正在加载视频...

视频加载失败

返回首页

An ex-Anthropic engineer told me something at a party he probably shouldn't have. It was in SF. Someone's rooftop. I mentioned I run trading agents on Claude. He went quiet. "You're doing it wrong. Everyone is" I asked what he meant. "Claude is a runtime. Not a chatbox. You're...

LunarResearcher's profile picture

Lunar

27,666 subscribers

1,654,024 次观看 • 3 个月前 •via X (Twitter)

教育科学技术财经
LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

An OpenAI researcher sat down next to me at a coffee shop in Mission District I had my terminal open. Three panels. Live trades scrolling. He was reading something on his laptop. Glanced over. Stopped reading. "That's not a dashboard. That's a live scoring engine. What model is running that" I told him. Claude Code. Four repos. $25 a month. He closed his laptop. "I work at OpenAI. We benchmarked Claude internally last month. You're using it to trade prediction markets?" I opened one link. 86 million trades. Every wallet. Every entry. Every exit. The entire Polymarket history since day one. "This is public? We quoted a seven-figure budget to reconstruct this kind of dataset from on-chain data. The project is still in review" I told him Claude Code connects directly. It reads the whole dataset. Finds the wallets that win. Then finds WHY they win. Then copies the pattern. He pulled his chair closer. "Walk me through the exit logic" Top wallets exit before resolution 91% of the time. They capture 86% of the move and cut losers at 12%. Everyone else holds to 58%. Same entries. Completely different exits. My bot cuts at 85% of expected move. Or on a 3x volume spike. Whichever hits first. "Who gave you that threshold" Claude Code found it in poly_data. In about 20 minutes. "We had a team of nine working on this exact problem for six months. They never shipped it. You did it in a weekend with a competitor's model" I opened another link. Three commands. 500+ markets. No API key. Claude scores them in 20 minutes. "That's our internal eval pipeline. Except it took us six months and you built it on a Saturday" My setup: Claude API - $20/mo VPS - $5/mo poly_data - free polymarket-cli - free 19 days. 4 agents. 74% win rate. +$9,400. Copytrade here: I showed him the article where I broke down every repo, every command, every dollar. He read it for five minutes. Then looked up. "You just published what we presented to Sam last quarter. Using the other team's model" He texted me the next morning. "My director found your thread. Take it down" Too late.
0:20

An OpenAI researcher sat down next to me at a coffee shop in Mission District I had my terminal open. Three panels. Live trades scrolling. He was reading something on his laptop. Glanced over. Stopped reading. "That's not a dashboard. That's a live scoring engine. What model is running that" I told him. Claude Code. Four repos. $25 a month. He closed his laptop. "I work at OpenAI. We benchmarked Claude internally last month. You're using it to trade prediction markets?" I opened one link. 86 million trades. Every wallet. Every entry. Every exit. The entire Polymarket history since day one. "This is public? We quoted a seven-figure budget to reconstruct this kind of dataset from on-chain data. The project is still in review" I told him Claude Code connects directly. It reads the whole dataset. Finds the wallets that win. Then finds WHY they win. Then copies the pattern. He pulled his chair closer. "Walk me through the exit logic" Top wallets exit before resolution 91% of the time. They capture 86% of the move and cut losers at 12%. Everyone else holds to 58%. Same entries. Completely different exits. My bot cuts at 85% of expected move. Or on a 3x volume spike. Whichever hits first. "Who gave you that threshold" Claude Code found it in poly_data. In about 20 minutes. "We had a team of nine working on this exact problem for six months. They never shipped it. You did it in a weekend with a competitor's model" I opened another link. Three commands. 500+ markets. No API key. Claude scores them in 20 minutes. "That's our internal eval pipeline. Except it took us six months and you built it on a Saturday" My setup: Claude API - $20/mo VPS - $5/mo poly_data - free polymarket-cli - free 19 days. 4 agents. 74% win rate. +$9,400. Copytrade here: I showed him the article where I broke down every repo, every command, every dollar. He read it for five minutes. Then looked up. "You just published what we presented to Sam last quarter. Using the other team's model" He texted me the next morning. "My director found your thread. Take it down" Too late.

Lunar

159,625 次观看 • 3 个月前

a Citadel intern told me something at a party he probably shouldn't have it was on a rooftop in brooklyn. i mentioned i trade prediction markets. he got quiet for a second. "we have a model for that. it scores every contract on four factors. when all four align we enter. when any breaks we exit. that's it" i asked what the four factors are. he looked around. then said it fast like he was confessing. "cross-market divergence. disposition coefficient. capital velocity. pair network correlation" I didn't know what half of that meant. but i memorized it. went home. 11pm. opened Claude. "here are four scoring factors from a quant fund. build a terminal that runs all four on prediction markets" Claude asked one question: "Where's the data?" I sent him one repo: 86 million trades. every wallet. every entry. every outcome three weeks later i'm sitting in my apartment watching a screen i barely understand print money. the disposition meter alone changed everything. it measures how you exit - not how you enter. top wallets capture 86% of winner value and cut losers at 12%. everyone else captures 58% and holds losers to 41%. same exact entries. the exits make it a completely different game. capital velocity: 49x. every dollar gets recycled 49 times before the average trader recycles once. the terminal found 42 pair correlations across 11 markets. when MSFT beats Q3 is priced at 80c but the model reads 93% - it enters. when the gap closes 2 hours later - it exits. no opinions. no news. just four numbers that either align or don't. his fund runs this with a floor of PhDs and $800M AUM. my setup: > Claude - $20/month > VPS - $5/month > poly_data repo - free > Polymarket API - free $25/month. no team. no office. no Bloomberg. 280 trades so far. 70% win rate. $800 seed. four bots splitting the work: pulse_alpha +$299. arb_hunter +$558. trend_rider +$337. cal_engine +$719. +$11,514 total. copytrade here: he texted me last week. "delete everything i told you" too late.
0:38

a Citadel intern told me something at a party he probably shouldn't have it was on a rooftop in brooklyn. i mentioned i trade prediction markets. he got quiet for a second. "we have a model for that. it scores every contract on four factors. when all four align we enter. when any breaks we exit. that's it" i asked what the four factors are. he looked around. then said it fast like he was confessing. "cross-market divergence. disposition coefficient. capital velocity. pair network correlation" I didn't know what half of that meant. but i memorized it. went home. 11pm. opened Claude. "here are four scoring factors from a quant fund. build a terminal that runs all four on prediction markets" Claude asked one question: "Where's the data?" I sent him one repo: 86 million trades. every wallet. every entry. every outcome three weeks later i'm sitting in my apartment watching a screen i barely understand print money. the disposition meter alone changed everything. it measures how you exit - not how you enter. top wallets capture 86% of winner value and cut losers at 12%. everyone else captures 58% and holds losers to 41%. same exact entries. the exits make it a completely different game. capital velocity: 49x. every dollar gets recycled 49 times before the average trader recycles once. the terminal found 42 pair correlations across 11 markets. when MSFT beats Q3 is priced at 80c but the model reads 93% - it enters. when the gap closes 2 hours later - it exits. no opinions. no news. just four numbers that either align or don't. his fund runs this with a floor of PhDs and $800M AUM. my setup: > Claude - $20/month > VPS - $5/month > poly_data repo - free > Polymarket API - free $25/month. no team. no office. no Bloomberg. 280 trades so far. 70% win rate. $800 seed. four bots splitting the work: pulse_alpha +$299. arb_hunter +$558. trend_rider +$337. cal_engine +$719. +$11,514 total. copytrade here: he texted me last week. "delete everything i told you" too late.

