When another question arrives, the system embeds it and compares it with previously answered questions. If it finds a sufficiently close match, it returns the stored response without invoking the LLM again. A cache hit removes the input tokens, output tokens, and decoding time associated with another LLM call. In practice, it is important to decide which questions can safely share an answer since a production setup needs well-tuned similarity thresholds, expiration policies, data isolation, and monitoring for incorrect matches. If you want to use this in practice, Redis already implements it as a managed service called Redis LangCache. Under the hood, it generates embeddings, searches previous responses, and returns a matching answer before another model call occurs. Redis also handles access scopes, custom filtering, TTL and eviction controls, and cache monitoring through Redis Cloud. I built an interface to compare it against direct LLM inference. The video below shows this in action, and I worked with Redis on this post to put this together. For the paraphrased question in my run, direct inference took 2.232 seconds and consumed 514 input tokens plus 250 output tokens. Redis returned the earlier response in 0.37 seconds with zero LLM input or output tokens. That was roughly 6x faster in this run. Redis reports API cost savings of up to 90% and cache-hit responses up to 15x faster. The actual result depends on how much safe repetition exists in the workload. You can try Redis LangCache here: If you want to dive deeper, I have already written a detailed breakdown of KV, prefix, prompt, and semantic caching in the article quoted below. This demo builds on the final technique and shows it running in practice. Read it below.

Avi Chawla

166,230 views • 1 month ago

What are your thoughts on Chris Christie's words to Trump supporters in Florida? Does he have a point? “Now look, every one of those boos, everyone one of those cat calls, everyone one of those yells will not … solve one problem we face in this country. Your anger against the truth is reprehensible.” “When you think about the problems that our country and this world is facing, when you think about that, this type of pettiness … is beneath … the process of electing a president.” “The problem is … you fear the truth. You want to shout down any voice that says anything different than what you want to hear. And you can continue to do it. And believe me … it doesn’t bother me one bit.”

What are your thoughts on Chris Christie's words to Trump supporters in Florida? Does he have a point? “Now look, every one of those boos, everyone one of those cat calls, everyone one of those yells will not … solve one problem we face in this country. Your anger against the truth is reprehensible.” “When you think about the problems that our country and this world is facing, when you think about that, this type of pettiness … is beneath … the process of electing a president.” “The problem is … you fear the truth. You want to shout down any voice that says anything different than what you want to hear. And you can continue to do it. And believe me … it doesn’t bother me one bit.”

Ed Krassenstein

3,125,745 views • 3 years ago

Everything starts with something simple. A prompt. But the prompt is only the beginning. CreoPlay AI is built to take an idea further, helping turn a prompt into something you can play, test, and keep refining. Different ideas. Different games. The same starting point. Describe what you want to create, then build from there. This is the direction we are building toward with CreoPlay AI. From prompt to playable!

Everything starts with something simple. A prompt. But the prompt is only the beginning. CreoPlay AI is built to take an idea further, helping turn a prompt into something you can play, test, and keep refining. Different ideas. Different games. The same starting point. Describe what you want to create, then build from there. This is the direction we are building toward with CreoPlay AI. From prompt to playable!

Creo Engine

11,112 views • 1 month ago

Harness vs. Graphs, clearly explained! a harness is great, and most people think it is the whole thing: retries, timeouts, a sandbox, a log, the context it assembles before every call. all of that is real work, and all of it wraps exactly one call. run it a hundred times and you have one call, made very safely, a hundred times. Graph engineering fixes this by moving the decision up a layer: not how safely one call is made, but which calls exist to be made at all. you need both, and here is the sentence that resolves the whole confusion: the harness is everything around one call. the graph is everything between them. ↳ around one call: retry, timeout, sandbox, log, assemble the context, hand back a result ↳ between calls: split, fan out, merge, gate, send back Prompts → Context → Harness → Loops → Graphs the harness does not go away when you build a graph. it moves under each node, and now there are five of them, each wrapping a call you would never have made by hand. the trick is knowing which layer a failure belongs to. turn a piece off and run it again. if the call still works, it was the harness. if the wrong step runs at all, it was the graph. people spend weeks hardening a harness around a node that should not have existed. one thing to know before you scale it. most of what people call their agent is a harness with a chat box on it. ↳ it retries, it times out, it logs, it assembles context, it holds one call up beautifully ↳ it has never once decided that a second call should exist, and that is the entire difference that last one catches careful people. a harness that never fails is not evidence the system is right. it is evidence one call went well, which is the smallest possible claim. and the one that eats whole nights: a harness cannot save you from the wrong step running. you can retry a bad decision three times with a clean log and perfect isolation, and all you bought was three copies of it. below i have quoted my full guide on graph engineering. it covers the three topologies, the verifier patterns, and where the gate should actually open. save this and read it below ↓

