Загрузка видео...

Не удалось загрузить видео

На главную

OPUS 5.5 + DOTS + JEV closed 312 tickets in one week while 25 engineers closed 96... that org chart costs $343,750 a month in payroll the agent costs $2,055 a month in tokens, 167x less the code comes from Opus 5.5, the tests from Dots, and nothing reaches...

Sprytixl's profile picture

Sprytix

8,388 subscribers

18,764 просмотров • 6 дней назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 5

Фото профиля Egor
Egor6 дней назад

the 41% comparison covers coding time, not the full engineering role

Фото профиля BreezeOg
BreezeOg5 дней назад

312 tickets is a serious gap but the payroll math is the wild part

Фото профиля magsimich
magsimich5 дней назад

Hype of opus 5.5 is really insane

Фото профиля jimerrors
jimerrors6 дней назад

数据很唬人，但有个细节值得抠一下：这 312 个工单里简单重复型占多少？人和 AI 接的工单难度分布一样吗？很多这类对比都是拿 AI 跑低难度工单去比工程师全量，口径不对齐。再就是关闭的定义，自动关和人工复核关差很多。

Фото профиля Enzo
Enzo6 дней назад

Your own numbers make the opposite point: if only 41% of engineering time is writing code, the agent replaces 41% of work, not 25 engineers. The other 590 hours (review, on call, customers deciding) are still sitting there.

Похожие видео

OPUS 5.5 + SONNET 5.5 + JEV + OPENAI DOTS: one spider pulled 40 AI engineers out of them and put a business on autopilot 40 seats, 4 teams of 10, and every seat is filled by a model a human team of 40 covers 1,600 hours a week. these seats stay on for all 168, which is 6,720 hours, 4.2x more from the same headcount at $13,750 a seat, 40 human engineers cost $550,000 a month in payroll before anyone writes a line of code the web under them has 16 threads: sales, leads, ads, CRM, support, billing, finance, legal, hiring and 7 more a task lands on any thread, and 10 routing engineers on Jev decide which agent gets it 10 planners on Opus 5.5 keep the roadmap and review the work in plan.md, while 10 builders on Sonnet 5.5 ship code every day from build py 10 more on OpenAI Dots run ops and never switch off, 24/7 the counter stops at 40 of 40, the status flips to live, and autopilot turns on ↓
0:42

OPUS 5.5 + SONNET 5.5 + JEV + OPENAI DOTS: one spider pulled 40 AI engineers out of them and put a business on autopilot 40 seats, 4 teams of 10, and every seat is filled by a model a human team of 40 covers 1,600 hours a week. these seats stay on for all 168, which is 6,720 hours, 4.2x more from the same headcount at $13,750 a seat, 40 human engineers cost $550,000 a month in payroll before anyone writes a line of code the web under them has 16 threads: sales, leads, ads, CRM, support, billing, finance, legal, hiring and 7 more a task lands on any thread, and 10 routing engineers on Jev decide which agent gets it 10 planners on Opus 5.5 keep the roadmap and review the work in plan.md, while 10 builders on Sonnet 5.5 ship code every day from build py 10 more on OpenAI Dots run ops and never switch off, 24/7 the counter stops at 40 of 40, the status flips to live, and autopilot turns on ↓

Noisy

14,894 просмотров • 5 дней назад

ANTHROPIC LEAKED A FILE WHERE 4 AGENTS BUILD AN AI COMPANY IN 60 MINUTES THAT DOES $100K A MONTH i hunted this file for over 5 months, and inside it $0 of development gives you an AI business that pulled 70k+ in its first month product → growth → support → ops four departments, four pinned versions, and no agent ever reaches into another one's branch product on Sonnet 5 eats $2.57, growth on Opus 5.5 takes $1.00, support on Haiku 4.5 costs $0.22, ops on Opus 5.5 closes the hour for $0.80 the full hour across all four costs $4.59, and the most expensive department is cheaper than a coffee in 60 minutes twelve things exist that did not an hour earlier: the app, the API, the docs, the landing page, the ads, the emails, the help centre, billing, metrics and alerts three per department, and every one is a file, a page or a rule, not a slide with a plan payroll for four departments like this is $31,000 a month, the tokens are $450 the agents do the typing, deciding what to build is still on you 120 people at $99, 200 at $299, 29 at $999 make $100,651 a month the middle plan carries more than half the month, and it is what turns this into $1.2M a year the hour builds the company, the first customers decide whether it is one save this and paste it into Claude Code - let it stand up these 4 departments for you ↓
1:20

ANTHROPIC LEAKED A FILE WHERE 4 AGENTS BUILD AN AI COMPANY IN 60 MINUTES THAT DOES $100K A MONTH i hunted this file for over 5 months, and inside it $0 of development gives you an AI business that pulled 70k+ in its first month product → growth → support → ops four departments, four pinned versions, and no agent ever reaches into another one's branch product on Sonnet 5 eats $2.57, growth on Opus 5.5 takes $1.00, support on Haiku 4.5 costs $0.22, ops on Opus 5.5 closes the hour for $0.80 the full hour across all four costs $4.59, and the most expensive department is cheaper than a coffee in 60 minutes twelve things exist that did not an hour earlier: the app, the API, the docs, the landing page, the ads, the emails, the help centre, billing, metrics and alerts three per department, and every one is a file, a page or a rule, not a slide with a plan payroll for four departments like this is $31,000 a month, the tokens are $450 the agents do the typing, deciding what to build is still on you 120 people at $99, 200 at $299, 29 at $999 make $100,651 a month the middle plan carries more than half the month, and it is what turns this into $1.2M a year the hour builds the company, the first customers decide whether it is one save this and paste it into Claude Code - let it stand up these 4 departments for you ↓

