Загрузка видео...

Не удалось загрузить видео

На главную

this is rare f*cking gold an internal AI engineering document leaked. it's saving solo devs $300,000 a year that number is just the three hires you never make: the one who writes the spec, the one who reviews the output, the one who runs the queue prompt-driven is out....

26,968 просмотров • 22 дней назад •via X (Twitter)

Комментарии: 6

Фото профиля Garv Sanwariya
Garv Sanwariya22 дней назад

the reviewer role is where people get stuck. are you running verification as an isolated sub-agent or in the same session?

Фото профиля かな
かな21 дней назад

フォロー失礼します

Фото профиля Darshan 👨‍💻💻
Darshan 👨‍💻💻21 дней назад

It's good but what it's doing bad task and not monitored/reviewed ? What if we want to roll back to the point it's good like tagging

Фото профиля 𝑨𝒇𝒓𝒊𝒏
𝑨𝒇𝒓𝒊𝒏22 дней назад

saving that $300k really makes sense if you cut the spec writer, reviewer and queue runner out

Фото профиля sophia v
sophia v21 дней назад

Great point!

Фото профиля Xpress
Xpress22 дней назад

the queue is where this gets real. one bad task sitting at the head can make every green worker look broken, so i want queue age and the oldest item on the dashboard, not just throughput.

Похожие видео

Automation engineer sent two AI to war. One fights to place the trade. The other fights to prove it's a mistake. Only what survives the battle gets his money - $392,000 profit of it so far. He doesn't pick the trades anymore. He built loop and stepped back. His wallet: The article below explains why that second AI, the one whose only job is to say no - is the entire game. Without a real check, you don't have a loop. You have a model agreeing with itself until the account's empty. He builds these loops for a living - agents that ship code and run themselves. One weekend he built one that trades. Here's how the war actually plays out. The maker reads the 5-minute candle and builds a case: buy Up, here's why. The checker has one purpose - break that case. Wrong regime, thin edge, bad timing. Poke one hole and the trade dies on the spot. Only the trades the checker can't kill ever reach the market. Every night the loop writes down which calls went wrong and tightens its own rules. It stops itself cold at the daily loss cap - nothing runs forever. $5,000 → $392,000. The checker vetoes far more trades than it lets through. That's the point. He didn't build a smarter bot. He built one that has to win an argument before it spends a dollar. Save this and read the breakdown below - it's the clearest explanation of loop engineering on your timeline, and it's the exact idea this whole system runs on. Or skip the build: the loop's live right now, two AI arguing over the next candle. Two clicks and its winners land in your wallet too:

cvxv666

42,548 просмотров • 3 месяцев назад

HOW TO USE AI LOOPS TO RUN YOUR BUSINESS 24/7 A lot has been written about loop engineering for building products. Almost nothing about using loops to run the business itself. That's the bigger idea. A loop is when you give an agent a goal, a way to check its own work, and permission to keep trying until it hits that goal. Build. Verify. Repeat. Stop when the condition is met. Here's what it looks like in practice: 1/SEO loop You're position 30 for a term you want. The loop runs once a month, makes changes, checks where you rank, and keeps pushing until you're on page one. This is running in production right now on Inbox Zero. 2/Ads loop You're spending $100 a day and losing money. The loop tests creative, checks profitability, kills what fails, and keeps going until the account is in the black. 3/Eval loop Your AI feature is only 88% accurate. The loop keeps adjusting the prompt and swapping the model until it passes 90%. 4/LLM visibility loop People search in ChatGPT now, not just Google. Same loop, new scoreboard. Are we the answer or not? The whole thing hinges on one thing: a metric that comes back black and white. Where do I rank? Did it hit profitability? Did the evals pass? Give an agent that scoreboard and it runs for months. Loops used to run for 30 minutes. These run for a year. Take a step, sleep, wake up next month, take another one. You're basically hiring an agency that never sleeps, gets paid in tokens instead of invoices, and undoes its own mistakes when the number goes down. Full episode on The Startup Ideas Podcast (SIP) 🧃 watch

GREG ISENBERG

83,349 просмотров • 2 месяцев назад

BlackRock runs on 20,000 people. Elon's Grok Bot runs the same shape for $300 a month, and it hires its own staff. You do not get an assistant. You get a company that hires. It does not throw ten agents at your problem and hand you the pile. It makes one agent that makes 10, and those ten make a 100. > LAYER ONE is one agent, the chief of staff, and it never touches the market > LAYER TWO is six desk heads, one job each, every one on its own computer with its own logins > LAYER THREE is whatever those six decide they need, spun up on the spot and shut down when the work is done Nobody writes a task list. You hand out job titles and the org fills itself in underneath. The swarm is never the same twice. Agents get spun up for one job, finish it, and are gone before I ever read their names. Not one of them sees the whole picture. The answer only exists after they hand off to each other. Wall Street cannot copy that. You cannot hire a hundred people for eleven minutes. BlackRock holds that shape together with a risk system called Aladdin. Mine holds it together with one agent that is only allowed to say no. I gave it $1,000 and told it to grow the money or get deleted. 15 hours later it was holding $3,900, on an address anyone can open and read. I was asleep for most of it, and I have still not written a line of code. The whole thing runs with my laptop shut, because none of it lives on my laptop. Setup is one evening. Create the chief, hand out the titles, run one trade on your screen while they watch, connect Telegram. Ten years ago a machine this shape had its name on a tower. Mine has a name I typed into a box. Save this while the whole thing still fits on one screen.

cvxv666

45,488 просмотров • 1 месяц назад

Someone just posted the full blueprint for an AI swarm that does the job of a 200-person quant research team. Six agents. Running 24/7. Finding brand-new alpha while you sleep. Citadel needs 100 PhDs to do this. Two Sigma needs 200. This does it with six bots and one laptop. Two ways to play this - spend a weekend building your own swarm, or copy the wallet of one that's already up $2M: Boris Cherny runs Claude Code at Anthropic. Two weeks ago he said: "I don't prompt Claude anymore. I have loops running that prompt Claude. My job is to write loops" Alpha research is just a pipeline. So instead of sitting in it, you hand each stage to its own agent: > one reads every new research paper overnight and pulls out the trade idea > one builds the features and cleans the data > one backtests it over 20 years, costs and slippage included > one runs the hard stats and kills anything overfit > one checks it still works in every market regime > one strips out plain momentum and value to see if any real edge is left Each of those six is a job a fund pays a $600,000-a-year quant to do. He runs all six for the price of an API bill. The rule that makes it work: the agent that builds a signal never gets to approve it. A separate, stronger agent tries to kill it first. Whatever survives all six by morning is real, new alpha. One trader's already running this exact swarm on Polymarket. That $2M wallet is public, every trade on-chain. The full build is in the post below - six agents, the tool that runs them, and the five mistakes that kill most people. Bookmark & read this before it's buried.

cvxv666

104,237 просмотров • 3 месяцев назад