Harness vs. Graphs, clearly explained! a harness is great, and most people think it is the whole thing: retries, timeouts, a sandbox, a log, the context it assembles before every call. all of that is real work, and all of it wraps exactly one call. run it a hundred times and you have one call, made very safely, a hundred times. Graph engineering fixes this by moving the decision up a layer: not how safely one call is made, but which calls exist to be made at all. you need both, and here is the sentence that resolves the whole confusion: the harness is everything around one call. the graph is everything between them. ↳ around one call: retry, timeout, sandbox, log, assemble the context, hand back a result ↳ between calls: split, fan out, merge, gate, send back Prompts → Context → Harness → Loops → Graphs the harness does not go away when you build a graph. it moves under each node, and now there are five of them, each wrapping a call you would never have made by hand. the trick is knowing which layer a failure belongs to. turn a piece off and run it again. if the call still works, it was the harness. if the wrong step runs at all, it was the graph. people spend weeks hardening a harness around a node that should not have existed. one thing to know before you scale it. most of what people call their agent is a harness with a chat box on it. ↳ it retries, it times out, it logs, it assembles context, it holds one call up beautifully ↳ it has never once decided that a second call should exist, and that is the entire difference that last one catches careful people. a harness that never fails is not evidence the system is right. it is evidence one call went well, which is the smallest possible claim. and the one that eats whole nights: a harness cannot save you from the wrong step running. you can retry a bad decision three times with a clean log and perfect isolation, and all you bought was three copies of it. below i have quoted my full guide on graph engineering. it covers the three topologies, the verifier patterns, and where the gate should actually open. save this and read it below ↓

Hanako

51,717 views • 1 month ago

🚨200 GALLERY TOKENS IN UNDER A MINUTE🚨 These are the easiest gallery tokens you can achieve✅ However as always it comes at a tax cost. The best thing you can do is aim to snipe the players but it might take a bit more time⏰ #eafc #fc27 #futgallery

🚨200 GALLERY TOKENS IN UNDER A MINUTE🚨 These are the easiest gallery tokens you can achieve✅ However as always it comes at a tax cost. The best thing you can do is aim to snipe the players but it might take a bit more time⏰ #eafc #fc27 #futgallery

ProRecoil

144,417 views • 1 month ago

A top hedge fund never hands its analysts a single number. Here's what they hand over instead: Aakarsh Ramchandi (ex-Third Point, now RavenPack) explains: "You can always give a point estimate. Point estimates don't matter." "What matters is the confidence interval — can you measure the error of that estimate well?" "High-frequency data comes in weekly. The single source of truth only lands at quarter-end." "Can you build a system that defines a better confidence interval from that gap? That's the much harder problem." "So you hand over three things: a directional sign, a point estimate, and a confidence range. Then the analyst makes the call."

A top hedge fund never hands its analysts a single number. Here's what they hand over instead: Aakarsh Ramchandi (ex-Third Point, now RavenPack) explains: "You can always give a point estimate. Point estimates don't matter." "What matters is the confidence interval — can you measure the error of that estimate well?" "High-frequency data comes in weekly. The single source of truth only lands at quarter-end." "Can you build a system that defines a better confidence interval from that gap? That's the much harder problem." "So you hand over three things: a directional sign, a point estimate, and a confidence range. Then the analyst makes the call."

Ethan Kho

42,763 views • 4 months ago

Ever received a suspicious call with automated instructions? It could be a fake IVR scam! Learn how to spot the red flags and avoid getting scammed. Report suspicious calls to 1930. Watch the full video now! #WeServeWeProtect

Ever received a suspicious call with automated instructions? It could be a fake IVR scam! Learn how to spot the red flags and avoid getting scammed. Report suspicious calls to 1930. Watch the full video now! #WeServeWeProtect

