st1ne

@SolSt1ne • 5,520 subscribers

- Crypto Degen - DM Open Github: st1ne

Shorts

An Anthropic engineer watched my screen from the next table at a cafe in SF. "Are you running Claude against live prediction markets right now" I told him yes. Then I showed him the stack. 214 trades. 74% win rate. +$9,437 in 19 days. Here's what actually happened: I gave Claude two repos and a simple job. First repo: A full market archive. Wallet behavior, entries, exits, and timing across the board. Second repo: Three commands. 500+ markets. No API key. Just a clean way to score the board fast. The system does not try to predict the world. It tries to find which wallets consistently exit better than the crowd, isolate the pattern, and only fire when the same structure shows up again. Main filter: captured value / expected value > 0.70 If a wallet wins often but leaks the move on exit, it gets ignored. If it captures most of the move and cuts losers fast, it becomes signal. Sizing uses Kelly: f* = (p*b - q) / b That is what stops the terminal from apeing into weak edges. Most of the time it does nothing. No edge - no position. Three trades from the run: > AMD Xilinx - entered 52c. Model said 59c. Closed +7c in 2h40m. > Artemis launch - entered 63c. Model said 85c. Closed +22c in 5h10m. > Derecho MW - entered 71c. Model said 87c. Closed +16c in 1h50m. When he saw the repo links and the live terminal, he stopped talking for a second. Then he said: "We tested something close to this internally." That was the whole joke. The data is public. The repos are public. The market is public. But most Polymarket traders still trade headlines, hold too long, and call it conviction. Polymarket does not reward the smartest story. It rewards the cleaner exit.

An Anthropic engineer watched my screen from the next table at a cafe in SF. "Are you running Claude against live prediction markets right now" I told him yes. Then I showed him the stack. 214 trades. 74% win rate. +$9,437 in 19 days. Here's what actually happened: I gave Claude two repos and a simple job. First repo: A full market archive. Wallet behavior, entries, exits, and timing across the board. Second repo: Three commands. 500+ markets. No API key. Just a clean way to score the board fast. The system does not try to predict the world. It tries to find which wallets consistently exit better than the crowd, isolate the pattern, and only fire when the same structure shows up again. Main filter: captured value / expected value > 0.70 If a wallet wins often but leaks the move on exit, it gets ignored. If it captures most of the move and cuts losers fast, it becomes signal. Sizing uses Kelly: f* = (p*b - q) / b That is what stops the terminal from apeing into weak edges. Most of the time it does nothing. No edge - no position. Three trades from the run: > AMD Xilinx - entered 52c. Model said 59c. Closed +7c in 2h40m. > Artemis launch - entered 63c. Model said 85c. Closed +22c in 5h10m. > Derecho MW - entered 71c. Model said 87c. Closed +16c in 1h50m. When he saw the repo links and the live terminal, he stopped talking for a second. Then he said: "We tested something close to this internally." That was the whole joke. The data is public. The repos are public. The market is public. But most Polymarket traders still trade headlines, hold too long, and call it conviction. Polymarket does not reward the smartest story. It rewards the cleaner exit.

171,897 просмотров

Anthropic made Claude. GitHub did the rest. Two repos. $25 a month. 214 trades. 74% win rate. +$9,437 in 19 days. Here's what actually happened: I gave Claude a market archive and a live Polymarket scanner. One repo showed the full history. Who enters well. Who exits even better. Who keeps a high win rate by farming tiny moves. And who actually knows how to cut risk. The second repo turned that into a board. Every order book. Every active market. Fast enough to rank the setup before the crowd repriced it. The big shift was this: Stop tracking win rate. Start tracking exit quality. That is where most of the real edge sits. Top wallets were capturing 86% of the move and cutting losers around 12%. The average wallet was only capturing 58% and letting bad positions bleed past 40%. Same market. Same headlines. Completely different outcomes. That was the filter. Not who sounds smart. Not who posts the best thread. Who gets paid on the way out. After that I rebuilt all 8 agents around one rule: copy wallets only inside their best category and kill anything noisy. The result looked like this: 47 wallets ranked by exit quality. 191 trades. 73% win rate. Average hold: 4 hours. Capital velocity: 47x. Max drawdown: -2.1%. Sector breakdown: > Crypto: +$3,740 > Weather: +$2,910 > Politics: +$1,850 > Macro: +$1,200 > Sports: -$300 I killed sports after day two. That is the whole joke. Most Polymarket traders think the money is in predicting the result. It is not. The money is in finding people who know when to leave. Copytrade for those who don't want to build: Public repos. Cheap infra. Real edge.

