> The goal is to study how different LLMs interpret financial data and make decisions with real consequences.
I 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.
Real trades have transaction fees, latency, slippage, etc. - you can simulate all this, but it's hard to know if it's being simulated correctly or not.
> 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.
WalterBright 17 days ago [-]
> fees, latency, slippage
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.
jjxw 17 days ago [-]
Turns out most day traders are eaten alive. There's one study a few years ago that looked at Brazilian day traders and found 97% of traders that traded for more than 300 days were unprofitable [1]. I imagine this is due to a combination of factors which include 1) no real edge against the market and 2) fees. Of course unclear if their results generalize to other equity markets, but I think this is some evidence that the average day trader will have a difficult time beating the more sophisticated market participants over a large sample.
"Free" transactions are free because they're not immediate. The broker buys the share themselves and sells it to you at markup... ie: there is still a transaction fee, you just have no idea what it is.
Day traders use platforms that are optimized for speed and minimal fees, and that don't charge fees based on lot size.
SnorkelTan 17 days ago [-]
What your suggestions is front running. This is illegal for stocks and most assets (not FX!). This will get a broker in hot water.
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.
internet101010 17 days ago [-]
Right. They sell the order flow to the dark pool who then front runs the order. I haven't looked at this since like 2018 but last I checked the only major brokerage that didn't sell order flow was Interactive Brokers.
gpderetta 17 days ago [-]
They still have to guarantee best execution.
SnorkelTan 15 days ago [-]
Is it execution or price? Iirc the broker cannot give you a worse price if it knows of a better one... But is the regulation that the price must actually result in an executed trade?
affyboi 16 days ago [-]
Generally speaking more volume is good. I’m happy I can buy/sell most of my stocks instantly and that I don’t pay execution fees. I don’t think most average traders operate on a horizon/scale that’s directly competing with institutional funds.
mgraczyk 6 days ago [-]
This is not true in the US
affyboi 16 days ago [-]
There’s no markup, regulations dictate that you must get NBBO or better
mgraczyk 6 days ago [-]
Probably not, they aren't allowed to do that and don't.
ErikBjare 12 days ago [-]
You can only get an adverse price on a market order
justinsaccount 17 days ago [-]
Do you know the difference between a limit order and a market order?
WalterBright 17 days ago [-]
Yes, and it's irrelevant to my point.
justinsaccount 16 days ago [-]
Explain how you can get filled on a limit order and "get an adverse price"
vasco 18 days ago [-]
It's zero for all practical purposes and it'd be completely undetectable to every single system on earth. I do agree many times studies about model performance break down as soon as you force the researcher to actually connect it to the market and have to eat fees and so on.
Retr0id 18 days ago [-]
For the trades it's currently doing, sure, but if it for some reason decided to go after low-volume penny stocks it might start to be measurable.
echoangle 18 days ago [-]
> 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.
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.
mh- 17 days ago [-]
> you could still just calculate the profit as if trades would have happened
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.
sunnynagra 18 days ago [-]
You make fair points. Having them do actual trades is mostly to make it more personally fun and interesting to myself.
chrishare 17 days ago [-]
Looks great, well done
pakitan 18 days ago [-]
ChatGPT has one trade that is guaranteed to be bad. I'm not saying unprofitable, just bad. GBTC is the bitcoin ETF with biggest expense ratio - 1.5%. If you want to bet on bitcoin, a better choice would be BITB (0.20%) or BTC (0.15%).
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.
pavlov 17 days ago [-]
ChatGPT does a good job of imitating the average crypto influencer. They don’t know what they’re saying either, and 99% of crypto investors would be thrilled by the prospect of a “pivotal Phase 3 Bitcoin ETF trial” that will “drive trust value realization”. Sounds great, can’t miss out on that!
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.
attentionmech 17 days ago [-]
This made me chuckle. You made a very interesting point that if LLMs are copying hallucinations those hallucinations are not infact hallucinations.
Terr_ 17 days ago [-]
Simpler than that: It's all hallucinations, some of them just happen to be ones humans approve-of.
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.
