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.
NEXUSTRADE / VIDEOS
AI trading videos
Shorts I filmed while building NexusTrade.
Every video has a transcript.
52 shorts · every one transcribed
AI trading videos
Start watching ↗0:47Transcript
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%.
1:15Transcript
I let two AI agents trade $44,000 of my own money
Two AI trading agents manage $44,000 of Austin Starks' own money. The $25,000 Public Portfolio Challenge, the August strategy swap, and the paper control that measures it.
0:18Transcript
NVIDIA Is the Best Stock in History. Fifteen Trillion by 2030.
NVIDIA is the best stock in history. It is not too late and not too high. Fifteen trillion by 2030.
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.
1:15Transcript
Is NexusTrade legit? Does NexusTrade work?
Is NexusTrade legit? Austin Starks shows the public record: Coinbase, Figma, Carnegie Mellon, Cornell, 1.6M lines of code, and $25,000 of his own money in a live book.
0:36Transcript
20 things to do before you deploy an AI trading bot
Before deploying an AI trading bot, review this checklist covering data bias, overfitting, walk-forward analysis, backtesting, and paper trading.
0:32Transcript
20 steps to build a trading strategy that actually works
A 20-step process for developing a trading strategy: backtesting, inspecting backtest events, walk-forward optimization, out-of-sample testing, and paper trading.
0:26Transcript
How I Made $400K a Year as a Senior AI Engineer
Senior AI engineer Austin Starks on making $400k a year in big tech, the W-2 that proves it, and how he helps students land the same jobs.
1:21Transcript
How I Used AI to Code a Feature. 37 Seconds Became 14.3.
How I used Cursor and Claude Code to cut a 10-year NexusTrade backtest from 37 seconds to 14.3. Profile, change, measure.
0:47Transcript
I Spent 1,400 Days Building This. 35,000 People Have Tried It.
I spent 1,400 days building an algo trading platform. 1,873,324 lines, 35,000 people, and a live public book. Google Public Portfolio Challenge.
0:23Transcript
What Can You Do With a Biology Degree? Mine Led to CMU and Big Tech.
What can you do with a biology degree? Austin Starks used his to earn a CMU master's, work as a software engineer, and run a public AI trading experiment.
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.
1:24Transcript
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.
0:06Transcript
Stop Staring at Charts: What an Ex Jane Street Quant Told Me About Trading
An ex Jane Street quant told me staring at charts is fighting human emotion. Why I stopped looking and deployed AI trading bots to run my strategies instead.
0:50Transcript
How I Built an AI Trading Bot That Turned $25,000 Into $30,621
A $25,000 public account traded by AI is up 22.49% in 126 days. The rules, the day-two failure that forced a risk-engine rebuild, and what the drawdown looks like.
1:43Transcript
My top 3 stock picks for 2027
Why Duolingo, Oscar Health and NVIDIA are my three stock picks for 2027, with the revenue, margin and membership numbers behind each.