Anthropic made Claude. GitHub did the rest. Two repos. $25 a month. 214 trades. 74% win rate. +$9,437 in 19 days. Here's what actually happened: I gave Claude a market archive and a live Polymarket scanner. One repo showed the full history. Who enters well. Who exits even better. Who keeps a high win rate by farming tiny moves. And who actually knows how to cut risk. The second repo turned that into a board. Every order book. Every active market. Fast enough to rank the setup before the crowd repriced it. The big shift was this: Stop tracking win rate. Start tracking exit quality. That is where most of the real edge sits. Top wallets were capturing 86% of the move and cutting losers around 12%. The average wallet was only capturing 58% and letting bad positions bleed past 40%. Same market. Same headlines. Completely different outcomes. That was the filter. Not who sounds smart. Not who posts the best thread. Who gets paid on the way out. After that I rebuilt all 8 agents around one rule: copy wallets only inside their best category and kill anything noisy. The result looked like this: 47 wallets ranked by exit quality. 191 trades. 73% win rate. Average hold: 4 hours. Capital velocity: 47x. Max drawdown: -2.1%. Sector breakdown: > Crypto: +$3,740 > Weather: +$2,910 > Politics: +$1,850 > Macro: +$1,200 > Sports: -$300 I killed sports after day two. That is the whole joke. Most Polymarket traders think the money is in predicting the result. It is not. The money is in finding people who know when to leave. Copytrade for those who don't want to build: Public repos. Cheap infra. Real edge.

89,113 просмотров

An ex-Anthropic engineer stopped next to me at a meetup in LV. I had my Polymarket terminal open. He watched the ladder for maybe fifteen seconds and said one sentence. "You're trying to predict the market. You should be measuring when it falls asleep" I asked what that was supposed to mean. He pulled my laptop closer. Opened one repository. 86 million trades. Every wallet. Every fill. Every close. The full Polymarket record since day one. "Stop reading posts. Read behavior. Ask one question - who makes money when liquidity disappears" I asked why he cared about that more than entries. He said the best wallets are not better at guessing. They are better at waiting. Then he had Claude work through the dataset. Find wallets with 70%+ win rate. More than 100 trades. Then isolate what they do between 02:30 and 04:00 UTC. That was the first useful query I had run in months. The pattern was obvious. Normal hours: tight book. noisy edge. Wolf Hour: wide book. lazy pricing. Typical spread: 2-3 cents. Dead hours: 8-10 cents. Same market. Different level of defense. I asked why Claude Code instead of just using chat. He laughed. "Because chat gives opinions. Claude Code goes into the repo, reads the structure, and actually works through the data" Then he opened the scanner. Three commands. 500+ markets live. Read-only. No API key. Claude built the overnight filter in about twenty minutes. Fair value gap > 8 cents. Spread blown out beyond normal. Resolution in 4-48 hours. No new trades unless the contract was pre-approved during liquid hours. Most markets died immediately. The few that survived were the only ones worth touching. One example. Fair value during the day: $0.51. Wolf Hour target: $0.41. At 3:12 UTC the ask printed there. Order in. London woke up. Same contract traded back around $0.50. Not prediction alpha. Structural mispricing. Then he said the line that made the whole thing click. "Good traders use AI to think faster. Great ones use it to stop themselves from trading until the market gets stupid" I rebuilt the stack that week. Daytime research. Night scanner. Morning exits. Four real entries a week was enough. About 9 cents blended edge. Roughly $9,360 a year on around $2,000 average deployed capital. No team. No fancy infra. No sitting there at 3 AM pretending discretion is a system. the edge was never hidden in better prompts. it was sitting in the one part of the night when the market stopped protecting its own prices.

