Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

A Stirling engine burns no fuel inside itself. It runs on nothing but a difference in temperature. The same sealed gas stays inside forever. Heat one end and it expands and pushes a piston, then it gets shuffled to the cool side, contracts and pulls back. Scottish minister Robert... show more

Epic Vault

227,075 subscribers

15,530 görüntüleme • 22 gün önce •via X (Twitter)

Bilim & Teknoloji Eğitim

Anya Rossi• Live Now

Private livecam show

5 Yorum

rodo 27 profil fotoğrafı

rodo 2722 gün önce

The fuel (the oil/gas burning) is outside, so it doesn't change anything.

Nuke profil fotoğrafı

Nuke22 gün önce

Efficient.

Zebadey profil fotoğrafı

Zebadey22 gün önce

Interesting

Денис profil fotoğrafı

Денис21 gün önce

Сложно устроен, и имеет низкий КПД 🤷

Ratio_Disputati profil fotoğrafı

Ratio_Disputati22 gün önce

Fun to watch, but they produce no torque so they aren’t useful.

Benzer Videolar

A computer that needs fire instead of a power outlet Enthusiast built a real steampunk computer that generates electricity from a flame. No batteries or power supply — the fire heats a miniature Stirling engine, which drives a generator to produce electricity. The principle is simple: heated gas inside the engine expands and pushes a piston, then cools and contracts. The cycle repeats, spinning a flywheel that turns the generator. The system produces only about 150 mW, so the computer is extremely energy-efficient. It uses an ESP32-C3, a monochrome 128×64 OLED display and a 16-key keyboard. Wi-Fi and Bluetooth are disabled, and the processor clock speed has been reduced. Yet even that tiny amount of power is enough to run CHIP-8, including games such as Tetris, Snake and Pong. The creator also built in a simple editor that lets users write their own programs directly on the “fire-powered” computer. And the Stirling engine itself is more than two centuries old — Robert Stirling patented it back in 1816. Video: YouTube/PickentCode

A computer that needs fire instead of a power outlet Enthusiast built a real steampunk computer that generates electricity from a flame. No batteries or power supply — the fire heats a miniature Stirling engine, which drives a generator to produce electricity. The principle is simple: heated gas inside the engine expands and pushes a piston, then cools and contracts. The cycle repeats, spinning a flywheel that turns the generator. The system produces only about 150 mW, so the computer is extremely energy-efficient. It uses an ESP32-C3, a monochrome 128×64 OLED display and a 16-key keyboard. Wi-Fi and Bluetooth are disabled, and the processor clock speed has been reduced. Yet even that tiny amount of power is enough to run CHIP-8, including games such as Tetris, Snake and Pong. The creator also built in a simple editor that lets users write their own programs directly on the “fire-powered” computer. And the Stirling engine itself is more than two centuries old — Robert Stirling patented it back in 1816. Video: YouTube/PickentCode

NEXTA

43,825 görüntüleme • 2 ay önce

I've got a single-cylinder Stirling engine that runs on the heat from a ThioJoe coffee cup!

I've got a single-cylinder Stirling engine that runs on the heat from a ThioJoe coffee cup!

Dave W Plummer

21,470 görüntüleme • 8 ay önce

Navajo Stirling describes watching a fighter have a full on mental breakdown in the DWCS locker room Stirling shared the same locker room with Quemuel Ottoni back in 2024 and admits Ottoni ripped off 3 different sets of hand wraps and was crying before bailing on his fight

Navajo Stirling describes watching a fighter have a full on mental breakdown in the DWCS locker room Stirling shared the same locker room with Quemuel Ottoni back in 2024 and admits Ottoni ripped off 3 different sets of hand wraps and was crying before bailing on his fight

FULL SEND MMA

126,684 görüntüleme • 3 ay önce

The future of AI compute doesn't run on hype. It runs on real utility, real burns, and a network that gets stronger every time it's used. The Incentive Dynamic Engine (IDE) is now live!