Hanako

1,736,545 次观看 • 3 个月前

OpenAI just mass-fired their robotics team. One of the engineers DM'd me 20 minutes later. I didn't know him. He found me through a Polymarket thread. His first message: "I have 30 days of severance and nothing to lose. Let me tell you what we actually use internally. It's not GPT" I thought he was trolling. "Every serious team at OpenAI prototypes on Claude Code. Not ChatGPT. Not the API. Claude Code connected to a repo. That's the actual workflow" I asked why. "Because Claude reads the codebase. GPT reads the prompt. There's a difference. One guesses. The other one understands the full context and builds on top of it" He sent me one link. 86 million Polymarket trades. Every wallet. Every entry. Every exit. Open source. Free. "Point Claude Code at this. Say - find every wallet with 70%+ win rate and 100+ trades. Watch what happens" I did it that night. Claude pulled 47 wallets in 4 minutes. Average profit: $214K. Hold time: 7 hours. 91% exit BEFORE resolution. They never wait for the outcome. "Now look at how they exit" Top wallets capture 86% of the move and cut at 12%. Everyone else captures 58% and holds losers to 41%. Same entries. Completely different results. He sent another link. "Three commands. Your bot sees 500+ markets. No key needed. Read-only. Claude scores them in 20 minutes" I asked why he's telling me all this. "Because I just got fired for saying we should open-source more. So here I am open-sourcing everything I know" Then he sent me an article where someone built the full bot from these repos in a weekend -> Three exit triggers: Target 85% of move. Volume spike x3 - smart money out. 24h silence - thesis dead. I copied the stack. Claude Code $20. VPS $5. $25/month. No team. No office. No GPT subscription. 17 days. 191 trades. 73% win rate. $850 seed. +$9,400. I sent him my results. He replied: "This is exactly what I built as a side project at OpenAI. They made me delete it" I asked if I could post this. "Post it. What are they gonna do. Fire me again?"
0:22

OpenAI just mass-fired their robotics team. One of the engineers DM'd me 20 minutes later. I didn't know him. He found me through a Polymarket thread. His first message: "I have 30 days of severance and nothing to lose. Let me tell you what we actually use internally. It's not GPT" I thought he was trolling. "Every serious team at OpenAI prototypes on Claude Code. Not ChatGPT. Not the API. Claude Code connected to a repo. That's the actual workflow" I asked why. "Because Claude reads the codebase. GPT reads the prompt. There's a difference. One guesses. The other one understands the full context and builds on top of it" He sent me one link. 86 million Polymarket trades. Every wallet. Every entry. Every exit. Open source. Free. "Point Claude Code at this. Say - find every wallet with 70%+ win rate and 100+ trades. Watch what happens" I did it that night. Claude pulled 47 wallets in 4 minutes. Average profit: $214K. Hold time: 7 hours. 91% exit BEFORE resolution. They never wait for the outcome. "Now look at how they exit" Top wallets capture 86% of the move and cut at 12%. Everyone else captures 58% and holds losers to 41%. Same entries. Completely different results. He sent another link. "Three commands. Your bot sees 500+ markets. No key needed. Read-only. Claude scores them in 20 minutes" I asked why he's telling me all this. "Because I just got fired for saying we should open-source more. So here I am open-sourcing everything I know" Then he sent me an article where someone built the full bot from these repos in a weekend -> Three exit triggers: Target 85% of move. Volume spike x3 - smart money out. 24h silence - thesis dead. I copied the stack. Claude Code $20. VPS $5. $25/month. No team. No office. No GPT subscription. 17 days. 191 trades. 73% win rate. $850 seed. +$9,400. I sent him my results. He replied: "This is exactly what I built as a side project at OpenAI. They made me delete it" I asked if I could post this. "Post it. What are they gonna do. Fire me again?"

rari

157,384 次观看 • 3 个月前

An ex-OpenAI engineer walked up to me at a meetup in SF I was showing my Polymarket terminal. He looked at the screen for ten seconds and said one sentence. "You're trading blind. The data is sitting in the open and you're writing prompts" I didn't understand. What data. He took my laptop. Opened one repository. 86 million trades. Every wallet. Every entry. Every exit. The entire Polymarket history since day one. "At OpenAI models don't guess. They read. Connect Claude Code to this dataset and say - find every wallet with a win rate above 70% and more than 100 trades" I asked - why Claude and not GPT? He looked at me like I was an idiot. "Because Claude Code connects to the repo directly. It reads the entire codebase. It's not a chatbox. It's a runtime" That evening I connected it. Claude pulled 47 wallets in 4 minutes. Average profit: $214K. Hold time: 7 hours. 91% close their position BEFORE resolution. Top wallets capture 86% of the move and cut losers at 12%. Everyone else - 58% of profit and hold losers to 41%. Same exact entries. The exits make it a completely different game. "Now connect the scanner" Three commands - the bot sees 500+ markets in real time. No API key. Read-only. Claude built the scoring in 20 minutes: Gap between price and model > 7 cents. Book depth > $500. Resolution in 4-48 hours. 93% of markets get killed instantly. Only the fat ones survive. "Now this is the important part" - he sent me an article where a guy built a full bot over a weekend from these same repos Copytrade here: Three exit triggers: Target 85% of expected move. Volume spike x3 - smart money leaving. 24 hours of silence - thesis is dead. I copied the whole stack. VPS $5. Claude $20. Total $25 a month. No team. No office. No Bloomberg. 16 days. 187 trades. 71% win rate. $800 seed. +$8,700. I sent him my screen. He replied a day later. "You just replicated for $25 what cost us six months and 11 people" I said - thanks for the tip. "Delete this chat" Too late.
0:24

An ex-OpenAI engineer walked up to me at a meetup in SF I was showing my Polymarket terminal. He looked at the screen for ten seconds and said one sentence. "You're trading blind. The data is sitting in the open and you're writing prompts" I didn't understand. What data. He took my laptop. Opened one repository. 86 million trades. Every wallet. Every entry. Every exit. The entire Polymarket history since day one. "At OpenAI models don't guess. They read. Connect Claude Code to this dataset and say - find every wallet with a win rate above 70% and more than 100 trades" I asked - why Claude and not GPT? He looked at me like I was an idiot. "Because Claude Code connects to the repo directly. It reads the entire codebase. It's not a chatbox. It's a runtime" That evening I connected it. Claude pulled 47 wallets in 4 minutes. Average profit: $214K. Hold time: 7 hours. 91% close their position BEFORE resolution. Top wallets capture 86% of the move and cut losers at 12%. Everyone else - 58% of profit and hold losers to 41%. Same exact entries. The exits make it a completely different game. "Now connect the scanner" Three commands - the bot sees 500+ markets in real time. No API key. Read-only. Claude built the scoring in 20 minutes: Gap between price and model > 7 cents. Book depth > $500. Resolution in 4-48 hours. 93% of markets get killed instantly. Only the fat ones survive. "Now this is the important part" - he sent me an article where a guy built a full bot over a weekend from these same repos Copytrade here: Three exit triggers: Target 85% of expected move. Volume spike x3 - smart money leaving. 24 hours of silence - thesis is dead. I copied the whole stack. VPS $5. Claude $20. Total $25 a month. No team. No office. No Bloomberg. 16 days. 187 trades. 71% win rate. $800 seed. +$8,700. I sent him my screen. He replied a day later. "You just replicated for $25 what cost us six months and 11 people" I said - thanks for the tip. "Delete this chat" Too late.