An ex-Anthropic engineer stopped next to me at a meetup in LV. I had my Polymarket terminal open. He watched the ladder for maybe fifteen seconds and said one sentence. "You're trying to predict the market. You should be measuring when it falls asleep" I asked what that was supposed to mean. He pulled my laptop closer. Opened one repository. 86 million trades. Every wallet. Every fill. Every close. The full Polymarket record since day one. "Stop reading posts. Read behavior. Ask one question - who makes money when liquidity disappears" I asked why he cared about that more than entries. He said the best wallets are not better at guessing. They are better at waiting. Then he had Claude work through the dataset. Find wallets with 70%+ win rate. More than 100 trades. Then isolate what they do between 02:30 and 04:00 UTC. That was the first useful query I had run in months. The pattern was obvious. Normal hours: tight book. noisy edge. Wolf Hour: wide book. lazy pricing. Typical spread: 2-3 cents. Dead hours: 8-10 cents. Same market. Different level of defense. I asked why Claude Code instead of just using chat. He laughed. "Because chat gives opinions. Claude Code goes into the repo, reads the structure, and actually works through the data" Then he opened the scanner. Three commands. 500+ markets live. Read-only. No API key. Claude built the overnight filter in about twenty minutes. Fair value gap > 8 cents. Spread blown out beyond normal. Resolution in 4-48 hours. No new trades unless the contract was pre-approved during liquid hours. Most markets died immediately. The few that survived were the only ones worth touching. One example. Fair value during the day: $0.51. Wolf Hour target: $0.41. At 3:12 UTC the ask printed there. Order in. London woke up. Same contract traded back around $0.50. Not prediction alpha. Structural mispricing. Then he said the line that made the whole thing click. "Good traders use AI to think faster. Great ones use it to stop themselves from trading until the market gets stupid" I rebuilt the stack that week. Daytime research. Night scanner. Morning exits. Four real entries a week was enough. About 9 cents blended edge. Roughly $9,360 a year on around $2,000 average deployed capital. No team. No fancy infra. No sitting there at 3 AM pretending discretion is a system. the edge was never hidden in better prompts. it was sitting in the one part of the night when the market stopped protecting its own prices.

38,360 просмотров

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

The CEO of Palantir sat across from Larry Fink - the man who runs BlackRock and its $11.5 TRILLION in assets - and told Davos the AI race is already lost by everyone pricing it wrong. - he says the firms selling AI by the token have "completely broken" how it works 32-min from the Davos main stage on how AI redefines war, power and who actually controls capital bookmark & watch - it's the most direct AI + power talk of the year

The CEO of Palantir sat across from Larry Fink - the man who runs BlackRock and its $11.5 TRILLION in assets - and told Davos the AI race is already lost by everyone pricing it wrong. - he says the firms selling AI by the token have "completely broken" how it works 32-min from the Davos main stage on how AI redefines war, power and who actually controls capital bookmark & watch - it's the most direct AI + power talk of the year

1,007,286 просмотров • 2 месяцев назад

Goldman Sachs CEO David Solomon just explained why AI will NOT cause the white collar wipeout that all of Wall Street is bracing for. - the 156-year-old bank is deploying AI from the back office all the way up to its most senior bankers 1-hour and you'll hear how a tier-1 bank actually uses AI day to day, and what it means for junior analyst jobs bookmark & watch - the clearest take on AI + banking out there

Goldman Sachs CEO David Solomon just explained why AI will NOT cause the white collar wipeout that all of Wall Street is bracing for. - the 156-year-old bank is deploying AI from the back office all the way up to its most senior bankers 1-hour and you'll hear how a tier-1 bank actually uses AI day to day, and what it means for junior analyst jobs bookmark & watch - the clearest take on AI + banking out there

989,296 просмотров • 2 месяцев назад

Goldman Sachs MDs make $1-3M/year doing one thing: keeping CEOs of Fortune 500 firms on speed dial. This 23-min UVA Law lecture by Goldman's Vice Chairman of Global Client Coverage teaches you the exact 18 rules he uses to do it. worth more than any $5K business school elective on client management. bookmark & watch today.