ಬೆಂಗಳೂರು ನಗರ ಪೊಲೀಸ್‌ BengaluruCityPolice

31,957 views • 1 year ago

A 19 year old gets on Zoom calls with business owners and shows them how they're about to throw away $600,000. He opens with one question. How much are you paying your receptionist? The dental office owner says $60,000. The kid says: over the next 10 years that's $600,000 going to someone who calls in sick, takes lunch breaks and goes home at 5. For a job a machine can do for $12,000 once. Then the second question. How many calls do you miss every day? Voicemails nobody calls back. People who hang up after three rings. New patients who try once and never try again. The owner stops. Pulls up his phone log. Counts. 8 missed calls a day. Sometimes more. Each one is a $200 patient walking past the front desk while it's empty for lunch. $1,600 a day. Almost $600,000 a year in revenue he never knew was leaving. That number sits on top of the $600,000 in salary. The owner is staring at a chart he never let himself draw before. That's when the kid says it. I can build you something for $12,000. Picks up every call. Doesn't sleep. Doesn't take vacation. Books patients while you're operating on someone else. Pays for itself in the first week. The $12,000 invoice doesn't feel like an expense. It feels like a refund. The kid closes 3 to 4 of these calls a month. $50,000 in revenue. He's 19. Behind the scenes he's not building anything from scratch. He's running Kimi K2.6 with 300 parallel sub agents, paying $0.60 per million tokens instead of $5 with Claude. The same reception agent a real developer would charge $40,000 to build, he ships in 30 minutes. 12 hour autonomous sessions. Zero human involvement. One prompt and the agent goes live. Answering calls. Booking patients. Routing emergencies. Before the owner finishes his coffee. His friends are working summer shifts at coffee shops for $14 an hour. He's making $600,000 a year by walking into a Zoom call and naming the most uncomfortable number a business owner has on his books. His secret isn't technology. He never argues with the owner about whether AI works. He hands the owner a calculator and asks the questions the owner has been avoiding for years. By minute 8 the owner has done the math himself. By minute 12 the kid quotes the price. By minute 15 the contract is signed. He told his dad about it once. His dad is an insurance salesman. 30 years selling the same product to every client for the same reason: fear of losing what they already have. His dad listened. Then said: you sell the same thing I sell. You just call it AI. The kid said: I don't even call it that. I let them call it whatever they want. His dad smiled. Walked out of the room. The kid had another call in 10 minutes.

A 19 year old gets on Zoom calls with business owners and shows them how they're about to throw away $600,000. He opens with one question. How much are you paying your receptionist? The dental office owner says $60,000. The kid says: over the next 10 years that's $600,000 going to someone who calls in sick, takes lunch breaks and goes home at 5. For a job a machine can do for $12,000 once. Then the second question. How many calls do you miss every day? Voicemails nobody calls back. People who hang up after three rings. New patients who try once and never try again. The owner stops. Pulls up his phone log. Counts. 8 missed calls a day. Sometimes more. Each one is a $200 patient walking past the front desk while it's empty for lunch. $1,600 a day. Almost $600,000 a year in revenue he never knew was leaving. That number sits on top of the $600,000 in salary. The owner is staring at a chart he never let himself draw before. That's when the kid says it. I can build you something for $12,000. Picks up every call. Doesn't sleep. Doesn't take vacation. Books patients while you're operating on someone else. Pays for itself in the first week. The $12,000 invoice doesn't feel like an expense. It feels like a refund. The kid closes 3 to 4 of these calls a month. $50,000 in revenue. He's 19. Behind the scenes he's not building anything from scratch. He's running Kimi K2.6 with 300 parallel sub agents, paying $0.60 per million tokens instead of $5 with Claude. The same reception agent a real developer would charge $40,000 to build, he ships in 30 minutes. 12 hour autonomous sessions. Zero human involvement. One prompt and the agent goes live. Answering calls. Booking patients. Routing emergencies. Before the owner finishes his coffee. His friends are working summer shifts at coffee shops for $14 an hour. He's making $600,000 a year by walking into a Zoom call and naming the most uncomfortable number a business owner has on his books. His secret isn't technology. He never argues with the owner about whether AI works. He hands the owner a calculator and asks the questions the owner has been avoiding for years. By minute 8 the owner has done the math himself. By minute 12 the kid quotes the price. By minute 15 the contract is signed. He told his dad about it once. His dad is an insurance salesman. 30 years selling the same product to every client for the same reason: fear of losing what they already have. His dad listened. Then said: you sell the same thing I sell. You just call it AI. The kid said: I don't even call it that. I let them call it whatever they want. His dad smiled. Walked out of the room. The kid had another call in 10 minutes.

Marlow

295,813 views • 5 months ago

Aden Duale: Respectfully, you cannot call a minister a liar. You can call me a liar, you can call me a bulldozer, you can call me anything, but we will not pay the rejected 11 billion. We are going to publish all these people who wanted to get the 11 billion fraudulent rejected claims #JKLive

Aden Duale: Respectfully, you cannot call a minister a liar. You can call me a liar, you can call me a bulldozer, you can call me anything, but we will not pay the rejected 11 billion. We are going to publish all these people who wanted to get the 11 billion fraudulent rejected claims #JKLive

Citizen TV Kenya

84,295 views • 9 months ago

When someone crosses the line and bothers you in a store, your best choices are to walk away, find a worker, or call the police. But we know this guy was not going to call the police, find a coworker, or walk away. Violence is never a way to solve problems, but what would you do if someone stuck a horn in your ear several times?

When someone crosses the line and bothers you in a store, your best choices are to walk away, find a worker, or call the police. But we know this guy was not going to call the police, find a coworker, or walk away. Violence is never a way to solve problems, but what would you do if someone stuck a horn in your ear several times?

Gitmo (Health is a Wealth) 🇺🇸🇮🇱

364,901 views • 2 months ago