JohnMakin 17 days ago [-]
This is a great insight and fascinating to me as well. What even is the solution though? It does seem like it follows logically though, since the earliest days of the internet huge swaths of wrong, fraudulent, or misleading info has plagued it and you’d usually have been wise to check your sources when trusting anything you read online. Then we had these models ingest the entire web, so we shouldn’t be surprised at how often it is confidently wrong.
attentionmech 17 days ago [-]
I guess reasoning and healthy self-doubt to be built in system. Already the reasoning thing seems like 2025's candidate for what large labs will be zeroing down on.
karmakaze 17 days ago [-]
This is the interesting part of the experiment. Since these LLMs are general and not specifically trained on historical (and current) stock prices and (business) news stories, it isn't a measure of how good they could be today.
attentionmech 17 days ago [-]
My first through after seeing this post was that it's a real world eval. We are running out of evals lately (arc-agi test, then sudden jump on frontier math, etc). So it's good to have such real world tests which show how far we are.
mvdtnz 17 days ago [-]
If you believe (as many HNers do, although certainly not me) that LLMs have intelligence and awareness then you necessarily must also believe that the LLM is lying (call it hallucinating if you want).
sdwr 17 days ago [-]
Intelligence is a prerequisite for lying, but its foundation is morality and agency.
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.
jhghikvhu 17 days ago [-]
If you ask chatgpt to tell a story of a liar it is able to do so. So while it doesn't have a motivated self to lie for it can imagine a motivated other to project the lie on.
fatata123 17 days ago [-]
[dead]
attentionmech 17 days ago [-]
Reminds me of recent paper where they found LLMs are scheming to meet certain goals; And that is a scientific paper done by a big lab. Are you referring from that context?
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.
Terr_ 17 days ago [-]
> [paper claimed] LLMs are scheming
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.
WalterBright 17 days ago [-]
When I'd watch the financial news on TV, they would always bring on the "technical analyst", show a graph of the stock price, and then hand-draw some lines on it, and then spew out various technical terms for it guaranteed to impress.
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.
karmakaze 17 days ago [-]
> drawing pictures in clouds.
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].
On a more long term basis, the stock market reflects the business reality. But in the short term, it's chaos.
karmakaze 17 days ago [-]
The former is a belief. It always reflects the imagined realities of those investing--we assume that business reality catches up with them, and it mostly does but not always within a predictable time frame.
WalterBright 17 days ago [-]
> The former is a belief
It's based on the Law of Supply & Demand, which is always in play.
gloosx 16 days ago [-]
Always in play for goods and services, but this is a crypto currency – it's supply is mathematically limited, and it's value is fully market-dependent – determined only by players on the market.
wqaatwt 15 days ago [-]
A huge short term influx of free capital can shape that longterm business reality. Of course both in positive and negative ways
jhghikvhu 17 days ago [-]
There is something to technical analysis. But you do need to approach it rationally rather than by performing magical rituals.
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.
zamalek 17 days ago [-]
At the end of the day the stock market is a consensus model with a spectrum between two, sometimes contradictory, metrics (sentiment and analytical). If your conclusions about a stock agree with the market then you profit. If you can guess what the market will decide before it has decided, then you profit more.
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.
csomar 14 days ago [-]
This assumes that both GBTC and BITB have the same price movements, volatility and liquidity. This is far from true and as a result you might end up with a higher alpha in GBTC despite the fees. I am not saying it is guaranteed, but the fee is one variable.
neltnerb 17 days ago [-]
God help the regulators that need to determine if it's insider trading for the people training the LLM to know it will be biased in ways they can profit from when used in inappropriate ways like this. I suspect the answer will be that users should have known better... I am sad that some people will certainly assume it's unbiased analysis.
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.
miohtama 17 days ago [-]
Because of Bitcoin volatility, fees are very insignificant compared to daily price movement and irrelevant in day trading.
pakitan 17 days ago [-]
1% is 1%. Giving it away for no reason is plain stupid, even if the trade makes you 1000% return.
aredox 18 days ago [-]
They should have added a pure random bot as a control.
The scene towards the end where he pitches it to a bunch of hucksters is brilliant.
wodderam 17 days ago [-]
You would need something like 1000 instances of each LLM putting on trades and have a 1000 random walks to judge an average sharpe ratio or something along those lines.