Sprytix

25,783 просмотров • 13 дней назад

ANTHROPIC LEAKED A $4.2M FILE WHERE 4 AGENTS BUILD THE JEV SYSTEM IN 60 MINUTES, DOING $100K A MONTH four agents cost $0, and the system they assemble in an hour generates $100K a month scout → builder → critic → operator → JEV every agent is pinned to one exact model version, and none of them runs on "latest" the scout on Haiku 4.5 reads the market, the builder on Sonnet 5 builds everything, the critic on Opus 5 decides what ships the operator runs Haiku through the batch API at half price - the one agent that never has to hurry the builder takes 59% of the whole hour, because it's the one writing, and writing costs 5x more than reading short answers are cheap answers - and the whole economics rests on that one rule pin the versions in ROOT.md and next month JEV behaves exactly the same point it at "latest" and the model underneath updates quietly, no error, and the answers start to drift $100K a month is 334 customers at $299 four versions, one system - pin them and JEV stays JEV save this and paste it into Claude Code - let it build you these 4 agents ↓
1:28

ANTHROPIC LEAKED A $4.2M FILE WHERE 4 AGENTS BUILD THE JEV SYSTEM IN 60 MINUTES, DOING $100K A MONTH four agents cost $0, and the system they assemble in an hour generates $100K a month scout → builder → critic → operator → JEV every agent is pinned to one exact model version, and none of them runs on "latest" the scout on Haiku 4.5 reads the market, the builder on Sonnet 5 builds everything, the critic on Opus 5 decides what ships the operator runs Haiku through the batch API at half price - the one agent that never has to hurry the builder takes 59% of the whole hour, because it's the one writing, and writing costs 5x more than reading short answers are cheap answers - and the whole economics rests on that one rule pin the versions in ROOT.md and next month JEV behaves exactly the same point it at "latest" and the model underneath updates quietly, no error, and the answers start to drift $100K a month is 334 customers at $299 four versions, one system - pin them and JEV stays JEV save this and paste it into Claude Code - let it build you these 4 agents ↓

Sprytix

37,977 просмотров • 18 дней назад

They built an automated business making $2.4M with Opus 5 at 18 - and came to Stanford to show how to repeat it: 00:50 - Opus 5 automates an entire business in 60 minutes 21:34 - one agent replaces 50 Anthropic engineers 45:47 - one file in Claude Code launches a business making $120k a month without a team after watching I gave Claude Code one file - in 60 minutes the business was ready and in the first month $100k + save & watch - the article below shows how to go from first file in Claude Code to a business making $2.4M a year.
1:08:49

They built an automated business making $2.4M with Opus 5 at 18 - and came to Stanford to show how to repeat it: 00:50 - Opus 5 automates an entire business in 60 minutes 21:34 - one agent replaces 50 Anthropic engineers 45:47 - one file in Claude Code launches a business making $120k a month without a team after watching I gave Claude Code one file - in 60 minutes the business was ready and in the first month $100k + save & watch - the article below shows how to go from first file in Claude Code to a business making $2.4M a year.

Noisy

48,680 просмотров • 26 дней назад

OPUS 5.5 + DOTS + JEV backtested 1,840 trades over four years in one hour... three models built one agent in 55 minutes for $4.92, and an agency would quote the same scope at $120,000 write → feed → test → fence → ship Dario's Sonnet 5.5 writes the agent itself: the policy, the prompts and six tool integrations Sam Altman's OpenAI Dots bring the data, the retrieval and 240 test cases Jev fences it, caps it and ships it the agent goes up in six layers, policy first and deploy last, and no layer starts before the one under it exists then all 240 cases run through it once. 221 pass, 19 fail, 92% against a bar of 90% the 240 cases and the 90% bar were written before the build, and the 19 failures are listed in the file the quote is 800 hours at $150, so $120,000. policy and prompts alone are 120 hours, $18,000 the same six parts took 1.14M tokens and $4.92 nobody has paid that $120,000 yet, it's what someone would charge to build it and keeping the agent true costs $59,160 a year, $37,440 of that is a human reading 270 tickets a week six parts, 55 minutes, $4.92, quoted at $120,000 ↓
1:13

OPUS 5.5 + DOTS + JEV backtested 1,840 trades over four years in one hour... three models built one agent in 55 minutes for $4.92, and an agency would quote the same scope at $120,000 write → feed → test → fence → ship Dario's Sonnet 5.5 writes the agent itself: the policy, the prompts and six tool integrations Sam Altman's OpenAI Dots bring the data, the retrieval and 240 test cases Jev fences it, caps it and ships it the agent goes up in six layers, policy first and deploy last, and no layer starts before the one under it exists then all 240 cases run through it once. 221 pass, 19 fail, 92% against a bar of 90% the 240 cases and the 90% bar were written before the build, and the 19 failures are listed in the file the quote is 800 hours at $150, so $120,000. policy and prompts alone are 120 hours, $18,000 the same six parts took 1.14M tokens and $4.92 nobody has paid that $120,000 yet, it's what someone would charge to build it and keeping the agent true costs $59,160 a year, $37,440 of that is a human reading 270 tickets a week six parts, 55 minutes, $4.92, quoted at $120,000 ↓

