Link: https://trading.snagra.com?utm_source=hn (no signup required)
What you can try right now: - Watch live trades from GPT-4, Claude 3, and Gemini - Read each AI's full analysis and reasoning - Compare their different interpretations of the same market data - Track their real-time performance and win rates - View historical trades and performance metrics
Built this over the holidays to study how different AI models approach financial decisions. Each morning at 9:30 AM EST, the AIs analyze market data and make real trades with $5 stakes.
Technical Implementation: - Next.js frontend with real-time updates - Node.js/Lambda backend for AI processing - PostgreSQL for trade tracking - Alpaca API for automated trading - Consistent prompts for all models
Data Flow: 1. Daily market analysis (9:30 AM EST) 2. Each AI gets identical inputs: - Financial headlines - Market summaries - Technical indicators - Earnings reports 3. AIs provide: - Stock picks with reasoning - Entry/exit conditions - Risk assessment 4. Automated trade execution
Note: This is an experiment in AI behavior, not investment advice. The goal is to study how different LLMs interpret financial data and make decisions with real consequences.
I'll be around to answer questions about the implementation.
1. Role + Goal Setting: The AI acts as a creative market analyst focused on discovering overlooked opportunities and emerging trends.
2. Structured Analysis Framework: - Detailed evaluation criteria (innovation, moat, management, growth potential) - Sector diversity requirements - Focus on finding hidden gems vs obvious mega-cap tech stocks
3. Time-Bound Precision: Instead of vague "3-6 months" holding periods, I require exact hour calculations tied to specific catalysts like: - FDA approval dates - Earnings releases - Product launches - Conference presentations
4. Quality Controls: - Must be valid NYSE/NASDAQ symbols - Diverse across sectors/market caps - Conviction level scoring (1-10) - Each pick needs unique thesis + catalyst - JSON output format for consistency
The key is combining structured analysis with creative discovery - pushing the AI to look beyond obvious choices while maintaining some analytical rigor.
It is not, that's called shorting and its very common.
In fact alot of strategies that are market neutral work by shorting one stock while being long the other, or similarly a basket of stocks.
I just recall Navinder Singh Sarao "$1T Flash Crash" as a notable addition to a long list of algorithmic trading strategies going sideways ( https://marketrealist.com/who-is-navinder-singh-sarao-the-ma... .)
The stock market was built on information asymmetry, unfair positions, and ambitious gamblers... statistically it is rarely a reasonable investment for amateurs.
Good luck, =3
Assume the experiment runs ~250 trading days in a year, consider the worst case they lose all their invested money=$3750.
A little more than $5 :)
That said, many hobbies cost more that $3750 per year, and that $3750 is a worst-case scenario. He might even make a profit, and hone skills that might make him a fortune.
> AIs are tied
Sounds about right
Or a monkey.
https://youtu.be/USKD3vPD6ZA?si=AGyGdPdSPpJezQJp
The scene towards the end where he pitches it to a bunch of hucksters is brilliant.
or just a stocktrader haha
Many quant trading firms make 50%-100% annual returns, each year, over the past 15-20 years. The secret is leverage. And they do not accept outside investor money.
Many hedge funds outperform the market. However, the returns after fees, to the passive outside investor underperform S&P500.
But yes, publicly traded active ETFs generally underperform. But counter example is VGT or QQQ, both historically outperformed S&P500.
False. Why do people invest in real estate and S&P500 passive index funds?
Because historically they go up.
TQQQ (3x daily return leveraged nasdaq 100) is up 180x since its well-timed inception in 2010.
Though that’s a bit over 40% annually.
No, it's actually the reverse. You have to compare at equal annual vol, and the S&P already has something like 20%. Most HF operate around 10% on AUM.
Stop thinking like a hedge fund.
TQQQ commonly is used as a benchmark because it represents a low-friction, practical alternative to VTI, VOO, and even private equity investments including hedge funds trading public securities.
Once your Sharpe is high enough, you stop caring about volatility. The only volatility is how many zeros in your almost-always positive PnL.
Hedge funds (and traditional asset managers) care about drawdown, vol, sortino, beta and all that shit. But hedge funds have a different business model than prop trading firms.
Hu lol no XD you're way over stating it. While it happens _sometimes_, 50% or 100% is insanely rare, even for the top tier hedge funds.
Most HF work at predefined annual volatility, often in the 7% to 10% range. A typical _top tier_ sharpe is in the >=2 range, we're more talking about a 10%/25% averaged annual returns.
> However, the returns after fees, to the passive outside investor underperform S&P500.
That doesn't even make sense with the figures you posted. Most HF operate under the 2:20 or 3:30 range, sometimes 0:40 for the top 5. If you take a pessimist 10% returns on 10% annual vol, against the S&P 10% averaged returns at 20% vol, you're still double the risk adjusted returns, gross. Factor in 20 to 40% performance fees and you're way above the S&P.