The future of AI compute doesn't run on hype. It runs on real utility, real burns, and a network that gets stronger every time it's used. The Incentive Dynamic Engine (IDE) is now live!

io.net

9,825,489 görüntüleme • 5 ay önce

A pickle jar can function as a tiny jet engine. The setup is simple: a glass jar with a small hole in the lid holds a volatile fuel like methanol, which evaporates to create a fuel and air mixture inside. A flame brought to the hole ignites it, and the cycle begins. Here is what happens in each pulse. Combustion sends a sharp pressure spike through the jar, forcing hot gas out the lid hole as thrust. The escaping gas creates a brief partial vacuum inside, which pulls fresh air back in through the same hole. Residual heat ignites the new mixture automatically, and the cycle repeats dozens to hundreds of times per second. The jar and hole act as a resonant cavity, which is why it pulses instead of burning steadily. A single opening cannot handle exhaust and intake at the same time, so the system locks into a natural rhythm. It produces almost no real thrust, but it is a clear window into how actual pulsejet engines work, and the physics on display are the same ones used in real aerospace propulsion. Follow for more!

A pickle jar can function as a tiny jet engine. The setup is simple: a glass jar with a small hole in the lid holds a volatile fuel like methanol, which evaporates to create a fuel and air mixture inside. A flame brought to the hole ignites it, and the cycle begins. Here is what happens in each pulse. Combustion sends a sharp pressure spike through the jar, forcing hot gas out the lid hole as thrust. The escaping gas creates a brief partial vacuum inside, which pulls fresh air back in through the same hole. Residual heat ignites the new mixture automatically, and the cycle repeats dozens to hundreds of times per second. The jar and hole act as a resonant cavity, which is why it pulses instead of burning steadily. A single opening cannot handle exhaust and intake at the same time, so the system locks into a natural rhythm. It produces almost no real thrust, but it is a clear window into how actual pulsejet engines work, and the physics on display are the same ones used in real aerospace propulsion. Follow for more!

Mechanical Knowledge

131,156 görüntüleme • 8 ay önce

The Prince and Princess of Wales have tried their hand at curling while on a visit to the Scottish city of Stirling. Read more UK news here:

The Prince and Princess of Wales have tried their hand at curling while on a visit to the Scottish city of Stirling. Read more UK news here:

Sky News

79,537 görüntüleme • 9 ay önce

🚨 JAY LENO JUST PULLED UP IN A CAR THAT RUNS ON PERFUME OR TEQUILA — AND IT SOUNDS LIKE A GIANT VACUUM Jay Leno just rolled up in one of the strangest cars ever built: the 1963 Chrysler Turbine Car, with bodies hand-built by Ghia in Italy. Instead of a normal piston engine, it uses a jet-style turbine. And when it starts up, it doesn’t rumble like a V8. It sounds like a giant vacuum cleaner spooling up. Then Leno shows the part that catches everyone off guard first. He puts a bottle of water on the engine while it’s running… and it barely ripples. Almost no vibration at all while the turbine spins. Then he explains why this car is so bizarre. The engine is designed to run on almost anything that burns: • Diesel • Kerosene • Jet fuel • Heating oil • Cooking oil Leno says when Chrysler took the car to Mexico, they ran it on tequila. When they brought it to France, they filled the tank with Chanel No.5 perfume. Only 9 of these Chrysler Turbine Cars are believed to still exist today. If your car could run on almost anything that burns... what would you try putting in the tank first?

🚨 JAY LENO JUST PULLED UP IN A CAR THAT RUNS ON PERFUME OR TEQUILA — AND IT SOUNDS LIKE A GIANT VACUUM Jay Leno just rolled up in one of the strangest cars ever built: the 1963 Chrysler Turbine Car, with bodies hand-built by Ghia in Italy. Instead of a normal piston engine, it uses a jet-style turbine. And when it starts up, it doesn’t rumble like a V8. It sounds like a giant vacuum cleaner spooling up. Then Leno shows the part that catches everyone off guard first. He puts a bottle of water on the engine while it’s running… and it barely ripples. Almost no vibration at all while the turbine spins. Then he explains why this car is so bizarre. The engine is designed to run on almost anything that burns: • Diesel • Kerosene • Jet fuel • Heating oil • Cooking oil Leno says when Chrysler took the car to Mexico, they ran it on tequila. When they brought it to France, they filled the tank with Chanel No.5 perfume. Only 9 of these Chrysler Turbine Cars are believed to still exist today. If your car could run on almost anything that burns... what would you try putting in the tank first?