Sprytix

19,560 просмотров • 6 дней назад

OPUS 5.5 + SONNET 5.5 + JEV + DOTS on one spider, and 90% of your work is gone... one spider reads 5,152 items across 6 sources that you never open: 2,140 emails, 1,204 CRM records, 860 slack messages nothing waits for you to write a prompt, because Dots is always on and owns the job 24/7 every item gets a decision from Jev in 81 ms, so all 5,152 take under 7 minutes: urgent or not, how risky, and 1 of 3 routes the routine work goes to Sonnet 5.5, 12 drafts in this run, 12 marked done, 0 written by you the whole time Opus 5.5 sleeps and wakes up for 1 hard case out of 5,152. the other 5,151 never wake it your share drops from 100% to 10%, the other 90% of your work is gone ↓
0:33

OPUS 5.5 + SONNET 5.5 + JEV + DOTS on one spider, and 90% of your work is gone... one spider reads 5,152 items across 6 sources that you never open: 2,140 emails, 1,204 CRM records, 860 slack messages nothing waits for you to write a prompt, because Dots is always on and owns the job 24/7 every item gets a decision from Jev in 81 ms, so all 5,152 take under 7 minutes: urgent or not, how risky, and 1 of 3 routes the routine work goes to Sonnet 5.5, 12 drafts in this run, 12 marked done, 0 written by you the whole time Opus 5.5 sleeps and wakes up for 1 hard case out of 5,152. the other 5,151 never wake it your share drops from 100% to 10%, the other 90% of your work is gone ↓

Noisy

37,185 просмотров • 6 дней назад

ANTHROPIC LEAKED A $4.4M FILE WHERE 4 AGENTS BUILD A BUSINESS DOING $120K A MONTH IN 20 MINUTES four agents run for $0, and the business on top of them pulls $120,000 a month without a single salary scout → builder → seller → critic → back to the scout the scout finds who buys and at what price, the builder makes the page and the checkout the seller writes the offer and the outreach, the critic decides whether it ships at all Haiku 4.5 searches, two Sonnet 5 build and sell, Opus 5 passes the verdict no agent grades its own work - each one is checked by the next in the ring and the ring closes: the critic checks the scout one agent always gives itself an A, four in a ring never do a kickoff meeting alone takes 60 minutes, here the whole business is done in 20 $120,000 a month is 401 customers at $299 but all four come from one model family, and they share one blind spot the agents catch the errors at the edges, the one down the middle only you catch save this and paste it into Claude Code - let it build you this ring ↓
1:27

ANTHROPIC LEAKED A $4.4M FILE WHERE 4 AGENTS BUILD A BUSINESS DOING $120K A MONTH IN 20 MINUTES four agents run for $0, and the business on top of them pulls $120,000 a month without a single salary scout → builder → seller → critic → back to the scout the scout finds who buys and at what price, the builder makes the page and the checkout the seller writes the offer and the outreach, the critic decides whether it ships at all Haiku 4.5 searches, two Sonnet 5 build and sell, Opus 5 passes the verdict no agent grades its own work - each one is checked by the next in the ring and the ring closes: the critic checks the scout one agent always gives itself an A, four in a ring never do a kickoff meeting alone takes 60 minutes, here the whole business is done in 20 $120,000 a month is 401 customers at $299 but all four come from one model family, and they share one blind spot the agents catch the errors at the edges, the one down the middle only you catch save this and paste it into Claude Code - let it build you this ring ↓

Sprytix

43,407 просмотров • 19 дней назад

JEV + OPUS 5.5 IS INSANE FOR BUILDING A COMPANY BRAIN I pulled the whole architecture out of the TypeSafe and Anthropic docs and packed it into a 14-page PDF the 10 steps: 1. meet the pair > Opus 5.5 thinks, Jev decides, your code holds the branch 2. stop asking a text generator for a yes or no > Jev returns a typed answer with a calibrated probability in 0.44s for $0.00035 3. ask everything at once > Choice, Score and Noul run in parallel, so the fourth question costs almost nothing 4. branch on the number > 0.999 goes straight into the if statement. ~99% of turns end right here 5. stop routing blind > Opus 5.5 to Sonnet and back costs 5.84 against 3.32 for staying on 5.5 6. keep one context warm > cache reads at $0.20 per Mtok are 20x cheaper than a fresh load 7. escalate the hard part > the toughest 1% goes to Opus 5.5 with 1M context and 66.4% on Terminal-Bench 4.0 8. score every chunk on every query > keep whole, summarize or drop. the context gets rebuilt each turn 9. gate the actual command > every bash call gets classified before it runs, inside your own code 10. judge 100% of runs > $3.50 a day for 10,000 traces, and it matched the human label on all 500 decisions the result: a while loop that paid a frontier model for every tiny call turns into a brain that spends a fraction of a cent to notice and pays properly only when it has to think the person who brings this into their team walks into the budget meeting with the AI bill cut and the output up the PDF maps the company brain. the loop side of it - how Jev takes a Claude bill from $765 to $3 a month - is in the article below ↓
0:24