Goldman Sachs MDs make $1-3M/year doing one thing: keeping CEOs of Fortune 500 firms on speed dial. This 23-min UVA Law lecture by Goldman's Vice Chairman of Global Client Coverage teaches you the exact 18 rules he uses to do it. worth more than any $5K business school elective on client management. bookmark & watch today.

1,295,160 просмотров • 4 месяцев назад

The founder of Citadel went to China after DeepSeek dropped. What he saw should worry America - "Not one author on DeepSeek was educated in America. It was a point of national pride." Ken Griffin on losing the talent war, China quietly wiring Africa's power, airports and networks, and why US tariffs only speed the retreat bookmark & watch - the clearest warning that America is losing ground to China

The founder of Citadel went to China after DeepSeek dropped. What he saw should worry America - "Not one author on DeepSeek was educated in America. It was a point of national pride." Ken Griffin on losing the talent war, China quietly wiring Africa's power, airports and networks, and why US tariffs only speed the retreat bookmark & watch - the clearest warning that America is losing ground to China

488,268 просмотров • 1 месяц назад

BlackRock controls over $10 trillion in assets - more than the GDP of China. Larry Fink - the man behind it - just explained on stage exactly how he got there: the acquisitions, the macro bets, why the U.S. deficit "will overwhelm this country." 35-min and you'll see how the world's most powerful asset manager thinks about capital, risk, and the next decade. bookmark & watch - the most important Fink interview of 2025.

BlackRock controls over $10 trillion in assets - more than the GDP of China. Larry Fink - the man behind it - just explained on stage exactly how he got there: the acquisitions, the macro bets, why the U.S. deficit "will overwhelm this country." 35-min and you'll see how the world's most powerful asset manager thinks about capital, risk, and the next decade. bookmark & watch - the most important Fink interview of 2025.

1,115,230 просмотров • 4 месяцев назад

A 21-year-old left OpenAI, wrote a PDF, and it printed billions. They call it the "billion-dollar PDF" - once a decade someone crystallizes a technological shift into one paper, and everyone who reads it early gets rich. Black-Scholes. The Bitcoin whitepaper. Sequoia's RIP Good Times. Buffett's Superinvestors. The next one is being written right now. bookmark it before they do

A 21-year-old left OpenAI, wrote a PDF, and it printed billions. They call it the "billion-dollar PDF" - once a decade someone crystallizes a technological shift into one paper, and everyone who reads it early gets rich. Black-Scholes. The Bitcoin whitepaper. Sequoia's RIP Good Times. Buffett's Superinvestors. The next one is being written right now. bookmark it before they do

573,476 просмотров • 2 месяцев назад

Jamie Dimon runs JPMorgan - just said the bank will hire "more AI people and fewer bankers" - they already run an internal LLM that 150,000 staff use every single week - $20 BILLION tech budget. workers say it saves them 4 hours a day he's telling you the back office is done: compliance, data processing, routine client work - all going to AI bookmark & watch - this is the clearest signal yet of where Wall Street headcount is headed

Jamie Dimon runs JPMorgan - just said the bank will hire "more AI people and fewer bankers" - they already run an internal LLM that 150,000 staff use every single week - $20 BILLION tech budget. workers say it saves them 4 hours a day he's telling you the back office is done: compliance, data processing, routine client work - all going to AI bookmark & watch - this is the clearest signal yet of where Wall Street headcount is headed

699,830 просмотров • 3 месяцев назад

JPMorgan CEO Jamie Dimon just released the 35-min edited version of the 90-min master class he gave to 400 of his top executives. - complacency, arrogance and bureaucracy kill companies. he explains exactly how to fight all three. 35-min and you'll learn the management playbook of the CEO who has run America's largest bank for 20 years. bookmark - the most practical management lecture from Wall Street.

