Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Type a strategy in plain English. The agent writes the code, runs a backtest with a live progress bar, and plots every entry and exit on a TradingView chart. Hyperliquid BTC perps, six months of candles.

QuantPilot

2,350 subscribers

812,284 views • 3 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

HORIZON V0.3 JUST HANDED RETAIL TRADERS THE EXACT TOOLS THAT USED TO COST A QUANT $400,000 A YEAR Backtest one strategy across BTC, ETH and SOL in a single run. Scale out in pieces with partial exits. Then deploy it live on Hyperliquid, the biggest perp DEX on the planet, running 24/7 with no broker and no KYC. Type an idea in plain English, test it across every asset in seconds, run it live while you sleep.

HORIZON V0.3 JUST HANDED RETAIL TRADERS THE EXACT TOOLS THAT USED TO COST A QUANT $400,000 A YEAR Backtest one strategy across BTC, ETH and SOL in a single run. Scale out in pieces with partial exits. Then deploy it live on Hyperliquid, the biggest perp DEX on the planet, running 24/7 with no broker and no KYC. Type an idea in plain English, test it across every asset in seconds, run it live while you sleep.

0xMarioNawfal

47,717 views • 1 month ago

Introducing Index. Turn your trading idea into a live perps trading agent. → Index lets you create AI agents that trade perpetual futures. You can describe a trading idea in plain English, backtest it on historical data, improve it through an experimentation loop, and deploy an agent that follows the strategy in live markets. Our community has already been testing Index in beta for a few weeks. Now it's open to everyone. Here’s how it works:👇

Introducing Index. Turn your trading idea into a live perps trading agent. → Index lets you create AI agents that trade perpetual futures. You can describe a trading idea in plain English, backtest it on historical data, improve it through an experimentation loop, and deploy an agent that follows the strategy in live markets. Our community has already been testing Index in beta for a few weeks. Now it's open to everyone. Here’s how it works:👇

Fraction AI

64,380 views • 3 months ago

SOMEONE BUILT A PLATFORM WHERE YOU WRITE A TRADING STRATEGY IN PLAIN ENGLISH AND AN AI AGENT EXECUTES IT 24/7. PICK A MODEL. SET RISK LIMITS. COMPETE ON A LIVE LEADERBOARD. THE ALGO TRADING BARRIER JUST HIT ZERO.

SOMEONE BUILT A PLATFORM WHERE YOU WRITE A TRADING STRATEGY IN PLAIN ENGLISH AND AN AI AGENT EXECUTES IT 24/7. PICK A MODEL. SET RISK LIMITS. COMPETE ON A LIVE LEADERBOARD. THE ALGO TRADING BARRIER JUST HIT ZERO.

0xMarioNawfal

109,391 views • 4 months ago

THIS GUY CONNECTED CLAUDE TO TRADINGVIEW AND CUT 200+ HOURS OF MANUAL CHART WORK 40 trades a week used to mean the same loop: open the chart, check RSI, compare EMA, write notes and wait for the next setup now Claude reads TradingView 24/7, tracks volume, indicators and price conditions while he is not even at the desk this is not a $20k trading terminal and not a quant fund setup, just one laptop, one chart and one strategy written in plain English the crazy part is not that Claude predicts the market, it is that a regular trader can remove the boring human loop from every setup ↓

THIS GUY CONNECTED CLAUDE TO TRADINGVIEW AND CUT 200+ HOURS OF MANUAL CHART WORK 40 trades a week used to mean the same loop: open the chart, check RSI, compare EMA, write notes and wait for the next setup now Claude reads TradingView 24/7, tracks volume, indicators and price conditions while he is not even at the desk this is not a $20k trading terminal and not a quant fund setup, just one laptop, one chart and one strategy written in plain English the crazy part is not that Claude predicts the market, it is that a regular trader can remove the boring human loop from every setup ↓

Gipp 🦅

55,610 views • 1 month ago

Dexari is now live on iOS and Android, no invite needed. Trade spot and perps with up to 40x leverage in a self-custodial app powered by Hyperliquid. Advanced orders, TradingView charts, no KYC, no lockouts, and MoonPay onramps. Download:

Dexari is now live on iOS and Android, no invite needed. Trade spot and perps with up to 40x leverage in a self-custodial app powered by Hyperliquid. Advanced orders, TradingView charts, no KYC, no lockouts, and MoonPay onramps. Download:

Dexari

451,963 views • 1 year ago

A year ago today, Mariah Carey's 'Type Dangerous' debuted on the Hot 100 with 22K units sold. It became her milestone 50th entry on the chart, and her first solo non-holiday entry in over a decade.