HustleBitch

868,631 görüntüleme • 8 ay önce

How much force does it take to move the KARNO piston? About 4,000 pounds, that’s roughly the weight of an elephant. Most people see a piston and think fuel is exploding to push it down. That’s NOT how KARNO works. Inside the system, gas is heated, expands, and applies about 4,000 pounds of force to the piston. That force moves the piston, and that motion produces electricity

How much force does it take to move the KARNO piston? About 4,000 pounds, that’s roughly the weight of an elephant. Most people see a piston and think fuel is exploding to push it down. That’s NOT how KARNO works. Inside the system, gas is heated, expands, and applies about 4,000 pounds of force to the piston. That force moves the piston, and that motion produces electricity

Thomas Healy

16,422 görüntüleme • 5 ay önce

Another example of Xabi Alonso's team rotations. Palmer brings it forward in the RHS, Gusto wide; they rotate Palmer wide and Gusto inverted. Palmer is in a position for a 1v1 take-on, doesn't receive it in a way to go 1v1 and passes back; Acheampong makes an inside dart to the RHS. Central overload with Rogers, Gusto and Josh in and around the same area. Notice Chavarria, instead of pulling wide, stays inside for counterpressing purposes, and Chelsea are applying minimum width, no width on the left. Enzo plays a wonderful through ball, and Josh gets on to it. Robinson didn't know who to mark. Central attacking prioritized.

Another example of Xabi Alonso's team rotations. Palmer brings it forward in the RHS, Gusto wide; they rotate Palmer wide and Gusto inverted. Palmer is in a position for a 1v1 take-on, doesn't receive it in a way to go 1v1 and passes back; Acheampong makes an inside dart to the RHS. Central overload with Rogers, Gusto and Josh in and around the same area. Notice Chavarria, instead of pulling wide, stays inside for counterpressing purposes, and Chelsea are applying minimum width, no width on the left. Enzo plays a wonderful through ball, and Josh gets on to it. Robinson didn't know who to mark. Central attacking prioritized.

Oluwaseun 🇳🇬

35,346 görüntüleme • 2 ay önce

A FLURRY OF PUNCHES GETS THIS ONE DONE! ✅ Navajo Stirling gets back-to-back finishes in the Octagon! [ #UFCVegas119 | LIVE ON @ParamountPlus ]

A FLURRY OF PUNCHES GETS THIS ONE DONE! ✅ Navajo Stirling gets back-to-back finishes in the Octagon! [ #UFCVegas119 | LIVE ON @ParamountPlus ]

UFC on Paramount+

154,053 görüntüleme • 4 ay önce

I'm starting to get scared of my own Claude skill. i keep testing its limits, so today it got one picture of a robot jumping spider. how the skill built it: > the picture only sets the look, all 460 parts are code, down to the glass shins with a piston and a spring inside > the motion is math before anything gets drawn: 8 legs step in 2 sets of 4, it sinks down, then straightens them in 0.12 s to launch > every panel reads that same math, so the gait chart, the servo bars and the jump gauge never disagree > the iris in the 2 big eyes stops down every time it jumps > one click and it blows apart on a turntable, then snaps back together and comes at you again the spider is just one more example of what it can do. the skill and every prompt are in the article 👇