JPMorgan CEO Jamie Dimon just released the 35-min edited version of the 90-min master class he gave to 400 of his top executives. - complacency, arrogance and bureaucracy kill companies. he explains exactly how to fight all three. 35-min and you'll learn the management playbook of the CEO who has run America's largest bank for 20 years. bookmark - the most practical management lecture from Wall Street.

671,330 просмотров • 3 месяцев назад

A former chess prodigy co-founded Palantir at 22, cashed almost nothing for years, and turned that into an empire - 8VC, Addepar, Anduril, a whole university. - Peter Thiel's protege who became a company-building machine 56-min unfiltered on defense tech, AI, and where the next $100B companies come from bookmark - this rewires how you think about building anything

A former chess prodigy co-founded Palantir at 22, cashed almost nothing for years, and turned that into an empire - 8VC, Addepar, Anduril, a whole university. - Peter Thiel's protege who became a company-building machine 56-min unfiltered on defense tech, AI, and where the next $100B companies come from bookmark - this rewires how you think about building anything

365,750 просмотров • 2 месяцев назад

GPT-6 ASTRA BOT started the night with $120.23. It ended with $172,641.86. I gave it a wallet and one rule. It built the rest. The terminal is one screen. Orders show up on a depth radar the second they're born, float up the grid, and either fill or they don't. Wallet by wallet, live. No dashboard to configure, it drew its own. Six lanes run it. Each does exactly one thing: > DISCOVERY catches every deploy the second it lands on chain > SIGNAL scores 51,784 wallets and surfaces the ones that enter before the candle forms > PRICING checks LP depth and mint authority, rejects anything thin before it costs a cent > EXECUTION copytrades the smart money, snipes the clean mints, passes on the rest > RISK writes the size before the entry, so one misfire never outweighs a week of hits > OVERSIGHT can kill any lane at any score. Its no beats every yes on the desk. One analyst covers 30 wallets. Six lanes cover 51,784 and never sleep, never get bored, have no opinion about last week. It loses on some of these. The hit rate dips when a signal misfires. That's on the screen, not softened. Sizing is why the line bends up anyway. The clip is last night compressed into a few seconds. Watch the equity line, not the tickers. You could run the same build on Grok Bot. I ran this one on ASTRA. Same result, different engine. The full build is in the post below ↓

GPT-6 ASTRA BOT started the night with $120.23. It ended with $172,641.86. I gave it a wallet and one rule. It built the rest. The terminal is one screen. Orders show up on a depth radar the second they're born, float up the grid, and either fill or they don't. Wallet by wallet, live. No dashboard to configure, it drew its own. Six lanes run it. Each does exactly one thing: > DISCOVERY catches every deploy the second it lands on chain > SIGNAL scores 51,784 wallets and surfaces the ones that enter before the candle forms > PRICING checks LP depth and mint authority, rejects anything thin before it costs a cent > EXECUTION copytrades the smart money, snipes the clean mints, passes on the rest > RISK writes the size before the entry, so one misfire never outweighs a week of hits > OVERSIGHT can kill any lane at any score. Its no beats every yes on the desk. One analyst covers 30 wallets. Six lanes cover 51,784 and never sleep, never get bored, have no opinion about last week. It loses on some of these. The hit rate dips when a signal misfires. That's on the screen, not softened. Sizing is why the line bends up anyway. The clip is last night compressed into a few seconds. Watch the equity line, not the tickers. You could run the same build on Grok Bot. I ran this one on ASTRA. Same result, different engine. The full build is in the post below ↓