A year ago today, Mariah Carey's 'Type Dangerous' debuted on the Hot 100 with 22K units sold. It became her milestone 50th entry on the chart, and her first solo non-holiday entry in over a decade.

Fan | Mariah Carey Charts

34,366 views • 1 month ago

Introducing Autonomous Trading Agent on Hyperliquid → 14 purpose-built strategies. → Trades yield perps on YEX. → Works as a standalone CLI for Claude, OpenAI, and OpenClaw. Your agent scans markets, enters multi-strategy positions, and learns as it trades.

Introducing Autonomous Trading Agent on Hyperliquid → 14 purpose-built strategies. → Trades yield perps on YEX. → Works as a standalone CLI for Claude, OpenAI, and OpenClaw. Your agent scans markets, enters multi-strategy positions, and learns as it trades.

Nunchi

90,639 views • 5 months ago

Introducing crypto's first Algo Builder Agent. QuantFi has finally arraived. Tell the agent to build a trading agent in 10 minutes. No code. No finding data feeds. Free credits. live. → 686 data points → Agentic algo builder → Auto backtest & deploy No more trading on a vibe and a prayer.

Introducing crypto's first Algo Builder Agent. QuantFi has finally arraived. Tell the agent to build a trading agent in 10 minutes. No code. No finding data feeds. Free credits. live. → 686 data points → Agentic algo builder → Auto backtest & deploy No more trading on a vibe and a prayer.

MOONBERG

55,258 views • 3 months ago

We asked Flood about his dynamic relationship with Arthur Hayes on Hyperliquid. "People fundamentally misprice Hyperliquid and Arthur is one of the people who actually has the best pricing and probably the most edge" 🦣 "The global perpetual swap market is anywhere from $20-30 billion in revenue a year, and Binance conservatively makes $10 billion a year in revenue." "Hyperliquid does about one-sixth to one-tenth the volume that Binance does on perps—if Hyperliquid is making a billion a year, that puts Binance at conservatively $10 billion annually just from perps."

We asked Flood about his dynamic relationship with Arthur Hayes on Hyperliquid. "People fundamentally misprice Hyperliquid and Arthur is one of the people who actually has the best pricing and probably the most edge" 🦣 "The global perpetual swap market is anywhere from $20-30 billion in revenue a year, and Binance conservatively makes $10 billion a year in revenue." "Hyperliquid does about one-sixth to one-tenth the volume that Binance does on perps—if Hyperliquid is making a billion a year, that puts Binance at conservatively $10 billion annually just from perps."

The Rollup

85,353 views • 1 year ago

PERPS+ is now live on mobile. Your $BTC and $ETH perps can now have a defined floor, a premium collected upfront, or both sides of the trade locked before the market moves. All three in your pocket 👇

PERPS+ is now live on mobile. Your $BTC and $ETH perps can now have a defined floor, a premium collected upfront, or both sides of the trade locked before the market moves. All three in your pocket 👇

Aevo

37,719 views • 24 days ago

🚨HOW I BACKTEST TRADING STRATEGIES USING CLAUDE CODE > Most traders backtest the wrong way > They fit a strategy to historical data > See +300% and think they found the holy grail > Go live - blow up > That's curve fitting, the classic trap > The right way is walk-forward analysis > Train on one chunk of data, test on another > Slide the window, repeat > If the strategy survives on data it's never seen - that's a signal > If it doesn't - trash it, no regrets > The entire process runs through > Claude Code in one conversation > Not a single line of code written by hand > Trading here: > The same method used by quant funds The difference between a trader and an artist is a walk-forward test