JEV + OPUS 5.5 IS INSANE FOR BUILDING A COMPANY BRAIN I pulled the whole architecture out of the TypeSafe and Anthropic docs and packed it into a 14-page PDF the 10 steps: 1. meet the pair > Opus 5.5 thinks, Jev decides, your code holds the branch 2. stop asking a text generator for a yes or no > Jev returns a typed answer with a calibrated probability in 0.44s for $0.00035 3. ask everything at once > Choice, Score and Noul run in parallel, so the fourth question costs almost nothing 4. branch on the number > 0.999 goes straight into the if statement. ~99% of turns end right here 5. stop routing blind > Opus 5.5 to Sonnet and back costs 5.84 against 3.32 for staying on 5.5 6. keep one context warm > cache reads at $0.20 per Mtok are 20x cheaper than a fresh load 7. escalate the hard part > the toughest 1% goes to Opus 5.5 with 1M context and 66.4% on Terminal-Bench 4.0 8. score every chunk on every query > keep whole, summarize or drop. the context gets rebuilt each turn 9. gate the actual command > every bash call gets classified before it runs, inside your own code 10. judge 100% of runs > $3.50 a day for 10,000 traces, and it matched the human label on all 500 decisions the result: a while loop that paid a frontier model for every tiny call turns into a brain that spends a fraction of a cent to notice and pays properly only when it has to think the person who brings this into their team walks into the budget meeting with the AI bill cut and the output up the PDF maps the company brain. the loop side of it - how Jev takes a Claude bill from $765 to $3 a month - is in the article below ↓

Mr. Buzzoni

103,282 просмотров • 11 дней назад

Most people use AI agents for themselves. He turned them into a business doing $50,000 a month. He's 20. Made $5,000 today. Doesn't code. He sells them to local businesses. The receptionist that never sleeps. The Google review machine that makes them the top result in their city. The reactivation agent that goes through years of old leads and wakes them up. Businesses pay for outcomes, not technology. A missed call after hours is a lost customer. An AI receptionist costs less than one lost deal. A marketing agency had 6 people doing manual ops work. $28,000/month. 5 Claude agents replaced 80% of it. $200/month in tools. The builder charges $2,500/month to maintain them. 8 clients. $20,000/month. Build once. Collect forever. He doesn't code. He sells the problem solved.
1:13

Most people use AI agents for themselves. He turned them into a business doing $50,000 a month. He's 20. Made $5,000 today. Doesn't code. He sells them to local businesses. The receptionist that never sleeps. The Google review machine that makes them the top result in their city. The reactivation agent that goes through years of old leads and wakes them up. Businesses pay for outcomes, not technology. A missed call after hours is a lost customer. An AI receptionist costs less than one lost deal. A marketing agency had 6 people doing manual ops work. $28,000/month. 5 Claude agents replaced 80% of it. $200/month in tools. The builder charges $2,500/month to maintain them. 8 clients. $20,000/month. Build once. Collect forever. He doesn't code. He sells the problem solved.

Superior

10,516 просмотров • 4 месяцев назад

ANTHROPIC LEAKED A FILE WHERE 10 BUSINESSES ASSEMBLE IN 24 HOURS, MAKE $100K + A MONTH AND COST $8 A DAY TOGETHER one of those 10 loops replaces a $2,000/month agency - and it runs for $1.80 a day. the routing never changes: Haiku at the door, Sonnet on the volume, Opus only where being wrong is expensive. Opus enters exactly 4 loops out of 10 - and in each of those four the mistake has a name: a fine, a misjudged tender, a missed contradiction, 21 drafts sold to nobody. the other 6 fail cheaply and just retry - that's the whole test for who gets the expensive model. competitive intel reads 200 pages for $0.40 and hands back one paragraph - a subscription to the same thing is $500 a month. lead scoring sees 300 signals and 12 get a real letter - the other 288 cost less than a cent between them. review monitoring runs at $0.35 and answers in 4 minutes - a human notices the same review 2 days later. the onboarding agent closes 38 questions out of 40 and hands 2 to a person - a loop that never escalates is a loop that's guessing. the compliance check finds the 4 lines that differ and rules on them for $1.50 - a consultant charges that per hour. all 10 together are $243 a month against the salaries they replace. save this and paste it into Claude Code - cheap at the door, expensive only where being wrong costs ↓
1:11

ANTHROPIC LEAKED A FILE WHERE 10 BUSINESSES ASSEMBLE IN 24 HOURS, MAKE $100K + A MONTH AND COST $8 A DAY TOGETHER one of those 10 loops replaces a $2,000/month agency - and it runs for $1.80 a day. the routing never changes: Haiku at the door, Sonnet on the volume, Opus only where being wrong is expensive. Opus enters exactly 4 loops out of 10 - and in each of those four the mistake has a name: a fine, a misjudged tender, a missed contradiction, 21 drafts sold to nobody. the other 6 fail cheaply and just retry - that's the whole test for who gets the expensive model. competitive intel reads 200 pages for $0.40 and hands back one paragraph - a subscription to the same thing is $500 a month. lead scoring sees 300 signals and 12 get a real letter - the other 288 cost less than a cent between them. review monitoring runs at $0.35 and answers in 4 minutes - a human notices the same review 2 days later. the onboarding agent closes 38 questions out of 40 and hands 2 to a person - a loop that never escalates is a loop that's guessing. the compliance check finds the 4 lines that differ and rules on them for $1.50 - a consultant charges that per hour. all 10 together are $243 a month against the salaries they replace. save this and paste it into Claude Code - cheap at the door, expensive only where being wrong costs ↓