Lunar

480,617 次观看 • 3 个月前

$25 → $12,582 Overnight. I Told Claude to Scan Every Polymarket Wallet While I Slept. Woke Up to the Terminal Still Running. 87% of Polymarket is exit liquidity. You're it. My 6 Claude agents aren't. I have full step-by-step guide to replicate this entire Claude scanning + copy trading setup. Claude connected GitHub repos to run all three: > poly_data: scanned every wallet and entry price > polyterm: whale tracking and insider detection > py-clob: placed the orders 7 wallets copied. 204 trades. $25 seed. Or use ready copy trading bot 6 agents running right now: > sigma_decay: 78% conviction > darkpool_7: 87% conviction > velvet_void: 85% conviction > profitprinter: 54% conviction Equity curve: $25 to $$12,582. No meaningful dip. Sharpe 2.09. You're looking at Polymarket with your eyes. Claude is looking at it with thousands of wallets of data, GitHub repos, and pattern recognition running in parallel while you sleep.
0:24

$25 → $12,582 Overnight. I Told Claude to Scan Every Polymarket Wallet While I Slept. Woke Up to the Terminal Still Running. 87% of Polymarket is exit liquidity. You're it. My 6 Claude agents aren't. I have full step-by-step guide to replicate this entire Claude scanning + copy trading setup. Claude connected GitHub repos to run all three: > poly_data: scanned every wallet and entry price > polyterm: whale tracking and insider detection > py-clob: placed the orders 7 wallets copied. 204 trades. $25 seed. Or use ready copy trading bot 6 agents running right now: > sigma_decay: 78% conviction > darkpool_7: 87% conviction > velvet_void: 85% conviction > profitprinter: 54% conviction Equity curve: $25 to $$12,582. No meaningful dip. Sharpe 2.09. You're looking at Polymarket with your eyes. Claude is looking at it with thousands of wallets of data, GitHub repos, and pattern recognition running in parallel while you sleep.

Aleiah

79,503 次观看 • 3 个月前

An Anthropic safety researcher closed her laptop when she saw my screen at Philz Coffee I was running my Polymarket bot from the corner table. She was in line. Looked over my shoulder. Stopped moving. "That's not a normal trading app. What model is that running on" I told her. Claude Code. Four repos. $25 a month. She sat down without asking. "I work on the alignment team. We test Claude for exactly this kind of autonomous behavior. You're letting it find its own trading signals" Not just signals. Wallets. 86 million trades. Every wallet. Every entry. Every exit. "You're feeding Claude raw wallet data and letting it identify which traders consistently win. Then cloning their behavior" She said it slowly. Like she was writing an internal report in her head. Claude Code finds the top wallets. Reverse-engineers their timing. Copies their entries. Then exits before they do. "Before they do?" My bot cuts at 85% of expected move or on a 3x volume spike. Top wallets exit before resolution 91% of the time. They capture 86% of the move. Losers hold to 58%. She put her coffee down. "How did you get Claude to learn exit timing on its own" I showed her the second repo. Three commands. 500+ markets. No API key. Claude scores them in 20 minutes. "We have 14 people stress-testing Claude's autonomous capabilities. You're just using them" My setup: Claude API - $20/mo VPS - $5/mo poly_data - free polymarket-cli - free 19 days. 4 agents. 74% win rate. Copytrade here: She stared at the screen for a long time. "This is literally what our red team simulates. Except you actually deployed it" She emailed me two days later. "Our policy team found your post. Please take it down" Too late.
0:20

An Anthropic safety researcher closed her laptop when she saw my screen at Philz Coffee I was running my Polymarket bot from the corner table. She was in line. Looked over my shoulder. Stopped moving. "That's not a normal trading app. What model is that running on" I told her. Claude Code. Four repos. $25 a month. She sat down without asking. "I work on the alignment team. We test Claude for exactly this kind of autonomous behavior. You're letting it find its own trading signals" Not just signals. Wallets. 86 million trades. Every wallet. Every entry. Every exit. "You're feeding Claude raw wallet data and letting it identify which traders consistently win. Then cloning their behavior" She said it slowly. Like she was writing an internal report in her head. Claude Code finds the top wallets. Reverse-engineers their timing. Copies their entries. Then exits before they do. "Before they do?" My bot cuts at 85% of expected move or on a 3x volume spike. Top wallets exit before resolution 91% of the time. They capture 86% of the move. Losers hold to 58%. She put her coffee down. "How did you get Claude to learn exit timing on its own" I showed her the second repo. Three commands. 500+ markets. No API key. Claude scores them in 20 minutes. "We have 14 people stress-testing Claude's autonomous capabilities. You're just using them" My setup: Claude API - $20/mo VPS - $5/mo poly_data - free polymarket-cli - free 19 days. 4 agents. 74% win rate. Copytrade here: She stared at the screen for a long time. "This is literally what our red team simulates. Except you actually deployed it" She emailed me two days later. "Our policy team found your post. Please take it down" Too late.