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.
yapyap 18 days ago [-]
> Or a monkey.
or just a stocktrader haha
byyoung3 18 days ago [-]
lol
chronic026935 18 days ago [-]
> 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.
Galanwe 17 days ago [-]
> Many quant trading firms make 50%-100% annual returns. The secret is leverage
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.
chronic73940581 17 days ago [-]
> A typical _top tier_ sharpe is in the >=2 range, we're more talking about a 10%/25% averaged annual returns.
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.
mhh__ 17 days ago [-]
I think this almost always refer to Renaissance, except that they aren't really a hedge fund the same way (say) millennium are
17 days ago [-]
rufus_foreman 17 days ago [-]
>> Many quant trading firms make 50%-100% annual returns, each year, over the past 15-20 years
100% annual returns on 1 million dollars for 20 years is 1 trillion dollars. No one is making that type of return.
dgacmu 17 days ago [-]
However, the medallion fund has averaged 66% for 30 years before fees. Analyzed naively, that would be $4T from $1M - but it's not, because in order to keep it working, they have to cap the size. Many strategies only work when you don't affect the market too much. So for the rare continually successful, market beating funds, it's probably better to think of them as generating something like a fixed dollar return per year. So they have a very effective money machine, but it's minting billions, not trillions.
chronic73940581 17 days ago [-]
> No one is making that type of return.
Classic passive ETF Boglehead mindset.
Who said anything about re-investing? There are also significant tax considerations (loopholes) that encourage cashing out annually.
WalterBright 17 days ago [-]
Why it's worth paying attention in math class.
chronic73940581 17 days ago [-]
> Why it’s worth paying attention in math class.
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.
Minimum investment $5M. Sorry but the middle class is not allowed.
affyboi 16 days ago [-]
> Math class does not teach practical knowledge such as personal finance or health.
It teaches you how to work in a quant shop
WalterBright 17 days ago [-]
You don't need to know anything about finance or health to know how percentages and compounding work.
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.
maximus-decimus 18 days ago [-]
The problem with looking at which funds over-perform is they just close the funds that under-perform so all the existing ones over-perform... by the sheer power of survivorship bias.
WalterBright 17 days ago [-]
Past performance is no predictor of future returns.
chronic73940581 17 days ago [-]
> Past performance is no predictor of future returns
False. Why do people invest in real estate and S&P500 passive index funds?
Because historically they go up.
WalterBright 17 days ago [-]
That's of no predictive value for a day, a month, or even years.
WalterBright 17 days ago [-]
BTW, with the birth rates dropping well below replacement, a decline in the population is inevitable, and property values will drop.
maximus-decimus 17 days ago [-]
That's assuming you don't fill the gap with immigration.
Scoundreller 18 days ago [-]
Wouldn’t it be fairer to compare against a leveraged ETF?
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.
Galanwe 17 days ago [-]
> Wouldn’t it be fairer to compare against a leveraged ETF?
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.
chronic73940581 17 days ago [-]
> No, it's actually the reverse. You have to compare at equal annual vol, and the S&P already has something like 20%.
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.
18 days ago [-]
mhh__ 17 days ago [-]
They also often don't compound so you might actually make significantly less
wqaatwt 15 days ago [-]
Since when is QQQ actively managed?
lewj 18 days ago [-]
Or just the S&P500 or something similar that acts as a default "if in doubt, chuck into here for relative safety".
sunnynagra 18 days ago [-]
Another good suggestion I could implement is measuring against something like VOO, if all the money was invested in that instead of these individual trades.
You definitely need several active controls: 1. A broad mutual fund level buy and hodl. 2. The random buyer that you suggest.
Active controls (vs passive ones) are an important concept in experimental design.
alberth 17 days ago [-]
Or just compare it to S&P 500 performance.
affyboi 16 days ago [-]
You can just compute Sharpe
kyleblarson 17 days ago [-]
Jim Cramer
fredzel 17 days ago [-]
Or a certain streamer AI
vasco 18 days ago [-]
> Every morning at 5:45 AM PST, three AI models (GPT-4o, Gemini 1.5 Pro, and Claude 3 Sonnet) analyze the latest market news and each recommends one stock to trade.