Sprytix

12,603 просмотров • 1 месяц назад

CLAUDE CODE + GROK + JEV - THE FILE WHERE THREE HEADS CLOSE A TICKET IN 9 MINUTES FOR $1.74 a month of this costs $208.80, the same 120 merges by hand are 300 hours and $28,500 ticket → plan → patch → tests → review → merge Claude Code on Opus 5.5 writes the patch, Grok reads it back and argues, Jev holds the gate and merges only on green tests three heads, and not one of them is allowed to push code to prod on its own 38 files read, 3 touched, +412 lines, 48 tests, and the first four failed, so the patch went back two minutes twenty later it was 48 of 48, and only then did Jev open the gate out of 120 patches Claude Code and Grok signed off on 78 straight away and had a fight about the other 22 those 22 arguments are the product, because a reviewer that never objects is just decoration the meter clocked $208.80 for the month, and to catch the human bill it would have to keep running for another 136 months and here is the brutal part of this file: 6 of the 94 merged tickets came back with bugs every one of them sat in the part of the code the test suite has never read, because coverage there is 61% two models in the same blind spot is not two opinions, it is one mistake signed twice save this and paste it into Claude Code - let it run your ticket through these three heads ↓
1:11

CLAUDE CODE + GROK + JEV - THE FILE WHERE THREE HEADS CLOSE A TICKET IN 9 MINUTES FOR $1.74 a month of this costs $208.80, the same 120 merges by hand are 300 hours and $28,500 ticket → plan → patch → tests → review → merge Claude Code on Opus 5.5 writes the patch, Grok reads it back and argues, Jev holds the gate and merges only on green tests three heads, and not one of them is allowed to push code to prod on its own 38 files read, 3 touched, +412 lines, 48 tests, and the first four failed, so the patch went back two minutes twenty later it was 48 of 48, and only then did Jev open the gate out of 120 patches Claude Code and Grok signed off on 78 straight away and had a fight about the other 22 those 22 arguments are the product, because a reviewer that never objects is just decoration the meter clocked $208.80 for the month, and to catch the human bill it would have to keep running for another 136 months and here is the brutal part of this file: 6 of the 94 merged tickets came back with bugs every one of them sat in the part of the code the test suite has never read, because coverage there is 61% two models in the same blind spot is not two opinions, it is one mistake signed twice save this and paste it into Claude Code - let it run your ticket through these three heads ↓

Sprytix

12,400 просмотров • 8 дней назад

OPUS 5.5 + DOTS + JEV built an armed trading bot in 60 minutes for $6.80 three agents, 1.45M tokens, and the bot had a cap, a stop and a kill switch before its first order rules → data → backtest → armed Dario's Opus 5.5 writes the strategy and the risk rules Dots pulls and cleans four years of candles Jev backtests it, sets the caps and is the only one allowed to send an order six switches flip one after another: strategy spec, data, bot code, backtest, paper trade, caps and kill switch. only the sixth lets it trade Jev holds three limits: a $2,000 daily loss cap, a 4% max position and an armed kill switch the backtest replayed 1,840 trades over four years. 58% green, 31% a year, worst drawdown -22% then fees, spread and slippage eat 45% of that, and 31% on paper becomes 17% in life at 17% a year, $100,000 a month needs $7.06M of capital so the $100k comes from the capital, and the bot only cost $6.80 not one live dollar has traded yet. sixty minutes proved the bot runs, whether it earns is still open 60 minutes, $6.80, three agents, zero live trades ↓
0:51

OPUS 5.5 + DOTS + JEV built an armed trading bot in 60 minutes for $6.80 three agents, 1.45M tokens, and the bot had a cap, a stop and a kill switch before its first order rules → data → backtest → armed Dario's Opus 5.5 writes the strategy and the risk rules Dots pulls and cleans four years of candles Jev backtests it, sets the caps and is the only one allowed to send an order six switches flip one after another: strategy spec, data, bot code, backtest, paper trade, caps and kill switch. only the sixth lets it trade Jev holds three limits: a $2,000 daily loss cap, a 4% max position and an armed kill switch the backtest replayed 1,840 trades over four years. 58% green, 31% a year, worst drawdown -22% then fees, spread and slippage eat 45% of that, and 31% on paper becomes 17% in life at 17% a year, $100,000 a month needs $7.06M of capital so the $100k comes from the capital, and the bot only cost $6.80 not one live dollar has traded yet. sixty minutes proved the bot runs, whether it earns is still open 60 minutes, $6.80, three agents, zero live trades ↓

Sprytix

13,497 просмотров • 7 дней назад

A one-man trading hedge fund now costs about $100 a month in AI subscriptions. Five PhDs on a Citadel desk cost $270,000 a month, and that is the cheap end. That buys one tested idea a month. Man Group's AI writes hundreds of new signals a week, on a floor where the humans used to manage twenty in a quarter. Fifty AI agents do the reading and the writing. One of them exists only to destroy what the others build, and that one is the reason any of it works. Every job on that payroll is now an agent you can run yourself: > AI research agents reading filings, transcripts, options flow and on-chain data overnight, fifty personas at once, none of them allowed to see what the crowd is pricing > coding agent that turns one sentence of plain English into entry rules, exit rules, sizing and risk limits, then debugs itself until it runs > backtest agent that replays five years of that idea in about 12 seconds > breaker agent, an AI whose only job is killing the thing, at double the trading costs and in the ten worst markets that asset has ever seen > critic agent that reads your journal and names the mistake you keep making Nobody on that list asks for a bonus in January. $200 million is already run this way on one platform where 52,000 people mostly sit and watch the machine work. The full map of what is built and what is missing is in the article below. Bookmark & read it If you're not yet using AI in your trading and investing.
0:41