I'm starting to get scared of my own Claude skill. i keep testing its limits, so today it got one picture of a robot jumping spider. how the skill built it: > the picture only sets the look, all 460 parts are code, down to the glass shins with a piston and a spring inside > the motion is math before anything gets drawn: 8 legs step in 2 sets of 4, it sinks down, then straightens them in 0.12 s to launch > every panel reads that same math, so the gait chart, the servo bars and the jump gauge never disagree > the iris in the 2 big eyes stops down every time it jumps > one click and it blows apart on a turntable, then snaps back together and comes at you again the spider is just one more example of what it can do. the skill and every prompt are in the article 👇

Elvar

219,856 görüntüleme • 14 gün önce

This is getting out of hand: Claude Fable 5.2 can now take any gadget apart from one picture and nobody is talking about it. I gave it one picture of a PS5 controller and got back one that splits open part by part in 24 seconds. What made it work is teardown, a free open-source skill for Claude Code (3,000+ stars on GitHub) that makes Claude build the inside first. Why model a controller by hand for a week when Claude can write every part as code? Here is the workflow: from that one picture Claude writes the motion as math before it draws a single part, so every panel reads the same numbers as the model. It renders a still at every beat and fixes what it finds, then records the tour at 60 fps: the touchpad lifts, both sticks come out on their gimbals, the motor and gears behind L2 and R2 slide out and trigger force jumps from 30% to 78% the second push-back switches on. Step-by-step setup: 1. Install teardown with one npx line 2. Open Claude Code and type /teardown 3. Give it one picture of the thing you want to see inside 4. Let it check every still before it films 5. Record the tour and watch it come apart It runs inside Claude Code, so you'll never keyframe a teardown by hand again. The full guide and every prompt are in the article below.

This is getting out of hand: Claude Fable 5.2 can now take any gadget apart from one picture and nobody is talking about it. I gave it one picture of a PS5 controller and got back one that splits open part by part in 24 seconds. What made it work is teardown, a free open-source skill for Claude Code (3,000+ stars on GitHub) that makes Claude build the inside first. Why model a controller by hand for a week when Claude can write every part as code? Here is the workflow: from that one picture Claude writes the motion as math before it draws a single part, so every panel reads the same numbers as the model. It renders a still at every beat and fixes what it finds, then records the tour at 60 fps: the touchpad lifts, both sticks come out on their gimbals, the motor and gears behind L2 and R2 slide out and trigger force jumps from 30% to 78% the second push-back switches on. Step-by-step setup: 1. Install teardown with one npx line 2. Open Claude Code and type /teardown 3. Give it one picture of the thing you want to see inside 4. Let it check every still before it films 5. Record the tour and watch it come apart It runs inside Claude Code, so you'll never keyframe a teardown by hand again. The full guide and every prompt are in the article below.

Nyxera

36,377 görüntüleme • 3 gün önce

a shape with no inside. he filled it with water anyway pour water in and it stops almost immediately. the air has nowhere to escape, so it just sits there blocking you. tilt it and you get a little more in, then it blocks again so he put the whole thing in a vacuum chamber turn it on and the bottle starts bubbling. that's the air being pulled out through the neck, leaving as close to nothing inside as he can get then he lets the pressure back in, and the water rushes up into the empty space on its own still not full. so he runs it again, rarefying the smaller pocket of air that's left, and again after that here's the part that breaks your head: for a shape to have volume, it has to split the world in two. a ball does that. stretch it however you want, there's always a world inside and a world outside a Klein bottle has no such line. follow its surface and you never cross a boundary, never pass through a wall, never end up anywhere that isn't the same side you started on the inside is the outside. so there's nothing there to fill he filled it anyway that's the same shape as the room below. no plot, no payoff, just a question your brain won't drop -> can a thing with no inside hold anything at all two videos, two impossible questions, 20 million views between them. Paone broke down why this format works in the article underneath save this. the most watched thing today was a shape that shouldn't be able to hold anything, holding water

