3:18Transcript
AI Trading Advice Fact Check, Part 2: The Backtest Receipts
Three viral AI trading rules tested against buy-and-hold, with original NexusTrade backtest receipts, fees, benchmarks and implementation limits.
NEXUSTRADE / VIDEOS
AI trading videos
Shorts I filmed while building NexusTrade.
Every video has a transcript.
152 shorts · every one transcribed
Backtesting videos
Start watching ↗3:18Transcript
2:43Transcript
AI Trading Bots: 3 Missing Pieces Before You Risk Real Money
Three checks for AI trading bots: realistic simulation, financial research, and decision trails, with real NexusTrade screens and a paper-bot event.
1:04Transcript
Claude Trading Strategies: I Tested SPY Timing Against Buy-and-Hold
Connect Claude to NexusTrade with MCP and compare an SPY 200-day moving-average backtest with buy-and-hold, including returns, drawdown and strategy rules.
1:50Transcript
Top 10 Stocks vs News Sentiment: Same 251% Return, Half the 2022 Loss
Does a news sentiment filter improve a top 10 stocks strategy? Same +251% return, a smaller 2022 loss, and why holding the top 20 did even better on drawdown.
1:01Transcript
$10,000: Pelosi’s Strategy vs. the S&P 500
A five-year animated race between a Pelosi-inspired strategy simulation and SPY with the same $10,000 starting capital, using public disclosures, stocks and modeled options.
1:22Transcript
What the Top Three Institutional Trackers Held
Explore Carvana, Bloom Energy, Alumis and other holdings behind the top three public-filing backtests on NexusTrade.
3:39Transcript
How to Backtest a TikTok Trading Strategy. The $20K Month Lost 49.8%.
I gave my AI a TikTok claiming $20,000 in one month from day trading. It turned the claim into a strategy and backtested it. The closest version lost 49.8%.
0:47Transcript
I Put $25,000 Into an AI Trading Strategy
Austin Starks puts $25,000 into an AI trading strategy, audits the backtests, and shares his Public Portfolio Challenge. Watch and explore the portfolio.
1:38Transcript
An engineer's walkthrough of a congressional filings paper bot
An engineer builds a paper strategy from delayed congressional disclosures with the NexusTrade SDK, from signal to deployment.
1:29Transcript
Build a paper trading strategy from congressional filings
Build a paper trading strategy with the NexusTrade SDK using delayed public congressional filings. Includes a clearly labeled simulated backtest.
2:14Transcript
Copying Politicians' Trades: Hickenlooper Lost 91%. Pelosi Made 261%.
Simulated disclosure bots since Sep 2021: Hickenlooper -91%, McConnell +90%, Nancy Pelosi +261%. The fork is a paper portfolio.
1:39Transcript
How My AI Trading Bot Decides What to Buy and Sell
The three steps an AI trading agent takes to pick trades: writing a deterministic rule, walk-forward testing it over four folds, and deploying it to paper or live.
2:10Transcript
Fact Check: 0DTE Iron Condor Strategy With Zero Losses
A 0DTE SPX iron condor creator claimed $30,000 and zero losing days in August. Codified his stated rules and backtested them on minute data: sixteen green sessions, four red, and $840,000 of collateral behind the claim.
0:47Transcript
Does RSI Work? I Analyzed 222,010 Trading Backtests
Does RSI work? Across 222,010 real backtests RSI ranked 23rd of the 34 indicators with at least 500 runs, and strategies using it had a 0.51 median Sharpe against 0.87 without it.
1:22Transcript
Claude Code Trading Strategy: 1,100% in 11 Years, and a 59% Drawdown
One command connected Claude Code to my backtest data. The rule it kept turned $10,000 into $119,942 over 11 years, with a 59% worst drawdown.
1:41Transcript
I fact-checked a day trading strategy with 423,000 views. It loses to doing nothing.
A day trading strategy with 423,900 views, coded by an AI agent and backtested on a year of minute data. Tuned and charged zero fees, it still lost 2.40% out of sample while the index gained 1.02%.
1:14Transcript
GPT-6 Astra Made My Rust Engine 9x Faster. Four Models Said Impossible.
Four AI models could not speed up my Rust backtesting engine. GPT-6 Astra named the problem, found a 2014 paper, and cut 470 seconds to 51 warm.
1:26Transcript
Why Is My Backtest So Slow? GPT-6 Astra Cut Mine to 51 Seconds.
My backtests took ten minutes. GPT-6 Astra profiled the Rust engine, cited a 2014 paper, and got the run down to 51 seconds on hardware I already owned.
1:24Transcript
Every Rule My AI Trading Bot Follows Is Public. So Is the 12% Crash.
Every rule, backtest, crash and bug behind my $25,000 AI trading account is public. Here is what the live book actually did.
1:38Transcript
Buying the Five Largest Companies: A Market-Cap Strategy Backtest
Backtest a top-five market-cap strategy rebalanced every two weeks: $100,000 grew to $415,000 versus $246,000 for the S&P 500. See the rules, costs and drawdown.
2:06Transcript
AI Makes Doing the Impossible Possible
Austin explains how AI expanded the software he could build alone, using options backtesting and a large headline-research workload as examples. The animat
2:05Transcript
AI Makes the Impossible Possible: The Original Recording
In the original camera recording, Austin discusses how AI changes the scope of projects a solo software engineer can attempt, including options backtesting
0:47Transcript
Robinhood Agents Was Missing Backtesting. So I Built the Solution.
See how AI-created rules run through historical backtesting, then paper trading and a connected Robinhood account before moving live.
2:57Transcript
Why Trading Strategies Fail: You Shipped Version One
Learn why trading strategies fail after a great backtest, and how strategy variants, market regimes, and unseen-data validation improve your research process.