A one-man trading hedge fund now costs about $100 a month in AI subscriptions. Five PhDs on a Citadel desk cost $270,000 a month, and that is the cheap end. That buys one tested idea a month. Man Group's AI writes hundreds of new signals a week, on a floor where the humans used to manage twenty in a quarter. Fifty AI agents do the reading and the writing. One of them exists only to destroy what the others build, and that one is the reason any of it works. Every job on that payroll is now an agent you can run yourself: > AI research agents reading filings, transcripts, options flow and on-chain data overnight, fifty personas at once, none of them allowed to see what the crowd is pricing > coding agent that turns one sentence of plain English into entry rules, exit rules, sizing and risk limits, then debugs itself until it runs > backtest agent that replays five years of that idea in about 12 seconds > breaker agent, an AI whose only job is killing the thing, at double the trading costs and in the ten worst markets that asset has ever seen > critic agent that reads your journal and names the mistake you keep making Nobody on that list asks for a bonus in January. $200 million is already run this way on one platform where 52,000 people mostly sit and watch the machine work. The full map of what is built and what is missing is in the article below. Bookmark & read it If you're not yet using AI in your trading and investing.

cvxv666

173,490 просмотров • 1 месяц назад

ANTHROPIC LEAKED A FILE WHERE 5 AGENTS WITH JEV BUILD A $1.2M A YEAR SYSTEM IN 30 MINUTES you pay $3.70 and walk away with an asset that can do $1.2M a year repo → data model → API → UI → evals no layer starts until the one under it is closed, and that edge is what turns five scripts into a system the operator on Haiku 4.5 brings up the repo and CI, the architect on Opus 5 lays down the data model and migrations two builders on Sonnet 5 run API and UI in parallel, and the reviewer on Opus 5.5 can keep finished code out of prod the evals were sitting in the file before the first line of code existed at minute zero there was not a single file, by the end it is a working product with payments and tests five agents cover in half an hour what a human team bills for a quarter JEV hands one line between layers instead of the whole history, so the next agent never re-reads the project and the run costs $3.70 instead of $370 the build takes 30 minutes, the first customers show up weeks later save this and paste it into Claude Code - let it assemble those 5 layers for you ↓
1:20

ANTHROPIC LEAKED A FILE WHERE 5 AGENTS WITH JEV BUILD A $1.2M A YEAR SYSTEM IN 30 MINUTES you pay $3.70 and walk away with an asset that can do $1.2M a year repo → data model → API → UI → evals no layer starts until the one under it is closed, and that edge is what turns five scripts into a system the operator on Haiku 4.5 brings up the repo and CI, the architect on Opus 5 lays down the data model and migrations two builders on Sonnet 5 run API and UI in parallel, and the reviewer on Opus 5.5 can keep finished code out of prod the evals were sitting in the file before the first line of code existed at minute zero there was not a single file, by the end it is a working product with payments and tests five agents cover in half an hour what a human team bills for a quarter JEV hands one line between layers instead of the whole history, so the next agent never re-reads the project and the run costs $3.70 instead of $370 the build takes 30 minutes, the first customers show up weeks later save this and paste it into Claude Code - let it assemble those 5 layers for you ↓

Sprytix

14,208 просмотров • 14 дней назад

Do you understand what just got open sourced? 5,800+ quant trading strategies for FREE along with its CODEBASE i gave these trading strategies to opus 5.5 + jev and it built me a PROFITABLE 24/7 trading agent here is how to use the repo and build AI trading bot: 1. clone the vault and get 5,806 trading strategies (spot, perps, grid, stat arb and market making) 2. open any strategy file, the math, the parameters and the source are already inside 3. point AgenKit at that file inside Claude Code with model as opus 5.5, one command and it reads the spec as ground truth 4. it will run a full engineering team and ships a production bot with risk controls 5. Jev is the live brain, it answers buy sell or hold in 81 milliseconds, calibrated, no hallucination 6. your engine sizes the trade from that confidence and fires it before the next block 7. a hard risk layer holds every limit, nothing goes live until you approve it 8. every night Opus 5.5 reviews the fills and ships a better version, so the agent improves while you sleep one model THINKS, the other REACTS and a strategy that sat locked in a vault now trades itself 24/7 the COMPLETE codebase and the EXACT Opus 5.5 + Jev trading system which I am running is in the article below:
0:39

Do you understand what just got open sourced? 5,800+ quant trading strategies for FREE along with its CODEBASE i gave these trading strategies to opus 5.5 + jev and it built me a PROFITABLE 24/7 trading agent here is how to use the repo and build AI trading bot: 1. clone the vault and get 5,806 trading strategies (spot, perps, grid, stat arb and market making) 2. open any strategy file, the math, the parameters and the source are already inside 3. point AgenKit at that file inside Claude Code with model as opus 5.5, one command and it reads the spec as ground truth 4. it will run a full engineering team and ships a production bot with risk controls 5. Jev is the live brain, it answers buy sell or hold in 81 milliseconds, calibrated, no hallucination 6. your engine sizes the trade from that confidence and fires it before the next block 7. a hard risk layer holds every limit, nothing goes live until you approve it 8. every night Opus 5.5 reviews the fills and ships a better version, so the agent improves while you sleep one model THINKS, the other REACTS and a strategy that sat locked in a vault now trades itself 24/7 the COMPLETE codebase and the EXACT Opus 5.5 + Jev trading system which I am running is in the article below:

Roan

95,925 просмотров • 12 дней назад

This is f*cking insane. This Claude Code tip saved me thousands of dollars. once Opus 5.5 is your main model, stop burning it on work Sonnet 5.5 can do, while Fable 5.1 sits idle hand the grunt work to Sonnet 5.5 subagents and put Fable 5.1 on call run /advisor fable Opus 5.5 plans and ships the final code Sonnet 5.5 subagents read, edit and run the tests Fable 5.1 reads the full session, every tool call included, and only speaks up at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Sonnet 5.5 builds. Fable 5.1 reviews. Opus 5.5 ships Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big models only see the ones that split anyone still running one model for everything is paying Opus prices to decide whether a file exists - the full tree > Opus 5.5 on high runs the main session > explorer reads the code on Sonnet 5.5 > worker edits and runs tests on Sonnet 5.5 > researcher pulls the docs on Sonnet 5.5 > all three on medium > Fable 5.1 on call for main and every subagent paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: sonnet, effort: medium > Skip any that pin a different model and list them 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳
0:31

This is f*cking insane. This Claude Code tip saved me thousands of dollars. once Opus 5.5 is your main model, stop burning it on work Sonnet 5.5 can do, while Fable 5.1 sits idle hand the grunt work to Sonnet 5.5 subagents and put Fable 5.1 on call run /advisor fable Opus 5.5 plans and ships the final code Sonnet 5.5 subagents read, edit and run the tests Fable 5.1 reads the full session, every tool call included, and only speaks up at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Sonnet 5.5 builds. Fable 5.1 reviews. Opus 5.5 ships Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big models only see the ones that split anyone still running one model for everything is paying Opus prices to decide whether a file exists - the full tree > Opus 5.5 on high runs the main session > explorer reads the code on Sonnet 5.5 > worker edits and runs tests on Sonnet 5.5 > researcher pulls the docs on Sonnet 5.5 > all three on medium > Fable 5.1 on call for main and every subagent paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: sonnet, effort: medium > Skip any that pin a different model and list them 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

delost

48,238 просмотров • 6 дней назад

Claude Code tip: once Opus 5.5 is your main model, stop leaving Fable 5.1 sitting idle and stop burning Opus tokens on tasks Sonnet 5.5 can swarm put it on call with /advisor run /advisor fable Opus 5.5 plans and ships the code Sonnet 5.5 swarms the routine work at medium effort Fable 5.1 reads the full session, every tool call included, and only speaks up at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Fable 5.1 reviews. Sonnet 5.5 executes. Opus 5.5 ships Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big model only sees the ones that split Plan on high. Delegate on medium. Keep Fable on call. - the full tree > Opus 5.5 on high runs the main session > explorer reads the code > worker edits and runs tests > researcher pulls the docs > all three on Sonnet 5.5 at medium effort > Fable 5.1 on call as the advisor paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: sonnet, effort: medium > Skip any that pin a different model and list them 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, any variable that stops feature-flag fetching) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳
0:25

Claude Code tip: once Opus 5.5 is your main model, stop leaving Fable 5.1 sitting idle and stop burning Opus tokens on tasks Sonnet 5.5 can swarm put it on call with /advisor run /advisor fable Opus 5.5 plans and ships the code Sonnet 5.5 swarms the routine work at medium effort Fable 5.1 reads the full session, every tool call included, and only speaks up at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Fable 5.1 reviews. Sonnet 5.5 executes. Opus 5.5 ships Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big model only sees the ones that split Plan on high. Delegate on medium. Keep Fable on call. - the full tree > Opus 5.5 on high runs the main session > explorer reads the code > worker edits and runs tests > researcher pulls the docs > all three on Sonnet 5.5 at medium effort > Fable 5.1 on call as the advisor paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: sonnet, effort: medium > Skip any that pin a different model and list them 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, any variable that stops feature-flag fetching) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

mirku

421,226 просмотров • 10 дней назад

ANTHROPIC LEAKED A FILE THEIR LEAD ENGINEER SPENT 4 YEARS BUILDING AT A COST OF $3.2M - ONE SUPER AGENT WITH JEV HOLDS A BUSINESS DOING $2.4M A YEAR the agent costs $0, and in month one it's already pulling $100K+ read → decide → build → ship → watch → back to reading 24 cycles a day, and each one starts exactly where the last one stopped it doesn't sleep, doesn't forget and never asks what to do next in one night it runs more cycles than a team closes in a quarter JEV holds the context, the budget and the stop condition between hours - without it every cycle would start from zero it picks one change an hour, not twenty - which is exactly why nothing breaks if things get worse it rolls back on its own, no meeting and no explanation the price of the loop doesn't grow with the revenue: it's the same at $0 and at $200,000 a month $2.4M a year is 669 customers, and that's only true while all 669 keep paying every month one agent is one point of failure: the night the loop stopped, nobody noticed until morning it ships the changes, it doesn't find the customers - that part is still yours save this and paste it into Claude Code - let it build you this loop ↓
0:59