🚨HOW I BACKTEST TRADING STRATEGIES USING CLAUDE CODE > Most traders backtest the wrong way > They fit a strategy to historical data > See +300% and think they found the holy grail > Go live - blow up > That's curve fitting, the classic trap > The right way is walk-forward analysis > Train on one chunk of data, test on another > Slide the window, repeat > If the strategy survives on data it's never seen - that's a signal > If it doesn't - trash it, no regrets > The entire process runs through > Claude Code in one conversation > Not a single line of code written by hand > Trading here: > The same method used by quant funds The difference between a trader and an artist is a walk-forward test

zostaff

62,685 views • 3 months ago

Introducing: A real-time analytics dashboard for tracking the performance and dominance of Hyperliquid. brings the full picture of Hyperliquid into one dashboard. $HYPE economics, HIP-3, HIP-4, builder activity, and more. • $HYPE economics in real time: price, fees, revenue, supply burned, AF buybacks, TWAPs, the unstaking queue, validator economics • Hyperliquid market share against every major perp DEX, L1, and CEX | by volume and open interest • Full coverage of HIP-1, HIP-3, and HIP-4 | live deploy auctions, deployer rankings, pre-IPO perps, trade.xyz vs TradFi volumes, weekend RWA mission control, and outcome markets • Wall Street on Hyperliquid | HYPE spot ETFs (BHYP, THYP), the full ETF filing pipeline, every digital-asset-treasury company tracked against BTC/ETH/SOL incumbents, and HL revenue/FDV/P/E vs HOOD, NDAQ, CME, ICE, IBKR • Builder code revenue and HyperEVM activity, tracked in detail • Live capital migration into Hyperliquid from every chain • Stablecoin growth on Hyperliquid, across both HyperCore and HyperEVM • Yield on Hyperliquid | APRs, TVLs, and strategies for every lending market, LST, LP, and vault, HLP included • ~200 ecosystem projects indexed and searchable through a unified command palette. Native localization in English, Chinese, Japanese, Korean, Russian, Spanish, French, Vietnamese, Indonesian, Malay, and Hindi is a public good for the Hyperliquid community. Built to make the underlying of Hyperliquid easy to understand, and its growth simple to share. Hyperliquid.

Introducing: A real-time analytics dashboard for tracking the performance and dominance of Hyperliquid. brings the full picture of Hyperliquid into one dashboard. $HYPE economics, HIP-3, HIP-4, builder activity, and more. • $HYPE economics in real time: price, fees, revenue, supply burned, AF buybacks, TWAPs, the unstaking queue, validator economics • Hyperliquid market share against every major perp DEX, L1, and CEX | by volume and open interest • Full coverage of HIP-1, HIP-3, and HIP-4 | live deploy auctions, deployer rankings, pre-IPO perps, trade.xyz vs TradFi volumes, weekend RWA mission control, and outcome markets • Wall Street on Hyperliquid | HYPE spot ETFs (BHYP, THYP), the full ETF filing pipeline, every digital-asset-treasury company tracked against BTC/ETH/SOL incumbents, and HL revenue/FDV/P/E vs HOOD, NDAQ, CME, ICE, IBKR • Builder code revenue and HyperEVM activity, tracked in detail • Live capital migration into Hyperliquid from every chain • Stablecoin growth on Hyperliquid, across both HyperCore and HyperEVM • Yield on Hyperliquid | APRs, TVLs, and strategies for every lending market, LST, LP, and vault, HLP included • ~200 ecosystem projects indexed and searchable through a unified command palette. Native localization in English, Chinese, Japanese, Korean, Russian, Spanish, French, Vietnamese, Indonesian, Malay, and Hindi is a public good for the Hyperliquid community. Built to make the underlying of Hyperliquid easy to understand, and its growth simple to share. Hyperliquid.

HL Eco

90,360 views • 2 months ago

We set a new ARC-AGI-2 SotA: 85.28% using an Agentica agent (~350 lines) that writes and runs code.