a shape with no inside. he filled it with water anyway pour water in and it stops almost immediately. the air has nowhere to escape, so it just sits there blocking you. tilt it and you get a little more in, then it blocks again so he put the whole thing in a vacuum chamber turn it on and the bottle starts bubbling. that's the air being pulled out through the neck, leaving as close to nothing inside as he can get then he lets the pressure back in, and the water rushes up into the empty space on its own still not full. so he runs it again, rarefying the smaller pocket of air that's left, and again after that here's the part that breaks your head: for a shape to have volume, it has to split the world in two. a ball does that. stretch it however you want, there's always a world inside and a world outside a Klein bottle has no such line. follow its surface and you never cross a boundary, never pass through a wall, never end up anywhere that isn't the same side you started on the inside is the outside. so there's nothing there to fill he filled it anyway that's the same shape as the room below. no plot, no payoff, just a question your brain won't drop -> can a thing with no inside hold anything at all two videos, two impossible questions, 20 million views between them. Paone broke down why this format works in the article underneath save this. the most watched thing today was a shape that shouldn't be able to hold anything, holding water

Banff

2,570,663 görüntüleme • 3 ay önce

This fan runs on kerosene and was widely used between 1890 and 1920. These fans operated not on electricity, but on the principles of the Stirling engine. A kerosene lamp (wick burner) located at the bottom was lit. The heat generated warmed the air inside the engine, causing it to expand and move the piston. The piston’s movement rotated the fan blades, allowing the fan to operate while the internal mechanism cooled the air and sustained the cycle. At the time, electricity networks were not yet widespread, particularly in rural areas and colonial regions, including hot countries such as India and parts of Africa. These fans provided a practical solution where electricity was unavailable. When high-quality kerosene was used, they produced almost no smoke and operated virtually silently. One of the best-known types of these fans was the “Jost Hot Air Fan,” manufactured by the German company Jost. TT @Ancient Hands

This fan runs on kerosene and was widely used between 1890 and 1920. These fans operated not on electricity, but on the principles of the Stirling engine. A kerosene lamp (wick burner) located at the bottom was lit. The heat generated warmed the air inside the engine, causing it to expand and move the piston. The piston’s movement rotated the fan blades, allowing the fan to operate while the internal mechanism cooled the air and sustained the cycle. At the time, electricity networks were not yet widespread, particularly in rural areas and colonial regions, including hot countries such as India and parts of Africa. These fans provided a practical solution where electricity was unavailable. When high-quality kerosene was used, they produced almost no smoke and operated virtually silently. One of the best-known types of these fans was the “Jost Hot Air Fan,” manufactured by the German company Jost. TT @Ancient Hands

vintage.chalabi

45,400 görüntüleme • 1 ay önce

$38 to $6,432 in 22 hours. I didn't touch the bot once. Grok Bot built a terminal that snipes new tokens on Solana and ran it on its own the whole time. no tweaks, no restarts, nothing. x169. 240 trades, 199 green, 83% win rate. it studied the history of 10k+ coins, and now it tells trash from something with a real shot on its own. every new pair runs the same chain, and you can watch it happen line by line in the log: > LP, checks the pool has real liquidity, not painted on > LOCK, checks whether that liquidity is locked and for how many days > DEV, checks how much supply sits on the deployer wallet, too much and the entry's cancelled > BUY, fires only after three greens in a row what actually got me is how much of the run is just the bot saying no. roughly one candidate in five makes it to a buy. the rest drop on step two or three, and it doesn't even spend gas on them. that's the opposite of how most of us snipe. a fresh ticker starts moving and we're in before checking a single thing about it. this thing checks first, every time, in the same order. and when a read does miss, it stays small. 41 red trades, none bigger than $34. $38 to $6,432 isn't one lucky snipe. it's a filter that throws out four tokens for every one it buys.