ANTHROPIC LEAKED A FILE THEIR LEAD ENGINEER SPENT 4 YEARS BUILDING AT A COST OF $3.2M - ONE SUPER AGENT WITH JEV HOLDS A BUSINESS DOING $2.4M A YEAR the agent costs $0, and in month one it's already pulling $100K+ read → decide → build → ship → watch → back to reading 24 cycles a day, and each one starts exactly where the last one stopped it doesn't sleep, doesn't forget and never asks what to do next in one night it runs more cycles than a team closes in a quarter JEV holds the context, the budget and the stop condition between hours - without it every cycle would start from zero it picks one change an hour, not twenty - which is exactly why nothing breaks if things get worse it rolls back on its own, no meeting and no explanation the price of the loop doesn't grow with the revenue: it's the same at $0 and at $200,000 a month $2.4M a year is 669 customers, and that's only true while all 669 keep paying every month one agent is one point of failure: the night the loop stopped, nobody noticed until morning it ships the changes, it doesn't find the customers - that part is still yours save this and paste it into Claude Code - let it build you this loop ↓

Sprytix

10,347 просмотров • 16 дней назад

This Chinese developer runs 9 agents on Claude Code under a GPT-5.5 orchestrator and they close 500 client tasks a month without a single assistant. His client work is closed without him, on a single laptop and only three subscriptions. The entire system lives on one MacBook Pro M4 with 128 GB of memory and subscriptions to Claude Code and GPT-5.5 cost him approximately $300 a month. There is no CRM, no team, no office only a terminal window with 9 parallel streams. The orchestrator works with a simple system prompt: «You are the orchestrator of a client inbox. Classify every incoming email into 4 categories: code, content, analysis, communication. Delegate to the corresponding worker agent. When the result is ready, check it for completeness, send it to the client on my behalf, and mark the task as closed. Do not ask clarifying questions.» And the orchestrator checks the inbox every 30 seconds, classifies fresh emails, and distributes them to 9 worker agents on Claude Code, each of whom is responsible for their own class of tasks. Here is an example of how one of them closes a request to refactor a client's auth module: Task: refactor user-auth module Broke the monolith into 3 files by responsibilities Added unit tests, coverage increased to 87% Renamed 4 functions to camelCase according to the style guide PR is ready for review, link below» And so about 50 cycles a day. By noon 25 tasks are closed, by dinner 50, and by the end of the month 500. On average, it takes about 7 minutes from the appearance of an email in the inbox to sending the result to the client. This is more than what a live team of 6 developers, copywriters and analysts working 8 hours a day closes. This is no longer an agency. This is a workstation where an orchestrator replaces a manager, and 9 worker agents replace the staff. The pipeline goes from inbox to closing 500 times a month without human participation at any step.
1:32

This Chinese developer runs 9 agents on Claude Code under a GPT-5.5 orchestrator and they close 500 client tasks a month without a single assistant. His client work is closed without him, on a single laptop and only three subscriptions. The entire system lives on one MacBook Pro M4 with 128 GB of memory and subscriptions to Claude Code and GPT-5.5 cost him approximately $300 a month. There is no CRM, no team, no office only a terminal window with 9 parallel streams. The orchestrator works with a simple system prompt: «You are the orchestrator of a client inbox. Classify every incoming email into 4 categories: code, content, analysis, communication. Delegate to the corresponding worker agent. When the result is ready, check it for completeness, send it to the client on my behalf, and mark the task as closed. Do not ask clarifying questions.» And the orchestrator checks the inbox every 30 seconds, classifies fresh emails, and distributes them to 9 worker agents on Claude Code, each of whom is responsible for their own class of tasks. Here is an example of how one of them closes a request to refactor a client's auth module: Task: refactor user-auth module Broke the monolith into 3 files by responsibilities Added unit tests, coverage increased to 87% Renamed 4 functions to camelCase according to the style guide PR is ready for review, link below» And so about 50 cycles a day. By noon 25 tasks are closed, by dinner 50, and by the end of the month 500. On average, it takes about 7 minutes from the appearance of an email in the inbox to sending the result to the client. This is more than what a live team of 6 developers, copywriters and analysts working 8 hours a day closes. This is no longer an agency. This is a workstation where an orchestrator replaces a manager, and 9 worker agents replace the staff. The pipeline goes from inbox to closing 500 times a month without human participation at any step.

Blaze

29,917 просмотров • 5 месяцев назад

Cursor pays engineers $1,100,000 a year to run teams of AI agents that ship code while they sleep. [The CEO of Cursor explained in 9 minutes how they ship at 100x speed using team of agents] ↓ Save this before everyone copies the playbook 1. Engineers no longer babysit one assistant. They manage dozens of agent colleagues working in parallel, each on its own remote machine 2. Validation contract before code, not after. Humans only at scoping and review. 3. The agent team handles the full loop : planning, coding, testing, shipping PRs with each agent specialised for a role. Watch the guide. Then read the guide below by Khairallah AL-Awady
9:37

Cursor pays engineers $1,100,000 a year to run teams of AI agents that ship code while they sleep. [The CEO of Cursor explained in 9 minutes how they ship at 100x speed using team of agents] ↓ Save this before everyone copies the playbook 1. Engineers no longer babysit one assistant. They manage dozens of agent colleagues working in parallel, each on its own remote machine 2. Validation contract before code, not after. Humans only at scoping and review. 3. The agent team handles the full loop : planning, coding, testing, shipping PRs with each agent specialised for a role. Watch the guide. Then read the guide below by Khairallah AL-Awady

Avid

638,269 просмотров • 4 месяцев назад