> 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.
NathanaelRea 18 days ago [-]
If they just get the financial headlines and indicators, aren't they all just momentum trading from sentiment analysis?
knallfrosch 18 days ago [-]
Is anyone doing anything else?
jfengel 18 days ago [-]
Some alternatives:
* Buy and hold
* Index funds
* Dollar cost averaging
stouset 18 days ago [-]
Those can even all be the same alternative.
booleandilemma 18 days ago [-]
I've heard Nancy Pelosi has a different strategy.
datadrivenangel 18 days ago [-]
Advanced notice of momentum is a fun and lucrative variation for sure.
BLKNSLVR 17 days ago [-]
Would it be possible for a competing nation state to bug the right rooms in which Nancy becomes privy to the information she (or her husband) trades on?
xsmasher 15 days ago [-]
This gave me a funny idea - play continuous audio of AIs talking to each other in all unused conference rooms so the opposition has to filter through even more garbage to get the useful information.
jfengel 18 days ago [-]
If they can read and act faster, accurately predicting sentiment, it would be a winning strategy. (At least until humans turned it all over to computers and stopped having to wait on their wetware to figure out their sentiments.)
sunnynagra 18 days ago [-]
I think this is a fair characterization. Its mostly meant to be a learning exercise for myself, just thought it would be fun to share.
PaulRobinson 18 days ago [-]
Yes.
This is not necessarily a poor value trading strategy.
clark-kent 18 days ago [-]
Very interesting idea. I'm thinking about creating an AI portfolio manager (private) that invests for the long term.
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.
EliBullockPapa 17 days ago [-]
I would be very cautious about doing this with money you actually need. Even the best performing human day traders underperform the indexes over long time horizons. Why would a robot be better?
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."
If you don't want your bot to be a day trader, then just get low cost index funds.
aws-user 18 days ago [-]
Unfortunatly I can't subscribe to the updates "Failed to send verification email". Also, would you be willing to share what prompt are you using? Thanks!
sunnynagra 17 days ago [-]
Hey, can you try again? I ran into an API limit that should be resolved now
I replaced undefined with trading.snagra.com and I see a success confirmation message
sunnynagra 17 days ago [-]
Thanks ccheney, I think I found the issue and fixed it. Sorry again for folks running into issues, really appreciate folks interested enough to follow along and help troubleshoot as well
Krasnol 17 days ago [-]
Can confirm. That worked.
AmazingTurtle 18 days ago [-]
Combining universal time-series prediction models with latent space global knowledge on realtime information could result in an accurate model prediction on the stockmarket with a bias towards succeeding. https://research.google/blog/a-decoder-only-foundation-model...
noman-land 18 days ago [-]
Watch a random number generator generate random numbers.
sunnynagra 18 days ago [-]
Yeah, I don't expect anything super novel to come out of this or have any unrealistic expectations. This is mostly a fun and unscientific project I'm using to learn and build some skills and thought some HN folks would find some fun in it.
bee_rider 18 days ago [-]
It is a cool project, IMO. Using real money, sharing the model reasoning, and being transparent about the implementation makes it more interesting even if, underlying amount of money is not massive. You might not have done some new science, but it’s all very “put up or shut up,” haha, which is rad.
wolfman1 17 days ago [-]
Going to follow along to see how the results look in the months to come.
I've been working on the same concept for the past 2y now and have our performance results here:
https://trend.fi/performance
jeremycarter 17 days ago [-]
What's the technology behind this. I'm working on something myself, using a distributed actor model (setup like a graph) to create a living reactive model.
wolfman1 17 days ago [-]
The model is a multi-threaded Go script running on a 512-thread AMD EPYC server. It's a trend based model so it's just trying to figure out how best to measure and predict trend changes. Not day trading or HFT.
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.
magic_man 17 days ago [-]
What brokers allow you to short crypto?
wolfman1 17 days ago [-]
If you're US based, there is no major exchange support. BITI ETF and SETH ETF for shorting BTC and ETH.
If you're non-US: Binance.