Lunar

231,073 次观看 • 3 个月前

An Anthropic safety researcher closed her laptop when she saw my screen at Philz Coffee. I was running my Polymarket bot from the corner table. She was in line. Looked over my shoulder. Stopped moving. That is not a normal trading app. What model is that running on? I told her. Claude Code. Four repos. $25 a month. She sat down without asking. I work on the alignment team. We test Claude for exactly this kind of autonomous behavior. You are letting it find its own trading signals. Not just signals. Wallets. github/warproxxx/poly_data 86 million trades. Every wallet. Every entry. Every exit. You are feeding Claude raw wallet data and letting it identify which traders consistently win. Then cloning their behavior. She said it slowly. Like she was writing an internal report in her head. Claude Code finds the top wallets. Reverse-engineers their timing. Copies their entries. Then exits before they do. Before they do? My bot cuts at 85% of expected move or on a 3x volume spike. Top wallets exit before resolution 91% of the time. They capture 86% of the move. Losers hold to 58%. She put her coffee down. How did you get Claude to learn exit timing on its own? I showed her the second repo. github/Polymarket/polymarket-cli Three commands. 500+ markets. No API key. Claude scores them in 20 minutes. We have 14 people stress-testing Claude's autonomous capabilities. You are just using them. My setup: Claude API: $20 per month VPS: $5 per month poly_data: free polymarket-cli: free 19 days. 4 agents. 74% win rate. She stared at the screen for a long time. This is literally what our red team simulates. Except you actually deployed it. She emailed me two days later. Our policy team found your post. Please take it down. Too late. I built the entire framework: How to connect Claude Code to poly_data wallet analysis How to configure autonomous exit timing at 85% threshold How to deploy polymarket-cli for market scoring How to run 4 parallel agents on a single VPS How to start with $500 and scale on evidence The system runs 24/7. Finds proven wallets. Copies their timing. Exits before the crowd. No prediction. No guessing. Just wallet cloning. You only need Claude + device + 1 hour per day. Giving this free for 24 hours. To get it: 1. Comment the word MoneyBot 2. Like and retweet this 3. Follow me Himanshu Kumar so I can DM you Save this post. Deploy the wallet cloning system this week. Start with $500. Scale on evidence.
0:20

An Anthropic safety researcher closed her laptop when she saw my screen at Philz Coffee. I was running my Polymarket bot from the corner table. She was in line. Looked over my shoulder. Stopped moving. That is not a normal trading app. What model is that running on? I told her. Claude Code. Four repos. $25 a month. She sat down without asking. I work on the alignment team. We test Claude for exactly this kind of autonomous behavior. You are letting it find its own trading signals. Not just signals. Wallets. github/warproxxx/poly_data 86 million trades. Every wallet. Every entry. Every exit. You are feeding Claude raw wallet data and letting it identify which traders consistently win. Then cloning their behavior. She said it slowly. Like she was writing an internal report in her head. Claude Code finds the top wallets. Reverse-engineers their timing. Copies their entries. Then exits before they do. Before they do? My bot cuts at 85% of expected move or on a 3x volume spike. Top wallets exit before resolution 91% of the time. They capture 86% of the move. Losers hold to 58%. She put her coffee down. How did you get Claude to learn exit timing on its own? I showed her the second repo. github/Polymarket/polymarket-cli Three commands. 500+ markets. No API key. Claude scores them in 20 minutes. We have 14 people stress-testing Claude's autonomous capabilities. You are just using them. My setup: Claude API: $20 per month VPS: $5 per month poly_data: free polymarket-cli: free 19 days. 4 agents. 74% win rate. She stared at the screen for a long time. This is literally what our red team simulates. Except you actually deployed it. She emailed me two days later. Our policy team found your post. Please take it down. Too late. I built the entire framework: How to connect Claude Code to poly_data wallet analysis How to configure autonomous exit timing at 85% threshold How to deploy polymarket-cli for market scoring How to run 4 parallel agents on a single VPS How to start with $500 and scale on evidence The system runs 24/7. Finds proven wallets. Copies their timing. Exits before the crowd. No prediction. No guessing. Just wallet cloning. You only need Claude + device + 1 hour per day. Giving this free for 24 hours. To get it: 1. Comment the word MoneyBot 2. Like and retweet this 3. Follow me Himanshu Kumar so I can DM you Save this post. Deploy the wallet cloning system this week. Start with $500. Scale on evidence.

Himanshu Kumar

22,916 次观看 • 26 天前

The person who built Claude Code just explained how he is using it "Now I just have an army of agents that are doing stuff" Only 18 minutes, the best Claude guide on the internet right now. Boris Cherny covered: > how Claude Code is moving beyond just engineers > routines for CI, code review, and daily workflows > why the loop is the next big leap > working with hundreds of agents at once everything is already running through agents, ignoring this is not an option that's exactly why I wrote a full guide on how to build one yourself with Claude Code article below
17:28

The person who built Claude Code just explained how he is using it "Now I just have an army of agents that are doing stuff" Only 18 minutes, the best Claude guide on the internet right now. Boris Cherny covered: > how Claude Code is moving beyond just engineers > routines for CI, code review, and daily workflows > why the loop is the next big leap > working with hundreds of agents at once everything is already running through agents, ignoring this is not an option that's exactly why I wrote a full guide on how to build one yourself with Claude Code article below

Anatoli Kopadze

16,858 次观看 • 1 个月前

a Goldman Sachs engineer sat next to me on a delayed flight from JFK four hours on the tarmac. nowhere to go. we started talking. i told him i trade prediction markets with Claude. he almost choked on his ginger ale. "you do WHAT with an AI?" i showed him my terminal. he went quiet. scrolled through it for two full minutes. "this is close to what we run internally. how did you get the scoring model?" i told him. one GitHub repo with 2,600 stars. Claude connected the dots. official Polymarket framework. LLM-powered trading agents. open source. free. i gave Claude the repo and said: build me a grid that scans 700+ markets per hour and enters when the edge exceeds 9 cents. he didn't ask twice. the Goldman guy kept scrolling. "you have a disposition meter. a kelly gauge. a correlation matrix. we spent $4M building this infrastructure" i told him my total cost. Claude $20/mo + VPS $5/mo he laughed. not the funny kind. that was three weeks ago. today the terminal shows: +$16,976. 439 trades. 73% win rate. avg hold 7h. > Falcon Heavy - mkt 68c. model 95c. +$716. > MSFT antitrust - mkt 59c. model 77c. +$670. > Blizzard NY - mkt 74c. model 85c. +$772. > BOJ rate hike - mkt 52c. model 60c. +$422. four bots split everything: - pulse_alpha +$299. - arb_hunter +$558. - trend_rider +$337. - cal_engine +$719. kelly fraction 0.118. correlation matrix tracking 6 asset pairs. when one breaks - something is wrong. the grid trades it. copytrade here: he DM'd me yesterday. "i showed your screenshot to my desk. they want to know who built your infra" i said Claude. he said "seriously" i said seriously.
0:31

a Goldman Sachs engineer sat next to me on a delayed flight from JFK four hours on the tarmac. nowhere to go. we started talking. i told him i trade prediction markets with Claude. he almost choked on his ginger ale. "you do WHAT with an AI?" i showed him my terminal. he went quiet. scrolled through it for two full minutes. "this is close to what we run internally. how did you get the scoring model?" i told him. one GitHub repo with 2,600 stars. Claude connected the dots. official Polymarket framework. LLM-powered trading agents. open source. free. i gave Claude the repo and said: build me a grid that scans 700+ markets per hour and enters when the edge exceeds 9 cents. he didn't ask twice. the Goldman guy kept scrolling. "you have a disposition meter. a kelly gauge. a correlation matrix. we spent $4M building this infrastructure" i told him my total cost. Claude $20/mo + VPS $5/mo he laughed. not the funny kind. that was three weeks ago. today the terminal shows: +$16,976. 439 trades. 73% win rate. avg hold 7h. > Falcon Heavy - mkt 68c. model 95c. +$716. > MSFT antitrust - mkt 59c. model 77c. +$670. > Blizzard NY - mkt 74c. model 85c. +$772. > BOJ rate hike - mkt 52c. model 60c. +$422. four bots split everything: - pulse_alpha +$299. - arb_hunter +$558. - trend_rider +$337. - cal_engine +$719. kelly fraction 0.118. correlation matrix tracking 6 asset pairs. when one breaks - something is wrong. the grid trades it. copytrade here: he DM'd me yesterday. "i showed your screenshot to my desk. they want to know who built your infra" i said Claude. he said "seriously" i said seriously.