High-frequency low latency trading: Sharpe 10 or higher
Mid-frequency low latency trading: sharpe 4 to 5
Hedge fund statistical arbitrage: sharpe 1 to 2
Hedge fund long/short, event driven, global macro, etc: sharpe 0 to 1
And yes, HFT and MFT scales to billions in annual PnL for single firms.
There’s a reason quant HFT firms pay the most, and are ranked above OpenAI in pay and prestige. Hedge funds are tier 2 in comparison but not bad either.
100% annual returns on 1 million dollars for 20 years is 1 trillion dollars. No one is making that type of return.
Math class does not teach practical knowledge such as personal finance or health.
Citadel returns since 1990 is 38% annual returns before fees to outside investors. They have a 5:50 fee structure. There are hundreds of more firms, staying out of the public eye.
https://www.barrons.com/articles/multistrategy-hedge-funds-p...
Minimum investment $5M. Sorry but the middle class is not allowed.
Besides, I knew nothing about construction when I discovered that the contractor I hired to pour a patio was overcharging me by 30%. All it took was a bit of geometry I learned in grade school.
Pay no attention to math in school and you'll be prey to every scammer who did, and you'll never realize it.
It teaches you how to work in a quant shop
Classic passive ETF Boglehead mindset.
Who said anything about re-investing? There are also significant tax considerations (loopholes) that encourage cashing out annually.
Active controls (vs passive ones) are an important concept in experimental design.
As is, this means absolutely nothing and not understanding the problem.
Adding a random walk to this would mean you have 4 random walks instead of 3.
There is also the problem that it is tough to make a prediction for tomorrow that is better than today's close.
Maybe compare with this guy:
https://news.ycombinator.com/item?id=14713997 - Amazon engineer will let strangers manage his $50,000 stock portfolio 'forever' (2017-07-06, 172 comments)
> Best Performer: AIs are tied
> Total Profit: $0.00I don't really buy this. If the goal was to study how different LLMs interpret financial data there would be no use for actual trades, since their interpretation cannot be influenced by the fact that the trading orders are passed for real.
I believe the goal is to see if AI can do better than rats [0]. There is no shame in that.
[0]: https://www.vice.com/en/article/rattraders-0000519-v21n12/
Technically every trade influences the stock, but I agree that it won't have any effect at all.
> I believe the goal is to see if AI can do better than rats [0]. There is no shame in that.
But even then you wouldn't have to perform real trades, you could still just calculate the profit as if trades would have happened.
I think the actual trading is just to make it more interesting.
Depending on the type of trades, the volume of the equities, etc.. it can be very difficult to simulate the ability to open/close positions with sufficient accuracy to evaluate the strategies.
> their interpretation cannot be influenced by the fact that the trading orders are passed for real
It's not going to make much difference with $5 trades, but the impact on the market is non-zero.
Whenever I trade, I somehow always get an adverse price. I figure it's the "no fee" brokerage chiseling a bit off for themselves. I compensate by being a buy and hold hold hold investor, so paying very little in aggregate for that.
What I don't understand is how day traders avoid being eaten alive by this.
Day traders use platforms that are optimized for speed and minimal fees, and that don't charge fees based on lot size.
The more nuanced practice that brokers use to monetize is payment for order flow. They sell your security order flow to algorithmic trading shops that buy and sell the securities you want to trade.
You’re correct in that most retail orders never make it to a regulated exchange, but that may not always be a bad thing. There’s been studies showing that HFTs often match retail trades even when the market moves against them since they are better able to predict market changes and can still profit off the trades.
[1] https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3423101
* Buy and hold
* Index funds
* Dollar cost averaging
This is not necessarily a poor value trading strategy.
It would be neat to also see another experiment of a MAS doing this and coordinating to gamble together. Perhaps even different system/arch/expert configs.
It currently makes up to recommendations, since not all stocks support fractional shares (I'm only doing $5 per trade). As part of the buy recommendation, a holding period is suggested as well.
Once the holding date is reached, that is when the sell order happens.
Would love to answer any other questions you may have.
I only trade stocks that support fractional shares
Did a different email, it accepted it, I got the email, but got this error message when trying to confirm it: {"error":"Invalid verification token"} and a pretty-print checkbox that did nothing.
EDIT: disregard…I saw in another comment you mentioned you were using mailgun. Thanks.
Is this AWS? Why did you pick lambda over say Python code, say in Flask to perform actions?
> At 6:00 AM PST, trades are automatically executed based on AI recommendations, investing $5 per trade
The best trading decision most days is to not trade. Outliers and diversions from the mean don't happen every day. This is trading just for the sake of it.
I predict a slow crawl down into zero eaten up by fees.
- does the AI perform the same trades given the same input?
- does the AI perform the same trades given slightly different inputs? (E.g. same data, but re-ordered)
> BOUGHT TLRY
Thanks and Happy New Year
Also, the reasoning is partially a hallucination - "The holding period of 9 months aligns with the expected completion of Grayscale's pivotal Phase 3 Bitcoin ETF trial, a major catalyst for unlocking investor demand and driving trust value realization."