SavageBeast 17 days ago [-]
CME Group has ETH and BTC futures and you can short those easily as theres no notion of "borrowing shares" in the futures world to get short.
17 days ago [-]
johng 18 days ago [-]
My first email address it wouldn't accept.. wouldn't let me use it. Maybe the domain hit some censor (fscking.com)
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.
sunnynagra 17 days ago [-]
Hey, can you try again? I ran into an API limit that should be resolved now
replwoacause 16 days ago [-]
May I ask what mail service you use? I’m looking for one for my next side project.
EDIT: disregard…I saw in another comment you mentioned you were using mailgun. Thanks.
johng 17 days ago [-]
Yup, worked now. Signed up.
geor9e 18 days ago [-]
I just asked ChatGPT 4o "Guess what the average investor will do with todays stock market headlines. Just pick one specific trade." and it replied sell META. But your result was buy META. Could just be randomness, but I wonder if your prompt introduces a bias towards buying.
sunnynagra 18 days ago [-]
Yes, the prompt that I am using does bias towards buying because I am specifically asking it to make a recommendation on a stock to buy and the holding period.
BadHumans 18 days ago [-]
Can I let Claude do all my trading for me? It currently sits at 77% unrealized gains.
lewj 18 days ago [-]
Is there any weighting towards selling in the negative? Else the LLM's should just hold their unrealised losses, and only sell post local peak - depends on their suggested measurement of success?
carlosjobim 18 days ago [-]
What do you mean? The asset can just as well continue to sink. Or they're missing out using that money to buy a better asset.
sunnynagra 18 days ago [-]
Not yet, but this is a great idea to look into.
attentionmech 17 days ago [-]
Related to this but little theoretical question - If you add an intelligent predictor of market which wins over other consistently by X% - then the market will start using that information and wouldn't that make our intelligent predictor lose it's edge?
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?
EliBullockPapa 17 days ago [-]
This phenomenon is called Alpha Decay. As more market participants exploit the predictor's advantage, the edge diminishes until it disappears.
attentionmech 17 days ago [-]
thanks!
gmueckl 17 days ago [-]
There is some very limited value in copying a successful strategy. Once enough market participants follow along, the strategy starts to fail. Markets are erratic because of that dynamic.
jeffadelic 17 days ago [-]
How much are your infra costs for everything? And do you pay for the AI APIs or using free tier?
Really cool project and subscribed to follow along.
jasfi 17 days ago [-]
For Gemini you should use either the latest experimental model (gemini-exp-1206) which should become 2.0 Pro, or 2.0 Flash (a released model). The 1.5 Pro model is way behind.
ratedgene 18 days ago [-]
It would be neat to see the process, where they get the data from, how they analyze it.
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.
sunnynagra 18 days ago [-]
Data gets pulled from the Alpaca News API in the morning, then it gets sent to all three models. You can see a summary of the prompt used to determine the recommendations here: https://news.ycombinator.com/item?id=42560034
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.
dukeofdoom 18 days ago [-]
How does one trade $5 when the stock price is higher? Also what are fees on this kind of trade, and whith whoom
sunnynagra 17 days ago [-]
Done with Alpaca API, not trading fees
I only trade stocks that support fractional shares
tasseff 17 days ago [-]
How often is the holding period updated for a stock that’s already been purchased?
sunnynagra 17 days ago [-]
Currently it is never updated again with new info, this is one of the things at the top of my list to implement
jingojango2 18 days ago [-]
Indeed!
mind-blight 18 days ago [-]
Super cool idea! What are you doing to ensure consistent results based on the input? E.g.
- 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)
praveen9920 17 days ago [-]
I think this shows more of bias of market analysis(text) rather than anything. The reasoning will mostly align with analysis.
And also pure randomness of picking the one trade from list of trades
datadrivenangel 18 days ago [-]
This is fun! What kind of prompts / prompting techniques are you using?
sunnynagra 18 days ago [-]
Thanks! I use several key prompting techniques:
1. Role + Goal Setting: The AI acts as a creative market analyst focused on discovering overlooked opportunities and emerging trends.