$38 to $6,432 in 22 hours. I didn't touch the bot once. Grok Bot built a terminal that snipes new tokens on Solana and ran it on its own the whole time. no tweaks, no restarts, nothing. x169. 240 trades, 199 green, 83% win rate. it studied the history of 10k+ coins, and now it tells trash from something with a real shot on its own. every new pair runs the same chain, and you can watch it happen line by line in the log: > LP, checks the pool has real liquidity, not painted on > LOCK, checks whether that liquidity is locked and for how many days > DEV, checks how much supply sits on the deployer wallet, too much and the entry's cancelled > BUY, fires only after three greens in a row what actually got me is how much of the run is just the bot saying no. roughly one candidate in five makes it to a buy. the rest drop on step two or three, and it doesn't even spend gas on them. that's the opposite of how most of us snipe. a fresh ticker starts moving and we're in before checking a single thing about it. this thing checks first, every time, in the same order. and when a read does miss, it stays small. 41 red trades, none bigger than $34. $38 to $6,432 isn't one lucky snipe. it's a filter that throws out four tokens for every one it buys.

boan

61,267 görüntüleme • 1 ay önce

Sapling is live. the final Zcash launchpad on Solana. STAMP proved Zcash can carry a record of a burn. you destroy a token, you get a receipt. we built what it could have been: you burn, you get paid, and then you get the receipt/stamp on Zcash mainnet. every coin planted on Sapling is a coin, paired with $ZEC instead of SOL. same curve, same graduation, same terminals. one difference: every coin has roots. the roots are a vault of ZEC under the coin. every trade feeds it: at least 0.50% of every trade, in ZEC. that floor is written into the program. burn the token on solana in one transaction. your share of the roots comes back in ZEC, in the same transaction. roots × your tokens ÷ supply. no claim, no wait. add a zcash address and a stamp lands on zcash mainnet, cut with exactly what you destroyed and exactly what the roots paid you. one-way, verifiable, and held by nobody but you. a stamp tells the world what you burned. Sapling pays you for it first. Zcash can't hold memecoins yet. it can hold proof. a stamp is a record, not a token. the first one is already on Zcash mainnet: certificate: on Zcash mainnet (transaction): 3edfa6cd1a8e3afbe7604e0c5f167c8b46d20ca1a7a6b56ec11a247fe78d7b04 the rest of the 2%: 0.80% to the deployer, almost 3x what pays. or hand it to your holders: ZEC pushed to every wallet holding $20+. permanent. 0.50% buys $SAPLING and burns it. every coin, every trade. 0.20% keeps the lights on. every fee, split, burn, harvest, payout and stamp sits on with its signature. the vault program went through a full security review before a single coin was planted. check it yourself: vault program (Solana): A9zFnNZpVjBbcE1SAPY92Z6H7WhicysLNPYPpDz15UxF rootstock (buys + burns $SAPLING): 3G6yQGLssh4VTNDaGpLn9CgARSZkXk2xRvfeu4f4SLA9 stamp issuer (Zcash): t1bBCoaVRECAc8Y8E5BRrhDPQ36nt27kX29 stamp rules + verifier: plant a coin. grow it in ZEC.

Sapling is live. the final Zcash launchpad on Solana. STAMP proved Zcash can carry a record of a burn. you destroy a token, you get a receipt. we built what it could have been: you burn, you get paid, and then you get the receipt/stamp on Zcash mainnet. every coin planted on Sapling is a coin, paired with $ZEC instead of SOL. same curve, same graduation, same terminals. one difference: every coin has roots. the roots are a vault of ZEC under the coin. every trade feeds it: at least 0.50% of every trade, in ZEC. that floor is written into the program. burn the token on solana in one transaction. your share of the roots comes back in ZEC, in the same transaction. roots × your tokens ÷ supply. no claim, no wait. add a zcash address and a stamp lands on zcash mainnet, cut with exactly what you destroyed and exactly what the roots paid you. one-way, verifiable, and held by nobody but you. a stamp tells the world what you burned. Sapling pays you for it first. Zcash can't hold memecoins yet. it can hold proof. a stamp is a record, not a token. the first one is already on Zcash mainnet: certificate: on Zcash mainnet (transaction): 3edfa6cd1a8e3afbe7604e0c5f167c8b46d20ca1a7a6b56ec11a247fe78d7b04 the rest of the 2%: 0.80% to the deployer, almost 3x what pays. or hand it to your holders: ZEC pushed to every wallet holding $20+. permanent. 0.50% buys $SAPLING and burns it. every coin, every trade. 0.20% keeps the lights on. every fee, split, burn, harvest, payout and stamp sits on with its signature. the vault program went through a full security review before a single coin was planted. check it yourself: vault program (Solana): A9zFnNZpVjBbcE1SAPY92Z6H7WhicysLNPYPpDz15UxF rootstock (buys + burns $SAPLING): 3G6yQGLssh4VTNDaGpLn9CgARSZkXk2xRvfeu4f4SLA9 stamp issuer (Zcash): t1bBCoaVRECAc8Y8E5BRrhDPQ36nt27kX29 stamp rules + verifier: plant a coin. grow it in ZEC.