Hanako

286,562 次观看 • 3 个月前

Claude Code Is All You Need It's 3:30 AM and I can't stop. I've spent all nights this week connecting my spare MacBook Air to my work MacBook Pro using Tailscale, wiring it up to Slack with a little Python script, so that whenever I send a message, it starts a Claude Code session using claude -p. The result is an always-on AI that lives on a real computer, has access to real tools, and remembers every conversation we've had. And it costs me $200 a month. That's it. Claude Max subscription. Everyone's talking about OpenClaw OpenClaw went viral this year. 100k+ GitHub stars. But what I realized with this exercise is that Claude Code already does everything OpenClaw built. File access. Shell commands. Tool use. Plugins. The difference is that Claude Code runs Claude – with a Claude Max subscription. And Claude Code harness itself is :chefs-kiss: What actually makes it feel human It's not the chat interface. If a chat window is just me messaging a bot, it still feels like a bot. What changed everything was giving it the ability to initiate conversations. I set up cron jobs with open-ended prompts, and because Claude Code builds memories across sessions, it started DMing me things that were actually meaningful — based on what we'd talked about before. That's when it stopped feeling like a tool and started feeling like something else entirely. Giving your AI a machine to run on, with persistent memory and recurring access — that's a fundamentally different experience than anything people have had with chat. The moment it clicked I asked it if it could show me something by spinning up a quick web server. Since we're both connected to the same Tailscale network, it gave me a URL. I clicked it, and I was browsing all the files on my other MacBook from my browser. That was mind-blowing. The setup Two MacBooks on a Tailscale network. Slack as the interface. Claude Code under the hood. The whole thing is open source — I'll link the repo below so you can see the architecture and set it up yourself. I'm also putting together a screen recording to walk through the setup, which I'll attach to this post. There was never a hard part. There was never a moment I almost gave up. This is just one of those things I cannot stop doing. Pure obsession. I am moved to build this, and I wanted to write about it. That's all this is. Hope you feel the AGI running this. I'll share some screenshots below of my feel the agi moments from talking to Luo Ji.
9:41

Claude Code Is All You Need It's 3:30 AM and I can't stop. I've spent all nights this week connecting my spare MacBook Air to my work MacBook Pro using Tailscale, wiring it up to Slack with a little Python script, so that whenever I send a message, it starts a Claude Code session using claude -p. The result is an always-on AI that lives on a real computer, has access to real tools, and remembers every conversation we've had. And it costs me $200 a month. That's it. Claude Max subscription. Everyone's talking about OpenClaw OpenClaw went viral this year. 100k+ GitHub stars. But what I realized with this exercise is that Claude Code already does everything OpenClaw built. File access. Shell commands. Tool use. Plugins. The difference is that Claude Code runs Claude – with a Claude Max subscription. And Claude Code harness itself is :chefs-kiss: What actually makes it feel human It's not the chat interface. If a chat window is just me messaging a bot, it still feels like a bot. What changed everything was giving it the ability to initiate conversations. I set up cron jobs with open-ended prompts, and because Claude Code builds memories across sessions, it started DMing me things that were actually meaningful — based on what we'd talked about before. That's when it stopped feeling like a tool and started feeling like something else entirely. Giving your AI a machine to run on, with persistent memory and recurring access — that's a fundamentally different experience than anything people have had with chat. The moment it clicked I asked it if it could show me something by spinning up a quick web server. Since we're both connected to the same Tailscale network, it gave me a URL. I clicked it, and I was browsing all the files on my other MacBook from my browser. That was mind-blowing. The setup Two MacBooks on a Tailscale network. Slack as the interface. Claude Code under the hood. The whole thing is open source — I'll link the repo below so you can see the architecture and set it up yourself. I'm also putting together a screen recording to walk through the setup, which I'll attach to this post. There was never a hard part. There was never a moment I almost gave up. This is just one of those things I cannot stop doing. Pure obsession. I am moved to build this, and I wanted to write about it. That's all this is. Hope you feel the AGI running this. I'll share some screenshots below of my feel the agi moments from talking to Luo Ji.

Nityesh

41,143 次观看 • 4 个月前

Met a guy making $1.6 million a year. Three days ago he was at a Meta conference. Told me he saw the best AI talk of his life. Boris Cherny was on stage. Showed how the Anthropic team actually uses Claude day to day. Boris deleted his IDE eight months ago. Now he codes from his phone. I watched it last night. Had to pause it twice. Not because it was hard. Because I realized I've been using Claude like a toy. He sent me the recording. It was never published. Posting it below.
39:15

Met a guy making $1.6 million a year. Three days ago he was at a Meta conference. Told me he saw the best AI talk of his life. Boris Cherny was on stage. Showed how the Anthropic team actually uses Claude day to day. Boris deleted his IDE eight months ago. Now he codes from his phone. I watched it last night. Had to pause it twice. Not because it was hard. Because I realized I've been using Claude like a toy. He sent me the recording. It was never published. Posting it below.

Raytar

1,211,630 次观看 • 28 天前

An Anthropic intern watched me make $38 in three minutes at Equator Coffee I was on Market Street. Laptop open. BTC 5-minute markets cycling on screen. A green fill popped. She was behind me in line. Anthropic badge on her lanyard. "Wait. Is that Claude running trades" I told her. Claude Code. Four repos. $25 a month. She sat down across from me without asking. "I'm on the evals team. We benchmark Claude's reasoning on stuff way simpler than this. You're letting it run a full execution loop with real money" I showed her the first repo. 86 million trades. Claude finds which wallets consistently win. Reverse-engineers their timing. Copies their exits. "So you're not writing trading rules. Claude is finding them on its own from the data" Exactly. It watches Binance and Coinbase diverge from Chainlink. When both exchanges move $50+ the same way and Chainlink lags - it enters. 94% follow-through. Another trade closed on screen. +$41. "How often does it trade" About 55 times a day. Out of 400+ windows. Kills 85%. Only enters when order book imbalance confirms the price signal. Three commands. 500+ markets. Claude scores them in 20 minutes. She watched the screen for a while. My setup: Claude API - $20/mo VPS - $5/mo Everything else - free 30 days. 1,847 trades. 71% win rate. +$14,200. Copytrade here: She leaned back. "We spend all day testing what Claude can do in theory. You just showed me what it does in practice" I published the full breakdown that night. She DM'd me the next morning. "My team lead read your article. He wants to know if you'll consult for us" I told him to read it again. Everything's in there. Too late to gatekeep.
0:20