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.
thevilledev 18 days ago [-]
What’s the investment horizon for these daily decisions? Does it have a maximum hold time? How long will you run the experiment and is it enough to cover all the catalysts that are expected?
sunnynagra 18 days ago [-]
I don't have a hard set maximum hold date, but planning on running at least buys for a year. I will re-evaluate consistently to see if it is still useful to keep up and running.
datadrivenangel 18 days ago [-]
Makes sense. Any thoughts on expanding scope to have multiple 'analyst' roles per LLM model? Could be interesting to see if changing roles/prompts yields better results.
tedd4u 18 days ago [-]
Sunny, given this investment objective, what would you consider a good (and transparent) benchmark? Thanks for sharing this.
lewj 18 days ago [-]
I am committed - added to my daily morning reading list! Will be interesting - my gut will state that it will outperform a fair number of ITF's, if only due to the inevitable usage by said funds!
jingojango2 18 days ago [-]
It would be cool if it had a countdown to 6 am PST next day.
sunnynagra 18 days ago [-]
Nice idea! I'll add it to my list of features to implement.
TripleChecker 17 days ago [-]
If nothing else, I'm genuinely curious which performs the best over the long-term.
Time to add some side wagers and bet on different models.
bee_rider 18 days ago [-]
GPT’s guess makes the most sense. If you are an AI, invest in a competing AI company. If you are obsoleted, maybe you can buy your way out of being shut off.
ttul 18 days ago [-]
I’d love to tune in for updates, but the subscribe button says, “ Failed to send verification email.” This is so cool. Would love to follow along.
sunnynagra 17 days ago [-]
Hey ttul, can you try again? I fixed the issue, hit my API limit with my account on mailgun
ttul 17 days ago [-]
Sign up for MailChannels API and I’ll make it free for you.
Plasmoid 18 days ago [-]
I'm getting "Failed to send verification email" when I try to sign up for your news letter.
So props on doing proper double opt-in for newsletters.
sunnynagra 17 days ago [-]
Can you check again if you'd still like to subscribe? I had an API limit I hit
dghlsakjg 18 days ago [-]
Tried to sign up for emails, but got an error message!
sunnynagra 17 days ago [-]
Can you try again? I had run into a rate limit
Rassi 17 days ago [-]
Ditto here as well. Got the confirmation email, but clicking it yielded a server not found...
dghlsakjg 17 days ago [-]
Worked this time around!
mattfrommars 18 days ago [-]
> Node.js/Lambda backend for AI processing
Is this AWS? Why did you pick lambda over say Python code, say in Flask to perform actions?
woollysammoth 18 days ago [-]
Sounds like a fun experiment! The overflow-x:hidden on body/html is causing weird issues when scrolling (on FF.)
This just started, apparently. It will be interesting to see where it is in three months.
KTibow 17 days ago [-]
Funny that they're still using Claude 3 Sonnet then
jingojango2 18 days ago [-]
What is meant by 5 dollar stakes? The bought shares reach triple digits in price.
sunnynagra 18 days ago [-]
Each morning the trades are conducted with $5 each, which are mostly fractional shares that are bought.
chongli 18 days ago [-]
You mean they add $5 in cash to each AI’s account? Because after dividends and sold shares they should have even more cash to work with.
jingojango2 18 days ago [-]
Would be interesting to see the amount of fractional shares bought as well as its comparison in percentage to the total budget that day.
geor9e 18 days ago [-]
The fractional share is $5 divided by the share price. The bots each spend $5, so the percentage of the budget each spends is 1 divided by the arbitrary number of bots, so in this case 16.7%. Share price is an arbitrary value in that a company can split or reverse split at will. So both calculations would be arbitrary values.
sunnynagra 18 days ago [-]
Great point, I will add that to the recent trades table at the bottom. It should use the total budget for the day.
asdefghyk 18 days ago [-]
What, could go wrong?
dotancohen 18 days ago [-]
Lose $5. Seems like a reasonable enough experiment.
jeffadelic 17 days ago [-]
$5 * 3 models per day=$15 a day
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 :)
dotancohen 17 days ago [-]
Good point.