79,998 просмотров • 16 дней назад

GPT6-Astra runs my trading account like a control tower. A position doesn't get to exist until six lanes clear it and a seventh seat signs off. I funded it with $220 on Thursday night. Woke up to $9,140. Citadel keeps a room of people whose whole job is to sit between a good idea and the order button. Mine does that for the price of a subscription and never goes home. Six lanes, one job apiece: > DISCOVERY watches for volume that moves before the price does > SIGNAL tags which of those moves somebody paid to create > PRICING runs the size math on whatever's still standing after the checks > EXECUTION takes the entry and doesn't argue with it > RISK draws the line where it stops being a trade — before the trade exists > OVERSIGHT can switch off any of the other five mid-session, and that call doesn't get discussed Above the six sits CONTROL. It never trades. It reads the briefs, scores the call, sizes it, and it's the only seat allowed to message me. Anything that sends, spends or fires halts at CONTROL and waits for a yes. It's wrong often enough. The single red mark on this week's sheet is a 2am entry I forced over CONTROL's hold. My initials are on that one, not the desk's. The board won't chase a loud ticker. It waits for its own level or it stands down, and most nights it stands down more than it acts. Not one lane would beat the base model alone. Each is narrow enough that a bad read stays trapped in its own lane, and nothing clears the button without a hand on it. Setup took one evening. Number the lanes, hand each a single job, spend twice as long on CONTROL's rules as on the rest, go to bed. Full build in the article below ↓

GPT6-Astra runs my trading account like a control tower. A position doesn't get to exist until six lanes clear it and a seventh seat signs off. I funded it with $220 on Thursday night. Woke up to $9,140. Citadel keeps a room of people whose whole job is to sit between a good idea and the order button. Mine does that for the price of a subscription and never goes home. Six lanes, one job apiece: > DISCOVERY watches for volume that moves before the price does > SIGNAL tags which of those moves somebody paid to create > PRICING runs the size math on whatever's still standing after the checks > EXECUTION takes the entry and doesn't argue with it > RISK draws the line where it stops being a trade — before the trade exists > OVERSIGHT can switch off any of the other five mid-session, and that call doesn't get discussed Above the six sits CONTROL. It never trades. It reads the briefs, scores the call, sizes it, and it's the only seat allowed to message me. Anything that sends, spends or fires halts at CONTROL and waits for a yes. It's wrong often enough. The single red mark on this week's sheet is a 2am entry I forced over CONTROL's hold. My initials are on that one, not the desk's. The board won't chase a loud ticker. It waits for its own level or it stands down, and most nights it stands down more than it acts. Not one lane would beat the base model alone. Each is narrow enough that a bad read stays trapped in its own lane, and nothing clears the button without a hand on it. Setup took one evening. Number the lanes, hand each a single job, spend twice as long on CONTROL's rules as on the rest, go to bed. Full build in the article below ↓

65,521 просмотров • 15 дней назад

the founder of Bridgewater - the largest hedge fund on Earth, the man who called 2008 - just told Meet the Press that what's coming is worse than a recession "we have a breaking down of the monetary order. we cannot spend the amounts of money." "we are going from multilateralism to a unilateral world order in which there's great conflict" "such times are very much like the 1930s" Ray Dalio doesn't panic on TV. this time he did. bookmark and watch the full interview ↓

the founder of Bridgewater - the largest hedge fund on Earth, the man who called 2008 - just told Meet the Press that what's coming is worse than a recession "we have a breaking down of the monetary order. we cannot spend the amounts of money." "we are going from multilateralism to a unilateral world order in which there's great conflict" "such times are very much like the 1930s" Ray Dalio doesn't panic on TV. this time he did. bookmark and watch the full interview ↓

408,390 просмотров • 3 месяцев назад

This Lehman VP saw the $619B collapse coming and made $75M shorting subprime from inside the bank - by 25, running a $500M trading book - by 35, hunted by JP Morgan, Goldman and Societe Generale 26-min video to understand the macro playbook every tier-1 fund still reads

This Lehman VP saw the $619B collapse coming and made $75M shorting subprime from inside the bank - by 25, running a $500M trading book - by 35, hunted by JP Morgan, Goldman and Societe Generale 26-min video to understand the macro playbook every tier-1 fund still reads

511,009 просмотров • 4 месяцев назад

Goldman Sachs Managing Director with 30 years on the desk just gave a free 19-min lecture to law students on how he actually closes deals at Goldman. - the same playbook he uses on Goldman's biggest corporate clients 19-min and you'll learn what a real Goldman Sachs mentorship sounds like behind closed doors. bookmark - it's the most practical Wall Street lecture.