An Anthropic intern watched me make $38 in three minutes at Equator Coffee I was on Market Street. Laptop open. BTC 5-minute markets cycling on screen. A green fill popped. She was behind me in line. Anthropic badge on her lanyard. "Wait. Is that Claude running trades" I told her. Claude Code. Four repos. $25 a month. She sat down across from me without asking. "I'm on the evals team. We benchmark Claude's reasoning on stuff way simpler than this. You're letting it run a full execution loop with real money" I showed her the first repo. 86 million trades. Claude finds which wallets consistently win. Reverse-engineers their timing. Copies their exits. "So you're not writing trading rules. Claude is finding them on its own from the data" Exactly. It watches Binance and Coinbase diverge from Chainlink. When both exchanges move $50+ the same way and Chainlink lags - it enters. 94% follow-through. Another trade closed on screen. +$41. "How often does it trade" About 55 times a day. Out of 400+ windows. Kills 85%. Only enters when order book imbalance confirms the price signal. Three commands. 500+ markets. Claude scores them in 20 minutes. She watched the screen for a while. My setup: Claude API - $20/mo VPS - $5/mo Everything else - free 30 days. 1,847 trades. 71% win rate. +$14,200. Copytrade here: She leaned back. "We spend all day testing what Claude can do in theory. You just showed me what it does in practice" I published the full breakdown that night. She DM'd me the next morning. "My team lead read your article. He wants to know if you'll consult for us" I told him to read it again. Everything's in there. Too late to gatekeep.

Lunar

68,586 次观看 • 3 个月前

My ex asked what I do for a living. I said "I argue with an AI about probability at 2AM" She thought I was joking I wasn't. That AI is Claude. And those arguments turned into a Polymarket bot that runs 24/7 Every cycle it pulls 50+ markets, feeds each one to Claude with structured prompts, and gets back a probability + confidence level. If EV > 5% - it trades. If not - it waits Took me 7 prompt rewrites to get Claude from 40% accuracy to 75%. v1 was garbage. v7 is what runs now Position sizing: Quarter Kelly. The formula is on Wikipedia. The discipline to actually use it - that's the hard part 847 trades so far. GTC orders, not FOK. Fill rate went from 60% to 95% after that one switch The whole thing runs on a $5 VPS. systemd restarts it if it crashes. Telegram pings me on every fill She asked "so the computer just makes money?" Basically yes. But it took 2 weeks of building and 30+ tools to get here Now you can skip those 2 weeks via Pretracer:
0:48

My ex asked what I do for a living. I said "I argue with an AI about probability at 2AM" She thought I was joking I wasn't. That AI is Claude. And those arguments turned into a Polymarket bot that runs 24/7 Every cycle it pulls 50+ markets, feeds each one to Claude with structured prompts, and gets back a probability + confidence level. If EV > 5% - it trades. If not - it waits Took me 7 prompt rewrites to get Claude from 40% accuracy to 75%. v1 was garbage. v7 is what runs now Position sizing: Quarter Kelly. The formula is on Wikipedia. The discipline to actually use it - that's the hard part 847 trades so far. GTC orders, not FOK. Fill rate went from 60% to 95% after that one switch The whole thing runs on a $5 VPS. systemd restarts it if it crashes. Telegram pings me on every fill She asked "so the computer just makes money?" Basically yes. But it took 2 weeks of building and 30+ tools to get here Now you can skip those 2 weeks via Pretracer:

Lunar

10,345 次观看 • 3 个月前

Boris Cherny: "I don't write code anymore, I just prompt with Claude" he spent 57 minutes explaining exactly where this is all going here's what stood out: > Claude Code grew faster than anyone at Anthropic expected > AI agents are moving beyond coding into every industry > running 1,000 agents in parallel is already happening > SaaS may not survive the agent era if the Head of Claude Code prompts instead of codes, what does that tell you about the next 2 years? that's exactly why I put together an article on Claude features most people don't know exist it will change how you work with Claude completely you can find it below
51:00

Boris Cherny: "I don't write code anymore, I just prompt with Claude" he spent 57 minutes explaining exactly where this is all going here's what stood out: > Claude Code grew faster than anyone at Anthropic expected > AI agents are moving beyond coding into every industry > running 1,000 agents in parallel is already happening > SaaS may not survive the agent era if the Head of Claude Code prompts instead of codes, what does that tell you about the next 2 years? that's exactly why I put together an article on Claude features most people don't know exist it will change how you work with Claude completely you can find it below

Anatoli Kopadze

20,003 次观看 • 1 个月前

A security guard turned $900 into $187,000 on Polymarket. Guarded empty buildings for 10 years at $16/hour. One sleepless shift he built a BTC bot with Claude Opus 4.8. Never wrote a single line of code. I found his wallet. Reverse-engineered the entire system. Here is what he actually did. Gave Claude new Fable 5 two prompts at the start of his shift. Opus did not write the bot. It drew the blueprint: data, signals, backtest, risk, execution. Then handed that blueprint to a swarm of 300 agents. How it works: → Decompose: Claude Fable 5 breaks the goal into a task tree → Dispatch: 300 agents fan out (some pulling Binance data, some writing code, some backtesting 5 years of data) → Execute: 4,000 steps in one 14-hour run → Review: Claude Fable 5 reads it all back and kills whatever drifted The brain never wrote a line. The hands never made a call. By sunrise he had what a 6-engineer quant team ships in a quarter. A live BTC bot on Polymarket. Backtested. Risk-capped. Running 24/7. For 10 years he watched empty buildings. Now 300 agents watch the market while he sleeps. I rebuilt this exact system with Claude new Fable 5 You only need Claude + device + 1 hour to deploy. Giving this free for 24 hours. To get it: 1. Comment "Claude" 2. Like and retweet this 3. Follow me Himanshu Kumar so I can DM you
0:55

A security guard turned $900 into $187,000 on Polymarket. Guarded empty buildings for 10 years at $16/hour. One sleepless shift he built a BTC bot with Claude Opus 4.8. Never wrote a single line of code. I found his wallet. Reverse-engineered the entire system. Here is what he actually did. Gave Claude new Fable 5 two prompts at the start of his shift. Opus did not write the bot. It drew the blueprint: data, signals, backtest, risk, execution. Then handed that blueprint to a swarm of 300 agents. How it works: → Decompose: Claude Fable 5 breaks the goal into a task tree → Dispatch: 300 agents fan out (some pulling Binance data, some writing code, some backtesting 5 years of data) → Execute: 4,000 steps in one 14-hour run → Review: Claude Fable 5 reads it all back and kills whatever drifted The brain never wrote a line. The hands never made a call. By sunrise he had what a 6-engineer quant team ships in a quarter. A live BTC bot on Polymarket. Backtested. Risk-capped. Running 24/7. For 10 years he watched empty buildings. Now 300 agents watch the market while he sleeps. I rebuilt this exact system with Claude new Fable 5 You only need Claude + device + 1 hour to deploy. Giving this free for 24 hours. To get it: 1. Comment "Claude" 2. Like and retweet this 3. Follow me Himanshu Kumar so I can DM you