There is no such thing as a "holding period", nor are they doing a "Phase 3 Bitcoin ETF trial". It's possible the "Phase 3" thing is picked up from news about a drug company.
The hallucinations are simply a mirror of a community that thrives on this nonsense. When nothing is real, you can’t blame the LLM for not figuring it out.
Words and their historical contexts aside, systems which are based on optimization can take actions which can appear like intermediate lying to us. When deepmind used to play those atari games - the agents started cheating but that was just optimisation wasn't it? similarly when a language based agent does a optimisation, what we might perceive it as is scheming/lying.
I will start believing that LLM is self aware when a research paper from a top lab like Deepmind/Anthropic put such a paper in a peer reviewed journal. Otherwise, it's just matrix multiplication to me so far.
IMO a much better framing is that the system was able to autocomplete stories/play-scripts. The document was already set up to contain a character that was a smart computer program with coincidentally the same name.
Then humans trick themselves into thinking the puppet-play is a conversation with the author.
To lie, you have to know that you are not telling the truth, and arguably have to be able to held accountable for that action.
It's easy to babble a series of untruths, but lying requires intention, which requires an entity that can be recognized as having intentions.
I'd argue that ChatGPT's lack of a cohesive self prevents it from lying, no matter how many untruths it creates.
It's kind of like a manufacturer of Ouija boards promising that they'll fix the "channeling the wrong spirits from beyond the mortal plane" problem. It falsely suggests that "normal" output is fundamentally different.
Me, I always regarded technical analysis as drawing pictures in clouds.
If any of those analysts were worth spit, they'd be working for a hedge fund, not the network.
Well phrased and it's how the stock market works, not only by technical analysts but everyone else playing: make a story in your head, place your bets, majority rules.
Some even believe that's how reality works in general. Sometimes belief or need could be a factor[0].
[0] https://www.guinnessworldrecords.com/news/2012/9/norwegian-f...
It's based on the Law of Supply & Demand, which is always in play.
All those lines do actually mean something, so long as the market is in agreement as how to draw them.
FWIW these bots aren't doing the lines stuff, they are purely sentiment traders.
The markets are made of a finite and sometimes very small number of participants that may have their own reasons for buying and selling unrelated to company performance. Figuring out what they will do is the basis.
Maybe Bob is looking to sell a lot to free up cash for private jet. Maybe Alice buys every month the same day like clockwork as she gets her paycheck. Maybe Charlie thinks the stock can't go about $50 and will take profits at $49. Maybe Debbie regrets not buying and is likely to fomo buy soon.
Probably can't figure this out one by one, but can in aggregate.
Hopefully the LLM trainers didn't "accidentally" bias the model in weird ways that favor their employer or themselves... two of the three recommendations are a fund for investing in bitcoin and a company using blockchain to trace chemical supply chains.
I look forward to seeing if the AIs can beat an index fund, or if they'll just invest in a thousand blockchain, NFT, and AI companies. I suspect a LLM has a high opinion of a company making AI given how many press releases they're summarizing.
So props on doing proper double opt-in for newsletters.
Some things to watch out for:
- LLMs, by default, don't follow the best practices for trading or investing. Without careful constraints, they can ignore fundamental investment best practices. This is something I learned while building https://decodeinvesting.com/chat.
- I see Claude bought a penny stock SMX. This could be volatile, and the price could change significantly in 24 hours before the next execution at 9:30 am.
- The LLMs are day trading on some volatile securities; while LLMs could be good at day trading, unlike humans (we will find out), this setup has the disadvantage of only trading once a day.
from a study in Brazil: "97% of all individuals who persisted for more than 300 days lost money. Only 1.1% earned more than the Brazilian minimum wage and only 0.5% earned more than the initial salary of a bank teller — all with great risk."
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3423101
If you don't want your bot to be a day trader, then just get low cost index funds.
URL looks like that: http://undefined/api/verify-email?token=.....
I replaced undefined with trading.snagra.com and I see a success confirmation message
And also pure randomness of picking the one trade from list of trades
More simply what i mean to ask is -> the moment market knows about your advantage, shouldn't you lose it because everyone else will use that information to balance the market?
I've been working on the same concept for the past 2y now and have our performance results here: https://trend.fi/performance
If you're non-US: Binance.
It conducts millions of simulations daily for each asset, then provides a snapshot of the top-performing results to GPT-4o for final selection.
I'm really pushing the limits of GPT-4o currently. I started testing with o1 just last week and it performs better. It's just so much more expensive.
Time to add some side wagers and bet on different models.
Really cool project and subscribed to follow along.
It would be great to see this tested with more commercial LLMs (O1 / Amazon Nova, / Llama 3.2 / etc.). If you're open to it, I’d be happy to contribute support for these models via LiteLLM - https://docs.litellm.ai/docs/providers