Sapling

34,255 görüntüleme • 1 ay önce

This series on the Montreal Canadiens is a look inside the rebuild, tons of access - a really cool view into how the team runs, who runs it and how the Habs intended to Destroy the Leafs - in due time. ;)

This series on the Montreal Canadiens is a look inside the rebuild, tons of access - a really cool view into how the team runs, who runs it and how the Habs intended to Destroy the Leafs - in due time. ;)

George Stroumboulopoulos 🐺

75,840 görüntüleme • 2 yıl önce

Sunset in Stirling, Scotland and it’s absolutely stunning. It’s been a tremendous first day here — more to come on the story — finishing it with a stroll to a hill looking out at Stirling Castle. Now it’s time for bed so I can wake up for Game 7 between the Leafs and Panthers.

Sunset in Stirling, Scotland and it’s absolutely stunning. It’s been a tremendous first day here — more to come on the story — finishing it with a stroll to a hill looking out at Stirling Castle. Now it’s time for bed so I can wake up for Game 7 between the Leafs and Panthers.

Devin Heroux

13,139 görüntüleme • 1 yıl önce

Boris Cherny gave Claude Code a memory that has no database, no indexing, no setup, and 80% of Anthropic runs on it a CLAUDE.md "gets automatically read into context at the start of every session" 12:48 - CLAUDE.md loads into memory every session 13:15 - Keep memory short or it burns your context 15:48 - Memory stacks from you to your whole company 17:30 - The memory command shows what Claude remembers 19:33 - Hit pound and Claude remembers it forever the whole memory layer is files → drop a CLAUDE.md in your repo and Claude reads it in on every session → nest more in subfolders and it pulls them only where it works → stack them personal to project to enterprise so one config serves the whole team → hit the pound key mid task and Claude writes the new fact into memory itself the best coding agent's memory was never a database, it was markdown you can open and edit

Boris Cherny gave Claude Code a memory that has no database, no indexing, no setup, and 80% of Anthropic runs on it a CLAUDE.md "gets automatically read into context at the start of every session" 12:48 - CLAUDE.md loads into memory every session 13:15 - Keep memory short or it burns your context 15:48 - Memory stacks from you to your whole company 17:30 - The memory command shows what Claude remembers 19:33 - Hit pound and Claude remembers it forever the whole memory layer is files → drop a CLAUDE.md in your repo and Claude reads it in on every session → nest more in subfolders and it pulls them only where it works → stack them personal to project to enterprise so one config serves the whole team → hit the pound key mid task and Claude writes the new fact into memory itself the best coding agent's memory was never a database, it was markdown you can open and edit

NO1ennn

13,015 görüntüleme • 3 ay önce

I put the fly brain on a skateboard and turned on dubstep..... It rides in rhythm for a while, even pushes with its back leg on the beat. Then the bass comes in and it starts shaking, falls off and lies next to the board. I did this to it again and I'll do it again.....

I put the fly brain on a skateboard and turned on dubstep..... It rides in rhythm for a while, even pushes with its back leg on the beat. Then the bass comes in and it starts shaking, falls off and lies next to the board. I did this to it again and I'll do it again.....

Alexey Fateev

240,697 görüntüleme • 2 ay önce