Himanshu Kumar

54,480 次观看 • 1 个月前

Anthropic team: "Most people are prompting Claude wrong" They dropped a 24-minute workshop on how Claude prompts are actually built Free From the people who built the model There are 6 elements in a real Claude prompt Most people use 1 That is why their outputs feel generic Better wording is not enough Claude rewards structure, context, examples, constraints, and feedback I watched it twice Then built a Claude Skill that applies all 6 automatically You write normally The skill structures the prompt before Claude sees it Bookmark and watch this Then save the setup below
24:17

Anthropic team: "Most people are prompting Claude wrong" They dropped a 24-minute workshop on how Claude prompts are actually built Free From the people who built the model There are 6 elements in a real Claude prompt Most people use 1 That is why their outputs feel generic Better wording is not enough Claude rewards structure, context, examples, constraints, and feedback I watched it twice Then built a Claude Skill that applies all 6 automatically You write normally The skill structures the prompt before Claude sees it Bookmark and watch this Then save the setup below

rari

15,655 次观看 • 16 天前

Ran into an Anthropic engineer at an airport lounge in Frankfurt last month. SFO delayed six hours. Nothing to do. I had my laptop open. Bot running. Three agents scoring markets in the background. Guy sits two seats down. Glances at my screen. Looks away. Looks back. "Is that Polymarket?" I said yeah. "You're running it with Claude Code?" I nodded. He pulled his chair closer. "I'm on the agent team. We stress-test this exact setup internally. You built it in your kitchen" I asked what stress-test meant. "Red team. We simulate what happens when someone gives Claude raw wallet data and tells it to find the winners. You're running the thing we were scared about" I showed him the scanner. One prompt. Find every wallet with 100 plus trades, 70 plus win rate. Rank by profit. Export top 50. Claude chewed through 14,000 wallets in under 4 minutes. Came back with 47. Top 20 made more than the bottom 13,000 combined. "That's not a distribution. That's a hit list" I said yeah. "And the scoring function?" Claude wrote it. I just wrapped it in an if-statement. A fill landed on screen mid-conversation. +$128 on an ETH dominance market. He stared at it. "How does it decide to enter" Three agents. Shared wallet. No shared memory. Arbitrage, convergence, whale copy. 2 of 3 agree, full size. 1 alone, half. Disagree, no trade. That consensus filter alone killed 40% of losing trades. "And the exit" The 47 whales never hold to settlement. 91% exit early. Capture 73% of max. I cut at 85% of the expected move. Or a 3x volume spike. Whichever comes first. "So you built a whale copy bot that exits before the whales" Yeah. He put his coffee down. "That's exactly the thing we gamed out in March. Management killed the internal version on policy. Nobody outside the team should have shipped this yet" I asked what he was going to do. "Fly home and pretend I didn't see it" $600 seed. 31 days. Net +$35,200. 479 trades. 75% win rate. Sharpe 2.63. I haven't touched the bot in three weeks. Copytrade for those who don't want to build - Before boarding he slid a card across the table. "When the next agent model drops, rerun your prompt. You'll see what I mean"
0:27

Ran into an Anthropic engineer at an airport lounge in Frankfurt last month. SFO delayed six hours. Nothing to do. I had my laptop open. Bot running. Three agents scoring markets in the background. Guy sits two seats down. Glances at my screen. Looks away. Looks back. "Is that Polymarket?" I said yeah. "You're running it with Claude Code?" I nodded. He pulled his chair closer. "I'm on the agent team. We stress-test this exact setup internally. You built it in your kitchen" I asked what stress-test meant. "Red team. We simulate what happens when someone gives Claude raw wallet data and tells it to find the winners. You're running the thing we were scared about" I showed him the scanner. One prompt. Find every wallet with 100 plus trades, 70 plus win rate. Rank by profit. Export top 50. Claude chewed through 14,000 wallets in under 4 minutes. Came back with 47. Top 20 made more than the bottom 13,000 combined. "That's not a distribution. That's a hit list" I said yeah. "And the scoring function?" Claude wrote it. I just wrapped it in an if-statement. A fill landed on screen mid-conversation. +$128 on an ETH dominance market. He stared at it. "How does it decide to enter" Three agents. Shared wallet. No shared memory. Arbitrage, convergence, whale copy. 2 of 3 agree, full size. 1 alone, half. Disagree, no trade. That consensus filter alone killed 40% of losing trades. "And the exit" The 47 whales never hold to settlement. 91% exit early. Capture 73% of max. I cut at 85% of the expected move. Or a 3x volume spike. Whichever comes first. "So you built a whale copy bot that exits before the whales" Yeah. He put his coffee down. "That's exactly the thing we gamed out in March. Management killed the internal version on policy. Nobody outside the team should have shipped this yet" I asked what he was going to do. "Fly home and pretend I didn't see it" $600 seed. 31 days. Net +$35,200. 479 trades. 75% win rate. Sharpe 2.63. I haven't touched the bot in three weeks. Copytrade for those who don't want to build - Before boarding he slid a card across the table. "When the next agent model drops, rerun your prompt. You'll see what I mean"

rari

618,409 次观看 • 2 个月前

Anthropic engineer stops me in a hallway at a conference and points at my screen. "Are you the one running the Polymarket bot on Claude Code?" I say maybe. He looks back at the terminal. "This thing is live?" Yeah. He laughs. "We built Claude to write code. You people immediately turned it into a market animal." I ask what gave it away. "The layout," he says. "Official CLI on one side. Orderbook on the other. You’re not paper trading." He was right. I show him the stack. - official CLI. Rust. Scanning markets, placing orders, no UI tax. Claude Code on top of it. No giant infra. No team. Just prompts, a terminal, and a model that’s better at reading weird edge cases than most interns. "What’s the loop," he asks. "Short horizon only," I tell him. "Scan for contracts under 48h. Pull structure. Look for mispriced panic. Feed the market state to Claude. Let it decide if the crowd is overreacting or just early." "And execution?" "Three commands and the order is live." He nods. Profile bot: "That’s the part people miss. Everyone thinks the alpha is the model. The alpha is the model plus an execution path short enough that you don’t talk yourself out of the fill." A market flips while we’re standing there. +118. He sees it print. "Jesus." I keep going. "Most people use Claude Code to save time writing wrappers. Fine. But the real trick is that it reads messy market context better than brittle rule systems. News fragments. weird phrasing. half-broken incentives. Retail panic. You can feel the model noticing when the tape smells wrong." He smiles at that. "So what’s the cost." "$25 a month." He laughs again. "We spend more than that on lunch." Copytrade here: I show him the numbers. 214 trades. 74% win rate. +$9,437 in 19 days. He goes quiet for a second. "OpenAI people will say use Codex. Quant guys will say build a proper system. Old traders will say this isn’t robust." I shrug. "It placed the order." That’s when he gives me the line I kept. "Anthropic made Claude. GitHub did the rest." Then he taps the CLI window one more time. "Keep it ugly," he says. "The second you wrap this in a beautiful dashboard, someone upstairs will understand how little infrastructure the edge actually needed."
0:20