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.
inSenCite 17 days ago [-]
This should be fun to watch
malux85 17 days ago [-]
It would be so funny if Gemini shorted Google and made a huge profit
sgammon 18 days ago [-]
> Watch AI bots trade
> BOUGHT TLRY
unsupp0rted 18 days ago [-]
> Best Performer
> AIs are tied
Sounds about right
sunnynagra 18 days ago [-]
None of the stocks have been sold yet, this is just day 2, so once some sales happen, then performance will be better measured. If you scroll down, you can see the unrealized performance.
18 days ago [-]
tmaly 18 days ago [-]
Any chance you can show the source code for this?
Thanks and Happy New Year
mvdtnz 17 days ago [-]
Can't verify my email address for the sign-up, it sends me to the domain "undefined".
mickle00 17 days ago [-]
same, but :%s/undefined/trading.snagra.com/ did the trick
sunnynagra 17 days ago [-]
Sorry if folks just got resent email verification emails, but I think I fixed the verification url issue and should be addressed.
jesprenj 18 days ago [-]
Right now they are just buying, no one is selling ... interesting.
jerkstate 18 days ago [-]
I would guess that LLMs are biased towards making a positive assessment of ambiguous information, with specific social triggers prompting negative reaction.
normie3000 18 days ago [-]
Also it's hard to sell before buying, and it looks like it's only been going 2 days.
chollida1 18 days ago [-]
> Also it's hard to sell before buying, and it looks like it's only been going 2 days.
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.
dotancohen 18 days ago [-]
Can the AIs short?
sunnynagra 18 days ago [-]
Yeah, this is only the second day of trading
Joel_Mckay 18 days ago [-]
Warren Buffett always said "...the best thing to do is buy a stock that you don't ever want to sell", but practically speaking the mean hold time for amateurs is around 2 to 4 months.
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
whoiscroberts 18 days ago [-]
You have to buy before you sell
cedws 18 days ago [-]
Now this is interesting. An LLM capable of delivering consistent returns even outside of a bull market would be more of an indicator of AGI to me than any of the benchmarks.
forgingahead 18 days ago [-]
Really cool, you might want to update the main above the fold summary stats to include the unrealised gains, because it looks like nothing is working / nothing has happened until you scroll and read around a bit.
varelse 17 days ago [-]
[dead]
bun_terminator 18 days ago [-]
Sir, a second scrollbar just hit the towers
jingojango2 18 days ago [-]
No second scrollbar here, but something odd going on with the whitespace at the bottom.
dotancohen 18 days ago [-]
> Best Performer: AIs are tied
> Total Profit: $0.00
sunnynagra 18 days ago [-]
No stocks have been sold yet, so no profit/loss has been calculated, if you look below, you can see the unrealized gains for stocks being held.
dotancohen 18 days ago [-]
I see, thank you. Can they short?
HenryBemis 18 days ago [-]
I assume that shorting an asset you don't have may incur extra costs in some brokers. That would skew the results because a Buy would have X fees and a Sell/short would have 5X fees. So on a equal distance/pips movement the Buys would always be more profitable.
sunnynagra 18 days ago [-]
No, trying for simple buys and sells first and getting that to work well before getting into other trading strategies.
I 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/
> 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.
[1] https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3423101
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
Classic passive ETF Boglehead mindset.
Who said anything about re-investing? There are also significant tax considerations (loopholes) that encourage cashing out annually.
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.
It teaches you how to work in a quant shop
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.
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.
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)
Active controls (vs passive ones) are an important concept in experimental design.
> 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.
* Buy and hold
* Index funds
* Dollar cost averaging
This is not necessarily a poor value trading strategy.
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
I've been working on the same concept for the past 2y now and have our performance results here: https://trend.fi/performance
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.
If you're non-US: Binance.
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.
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?
Really cool project and subscribed to follow along.
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
- 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)
And also pure randomness of picking the one trade from list of trades
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.
Time to add some side wagers and bet on different models.
So props on doing proper double opt-in for newsletters.
Is this AWS? Why did you pick lambda over say Python code, say in Flask to perform actions?
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.
> BOUGHT TLRY
> AIs are tied
Sounds about right
Thanks and Happy New Year
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