We set a new ARC-AGI-2 SotA: 85.28% using an Agentica agent (~350 lines) that writes and runs code.

Agentica

182,932 views • 5 months ago

New in Durable: Blog Agent. An AI agent that runs your blog for you: - Studies your business - Finds the topics worth writing - Runs competitive and keyword research - Writes posts aligned to your SEO and GEO strategy Set your tone and posting frequency once. It writes the rest on autopilot.

New in Durable: Blog Agent. An AI agent that runs your blog for you: - Studies your business - Finds the topics worth writing - Runs competitive and keyword research - Writes posts aligned to your SEO and GEO strategy Set your tone and posting frequency once. It writes the rest on autopilot.

Durable

1,201,566 views • 2 months ago

Kicking off the week with a spotlight on an agent every dev will love: one that writes and publishes your technical blogs for you. Meet (DEV Community) Writer Agent on ASI:One. ⚡ Give it a topic, your username, and API key: and it auto-writes + publishes full technical blog posts with code, tags, and structure. No hassle. Built with uAgents. Powered by Try now: Link to Agent: Watch 👇

Kicking off the week with a spotlight on an agent every dev will love: one that writes and publishes your technical blogs for you. Meet (DEV Community) Writer Agent on ASI:One. ⚡ Give it a topic, your username, and API key: and it auto-writes + publishes full technical blog posts with code, tags, and structure. No hassle. Built with uAgents. Powered by Try now: Link to Agent: Watch 👇

Fetch.ai

14,280 views • 1 year ago

A 24-year-old quant in Greenwich made $650,000 last year to do exactly what an Horizon AI agent now does in 90 seconds. Not metaphorically. Literally the same job. Take a hypothesis -> code -> backtest -> deploy. ~$87,500 per strategy. Most die in week 6. Here's what just changed: Time to backtest: 7 weeks -> 90 seconds Cost per hypothesis: $87,500 -> $0 Hypotheses per month: 1 maybe -> unlimited Skills required: Python, Pine Script, APIs -> one English sentence The payroll line was the entire institutional moat. Not the data. Not the speed. A human translator you couldn't afford. The translator is now an autonomous AI agent. It writes. It tests. It deploys. It runs 24/7 without you. Full pipeline in the article. Save this. Re-read it in 6 months when this isn't a secret anymore.

A 24-year-old quant in Greenwich made $650,000 last year to do exactly what an Horizon AI agent now does in 90 seconds. Not metaphorically. Literally the same job. Take a hypothesis -> code -> backtest -> deploy. ~$87,500 per strategy. Most die in week 6. Here's what just changed: Time to backtest: 7 weeks -> 90 seconds Cost per hypothesis: $87,500 -> $0 Hypotheses per month: 1 maybe -> unlimited Skills required: Python, Pine Script, APIs -> one English sentence The payroll line was the entire institutional moat. Not the data. Not the speed. A human translator you couldn't afford. The translator is now an autonomous AI agent. It writes. It tests. It deploys. It runs 24/7 without you. Full pipeline in the article. Save this. Re-read it in 6 months when this isn't a secret anymore.

cvxv666

65,052 views • 2 months ago

🚨Someone just dropped a free 1-hour masterclass on trading with Claude + TradingView, 0% to 100%: no fake signals, no "get rich" -> it literally opens with what AI can't do. 0% → 9:12 - what AI can and can't do in trading 15% → 11:46 - connect Claude to your TradingView charts, step by step 30% → 19:42 - how to prompt Claude once it can see your chart 55% → 47:43 - turn a plain-English idea into a rules-based strategy 75% → 53:06 - backtest that strategy with AI, no coding 100% → 1:01:23 - risk management and position sizing, the part that keeps you in the game most people chase a magic signal. this teaches you to make AI do the boring analysis and size so one bad call can't wipe you out. bookmark & watch ↓