Anthropic engineer stops me in a hallway at a conference and points at my screen. "Are you the one running the Polymarket bot on Claude Code?" I say maybe. He looks back at the terminal. "This thing is live?" Yeah. He laughs. "We built Claude to write code. You people immediately turned it into a market animal." I ask what gave it away. "The layout," he says. "Official CLI on one side. Orderbook on the other. You’re not paper trading." He was right. I show him the stack. - official CLI. Rust. Scanning markets, placing orders, no UI tax. Claude Code on top of it. No giant infra. No team. Just prompts, a terminal, and a model that’s better at reading weird edge cases than most interns. "What’s the loop," he asks. "Short horizon only," I tell him. "Scan for contracts under 48h. Pull structure. Look for mispriced panic. Feed the market state to Claude. Let it decide if the crowd is overreacting or just early." "And execution?" "Three commands and the order is live." He nods. Profile bot: "That’s the part people miss. Everyone thinks the alpha is the model. The alpha is the model plus an execution path short enough that you don’t talk yourself out of the fill." A market flips while we’re standing there. +118. He sees it print. "Jesus." I keep going. "Most people use Claude Code to save time writing wrappers. Fine. But the real trick is that it reads messy market context better than brittle rule systems. News fragments. weird phrasing. half-broken incentives. Retail panic. You can feel the model noticing when the tape smells wrong." He smiles at that. "So what’s the cost." "$25 a month." He laughs again. "We spend more than that on lunch." Copytrade here: I show him the numbers. 214 trades. 74% win rate. +$9,437 in 19 days. He goes quiet for a second. "OpenAI people will say use Codex. Quant guys will say build a proper system. Old traders will say this isn’t robust." I shrug. "It placed the order." That’s when he gives me the line I kept. "Anthropic made Claude. GitHub did the rest." Then he taps the CLI window one more time. "Keep it ugly," he says. "The second you wrap this in a beautiful dashboard, someone upstairs will understand how little infrastructure the edge actually needed."

Lunar

19,326 次观看 • 2 个月前

Boris Cherny, the creator of Claude Code, just explained why the features most users never find are the ones that matter most in this podcast he breaks down not just how to use Claude, but what it all means for the next few years: > the right way to give Claude context before it starts working > why giving it too much information is just as bad as too little > how Claude Code is already changing how engineers build things > how the people who built Claude actually use it day to day based on this podcast and months of using Claude myself, I put together a guide on everything Claude can do that most people have no idea exists you can find it below
1:22:03

Boris Cherny, the creator of Claude Code, just explained why the features most users never find are the ones that matter most in this podcast he breaks down not just how to use Claude, but what it all means for the next few years: > the right way to give Claude context before it starts working > why giving it too much information is just as bad as too little > how Claude Code is already changing how engineers build things > how the people who built Claude actually use it day to day based on this podcast and months of using Claude myself, I put together a guide on everything Claude can do that most people have no idea exists you can find it below

Anatoli Kopadze

22,412 次观看 • 1 个月前

An Anthropic researcher sat down next to me at a hackathon last week. Claude Opus 4.7 was running 4 agents on my laptop. Live. No manual input. She looked at the terminal and said: "What is this?" I showed her. 4 agents. 678 trades. 81% win rate. $16,200 last 30 days. She worked on the evals team. She'd never seen Claude pointed at 88 million on-chain trades. The setup is 3 public repos. All free. -> 88 million Polymarket trades. Every wallet. Every entry. Every exit. Every resolution. -> the framework that bridges Claude Opus 4.7 directly to live markets. Order placement, position tracking, exit timing. -> real-time WebSocket order book. Depth on both sides. No polling, no lag. Four agents. One loop. Agent 1 identifies which wallets win consistently across 88 million trades. Agent 2 reverse-engineers their entry timing. Agent 3 monitors order book volume spikes. Agent 4 sizes positions using Kelly. No overbet. Drawdown capped at 1.4% over 678 trades. 85% of windows get killed. No trade. The bot only enters when 3 signals align: -> Elite wallet consensus pointing the same direction. -> Price divergence with Binance and Coinbase both agreeing. -> Order book imbalance confirming the bias. Single-source price data was 57% accurate. All three together: 81%. Exit before resolution. Always. Losers hold to 0 or $1. The agents copy their exits. The agents don't gamble on that. My stack: Claude Opus 4.7 at $19/mo, VPS Hetzner at $4.99/mo, Everything else free. Total stats: $23.99/month. 30 days: 678 trades, 81% win rate, net +$16,200, max drawdown -1.2%, avg hold 4h 12m. She asked if Anthropic could test this internally. "We run Claude on benchmarks and evals. Nobody pointed it at a live market dataset with 88 million rows." Claude Opus 4.7 didn't need a system prompt. It read the wallet index, understood the signal structure, and wrote the combiner logic in one pass. The people who built the model hadn't thought to point it at this data. I had. Copy the live trades: -> all 4 agents run 24/7. The window is open right now. Save this, follow me and comment OPUS. I will send the guide to you.
0:26

An Anthropic researcher sat down next to me at a hackathon last week. Claude Opus 4.7 was running 4 agents on my laptop. Live. No manual input. She looked at the terminal and said: "What is this?" I showed her. 4 agents. 678 trades. 81% win rate. $16,200 last 30 days. She worked on the evals team. She'd never seen Claude pointed at 88 million on-chain trades. The setup is 3 public repos. All free. -> 88 million Polymarket trades. Every wallet. Every entry. Every exit. Every resolution. -> the framework that bridges Claude Opus 4.7 directly to live markets. Order placement, position tracking, exit timing. -> real-time WebSocket order book. Depth on both sides. No polling, no lag. Four agents. One loop. Agent 1 identifies which wallets win consistently across 88 million trades. Agent 2 reverse-engineers their entry timing. Agent 3 monitors order book volume spikes. Agent 4 sizes positions using Kelly. No overbet. Drawdown capped at 1.4% over 678 trades. 85% of windows get killed. No trade. The bot only enters when 3 signals align: -> Elite wallet consensus pointing the same direction. -> Price divergence with Binance and Coinbase both agreeing. -> Order book imbalance confirming the bias. Single-source price data was 57% accurate. All three together: 81%. Exit before resolution. Always. Losers hold to 0 or $1. The agents copy their exits. The agents don't gamble on that. My stack: Claude Opus 4.7 at $19/mo, VPS Hetzner at $4.99/mo, Everything else free. Total stats: $23.99/month. 30 days: 678 trades, 81% win rate, net +$16,200, max drawdown -1.2%, avg hold 4h 12m. She asked if Anthropic could test this internally. "We run Claude on benchmarks and evals. Nobody pointed it at a live market dataset with 88 million rows." Claude Opus 4.7 didn't need a system prompt. It read the wallet index, understood the signal structure, and wrote the combiner logic in one pass. The people who built the model hadn't thought to point it at this data. I had. Copy the live trades: -> all 4 agents run 24/7. The window is open right now. Save this, follow me and comment OPUS. I will send the guide to you.

slash1s

46,274 次观看 • 3 个月前