Goldman Sachs Managing Director with 30 years on the desk just gave a free 19-min lecture to law students on how he actually closes deals at Goldman. - the same playbook he uses on Goldman's biggest corporate clients 19-min and you'll learn what a real Goldman Sachs mentorship sounds like behind closed doors. bookmark - it's the most practical Wall Street lecture.

473,082 просмотров • 4 месяцев назад

The CEO of Palantir - a $400 BILLION company that builds AI for Western militaries - sat down in Germany and said the quiet part out loud about AI, the far right, and why Europe is unraveling. - he has a PhD in philosophy and runs one of the most powerful defense companies on Earth 63-min of Alex Karp saying things no other tech CEO will say on camera bookmark & watch - the most unfiltered take on AI and power right now

The CEO of Palantir - a $400 BILLION company that builds AI for Western militaries - sat down in Germany and said the quiet part out loud about AI, the far right, and why Europe is unraveling. - he has a PhD in philosophy and runs one of the most powerful defense companies on Earth 63-min of Alex Karp saying things no other tech CEO will say on camera bookmark & watch - the most unfiltered take on AI and power right now

240,563 просмотров • 2 месяцев назад

Citadel CEO Ken Griffin explained why generative AI is useless for hedge funds - "it works for the next 5 minutes. The next 2 years it falls apart" every VC pitching AI right now is selling the opposite of what the $65B fund is actually doing 48-min Stanford lecture and you'll understand what AI actually does inside a tier-1 hedge fund bookmark & watch - this is the AI take no fund manager will say out loud

Citadel CEO Ken Griffin explained why generative AI is useless for hedge funds - "it works for the next 5 minutes. The next 2 years it falls apart" every VC pitching AI right now is selling the opposite of what the $65B fund is actually doing 48-min Stanford lecture and you'll understand what AI actually does inside a tier-1 hedge fund bookmark & watch - this is the AI take no fund manager will say out loud

429,766 просмотров • 4 месяцев назад

Michael Burry asked Washington one question in the New York Times - two weeks later the government came after him he was a Stanford neurology resident posting stock picks at night - quit medicine in 2000 to run money he read the actual mortgage documents nobody on Wall Street bothered to read - and saw the crash coming in 2005 his investors revolted - demanded their money back - he locked the fund and held the bet the bet paid $700 million for his investors and $100 million for himself - his fund returned 489% while the S&P went nowhere in 2010 he asked publicly: why didn't anyone in Washington listen to those who predicted the crisis? "within two weeks, all six of my defunct funds were audited... and a little later, the FBI showed up" then he stood in front of UCLA's economics graduates and told the whole story 21-min - free. watch it bookmark and watch it today

Michael Burry asked Washington one question in the New York Times - two weeks later the government came after him he was a Stanford neurology resident posting stock picks at night - quit medicine in 2000 to run money he read the actual mortgage documents nobody on Wall Street bothered to read - and saw the crash coming in 2005 his investors revolted - demanded their money back - he locked the fund and held the bet the bet paid $700 million for his investors and $100 million for himself - his fund returned 489% while the S&P went nowhere in 2010 he asked publicly: why didn't anyone in Washington listen to those who predicted the crisis? "within two weeks, all six of my defunct funds were audited... and a little later, the FBI showed up" then he stood in front of UCLA's economics graduates and told the whole story 21-min - free. watch it bookmark and watch it today