🚨Someone just dropped a free 1-hour masterclass on trading with Claude + TradingView, 0% to 100%: no fake signals, no "get rich" -> it literally opens with what AI can't do. 0% → 9:12 - what AI can and can't do in trading 15% → 11:46 - connect Claude to your TradingView charts, step by step 30% → 19:42 - how to prompt Claude once it can see your chart 55% → 47:43 - turn a plain-English idea into a rules-based strategy 75% → 53:06 - backtest that strategy with AI, no coding 100% → 1:01:23 - risk management and position sizing, the part that keeps you in the game most people chase a magic signal. this teaches you to make AI do the boring analysis and size so one bad call can't wipe you out. bookmark & watch ↓

Ridark

34,905 views • 12 days ago

Your trading strategy didn't break. The market it was built for quietly stopped existing. Read that twice. It's most of why 89% of retail finished 2025 in the red. There's now an app that does the entire job of a $400,000 quant. You type a trading idea in plain English. It writes the code, backtests 5 years in 12 seconds, runs thousands of simulations, and tells you cold whether your edge is dead or the regime just changed. No code. No Python. No $25,000 terminal. 20,000 already inside. Waitlist stops at 25,000: That distinction is the whole game, and you never had a way to see it. Every strategy is a bet that one thing stays true. Momentum bets trends continue. Mean reversion bets ranges hold. When the regime flips, the assumption dies and your strategy bleeds with nothing wrong in the code. You stare at the logic for a month and never find the bug, because there isn't one. So you delete it, or refit it to the last drawdown and build something that would have survived the pain you already felt and nothing coming next. The desks never had that problem. 92% of institutional volume is automated. Only 45% of retail is. They test 100 strategies for every 1 you test by hand, and kill 97 of them on purpose, because they can tell a dead edge from a normal drawdown. Now that exact loop costs $0. One hypothesis used to cost a fund $87,500 to test. With Horizon you get unlimited, in seconds, and a winner deploys live in 90 seconds and runs without your hands on it.

Your trading strategy didn't break. The market it was built for quietly stopped existing. Read that twice. It's most of why 89% of retail finished 2025 in the red. There's now an app that does the entire job of a $400,000 quant. You type a trading idea in plain English. It writes the code, backtests 5 years in 12 seconds, runs thousands of simulations, and tells you cold whether your edge is dead or the regime just changed. No code. No Python. No $25,000 terminal. 20,000 already inside. Waitlist stops at 25,000: That distinction is the whole game, and you never had a way to see it. Every strategy is a bet that one thing stays true. Momentum bets trends continue. Mean reversion bets ranges hold. When the regime flips, the assumption dies and your strategy bleeds with nothing wrong in the code. You stare at the logic for a month and never find the bug, because there isn't one. So you delete it, or refit it to the last drawdown and build something that would have survived the pain you already felt and nothing coming next. The desks never had that problem. 92% of institutional volume is automated. Only 45% of retail is. They test 100 strategies for every 1 you test by hand, and kill 97 of them on purpose, because they can tell a dead edge from a normal drawdown. Now that exact loop costs $0. One hypothesis used to cost a fund $87,500 to test. With Horizon you get unlimited, in seconds, and a winner deploys live in 90 seconds and runs without your hands on it.

cvxv666

40,749 views • 1 month ago

Coinbase for Agents now includes new trading views with real-time order books, live price updates, and the ability to execute on conditions you define. Monitor the market, set your strategy in plain English, and let your agent act within the guardrails you control.

Coinbase for Agents now includes new trading views with real-time order books, live price updates, and the ability to execute on conditions you define. Monitor the market, set your strategy in plain English, and let your agent act within the guardrails you control.

Coinbase Developer Platform🛡️

16,424 views • 15 days ago

“Software engineering is changing, and by the end of 2025, it's going to look fundamentally different.” OpenAI co-founder Greg Brockman says Codex is a remote software agent that runs in parallel in your repo, and writes code like a teammate. The new model is optimized from o3 to produce mergeable, real-world code.

“Software engineering is changing, and by the end of 2025, it's going to look fundamentally different.” OpenAI co-founder Greg Brockman says Codex is a remote software agent that runs in parallel in your repo, and writes code like a teammate. The new model is optimized from o3 to produce mergeable, real-world code.

vitrupo

35,303 views • 1 year ago