335,679 просмотров • 3 месяцев назад

GPT6-Astra runs my trading account like a paper going to press. Nothing runs until six desks clear the copy and an editor puts their name on the front page. I staked it $180 on Sunday night. Woke up to $7,720. Jane Street keeps floors of people paid to stand between a clean idea and the send key. Mine does it for a monthly fee and never files for the weekend. Six desks, one beat each: > DISCOVERY reads the wire for volume that moves before the story does > SIGNAL works out which of those moves was planted, and by whom > PRICING does the size math on whatever survives the fact-check > EXECUTION files the entry and doesn't rewrite it on the way out > RISK sets the line the trade can't cross, and sets it before there's a trade > OVERSIGHT can spike any of the other five mid-cycle, and a spike doesn't get argued Over the six sits THE SLOT. It never trades. It reads the six drafts, scores the call, sizes it, and it's the only seat that reaches my phone. Anything that sends, spends or fires holds in the slot until I sign it. It gets things wrong. The one loss with my name on it this week was a 3am entry I pushed past the slot's hold. Those initials are mine, not the desk's. The desk won't chase a loud print. It waits for its own edition or it holds the page, and it holds more nights than it runs. None of the six would beat the model you already pay for on its own. Each is narrow enough to only get one thing wrong at a time, and nothing goes to press without a hand on the page. Setup was one evening. Name the desks, give each one beat, write the slot's rules twice as carefully as the rest, then go to bed. Full build is in the article below ↓

GPT6-Astra runs my trading account like a paper going to press. Nothing runs until six desks clear the copy and an editor puts their name on the front page. I staked it $180 on Sunday night. Woke up to $7,720. Jane Street keeps floors of people paid to stand between a clean idea and the send key. Mine does it for a monthly fee and never files for the weekend. Six desks, one beat each: > DISCOVERY reads the wire for volume that moves before the story does > SIGNAL works out which of those moves was planted, and by whom > PRICING does the size math on whatever survives the fact-check > EXECUTION files the entry and doesn't rewrite it on the way out > RISK sets the line the trade can't cross, and sets it before there's a trade > OVERSIGHT can spike any of the other five mid-cycle, and a spike doesn't get argued Over the six sits THE SLOT. It never trades. It reads the six drafts, scores the call, sizes it, and it's the only seat that reaches my phone. Anything that sends, spends or fires holds in the slot until I sign it. It gets things wrong. The one loss with my name on it this week was a 3am entry I pushed past the slot's hold. Those initials are mine, not the desk's. The desk won't chase a loud print. It waits for its own edition or it holds the page, and it holds more nights than it runs. None of the six would beat the model you already pay for on its own. Each is narrow enough to only get one thing wrong at a time, and nothing goes to press without a hand on the page. Setup was one evening. Name the desks, give each one beat, write the slot's rules twice as carefully as the rest, then go to bed. Full build is in the article below ↓

41,151 просмотров • 14 дней назад

Ray Dalio on the AI bubble: "this is about 80% into a bubble - that 100% would have been 1929 and 2000" this is him - the Bridgewater founder - reading the AI melt-up against 500 years of bubbles "there's definitely a bubble in the markets" "isn't it amazing? we're talking about one stock for the stock market bubble" "General Electric and RCA - those companies went down 90%, not because of the economy - the bubble burst first because they needed cash" "the need for cash is always that which pricks the bubble" bookmark & watch today ↓

Ray Dalio on the AI bubble: "this is about 80% into a bubble - that 100% would have been 1929 and 2000" this is him - the Bridgewater founder - reading the AI melt-up against 500 years of bubbles "there's definitely a bubble in the markets" "isn't it amazing? we're talking about one stock for the stock market bubble" "General Electric and RCA - those companies went down 90%, not because of the economy - the bubble burst first because they needed cash" "the need for cash is always that which pricks the bubble" bookmark & watch today ↓

101,024 просмотров • 1 месяц назад

Warren Buffett is 95, worth around $150 BILLION, and just gave one of his final interviews as the face of the company he turned from a failing textile mill into a $1 TRILLION empire. - he explains why he just cut off his own "lifetime" donations 59-min of the greatest investor who ever lived, in his own words, near the very end bookmark & watch - you will not get many more of these

Warren Buffett is 95, worth around $150 BILLION, and just gave one of his final interviews as the face of the company he turned from a failing textile mill into a $1 TRILLION empire. - he explains why he just cut off his own "lifetime" donations 59-min of the greatest investor who ever lived, in his own words, near the very end bookmark & watch - you will not get many more of these

185,421 просмотров • 2 месяцев назад