Hacker News Reader

Comment by tombert | Hacker News Reader

I use the Interactive Brokers MCP pretty heavily. I don't do any cool automatic fun "trading", but instead I use it to have "pseudo-QQQ".

I didn't like the relatively high fees for QQQ, and I realized that Invesco releases the weights for QQQ for free. I also think Tesla is too overvalued, and I want to avoid the SpaceX IPO. With the Interactive Brokers MCP, I just feed it the CSV of QQQ's weights, tell it to remove and redistribute Tesla, and then I tell it to buy "$1000 of pseudo-QQQ", in the form of raw stocks.

Doing this, I still basically get the same exposure as QQQ, without any fees.

EDIT: Some of the responses here were right; this is a actually a bad idea, at least with the naive way I was describing it. There's a lot more tax stuff that you avoid with ETFs compared to the makeshift thing I'm describing.

View on HN

This is absolutely and unfathomably terrible to such a great degree that I think it reinforces OPs point. It seems like using an LLM has given you the confidence to make an incredibly ill-informed decision that will cost you dearly.

Every single time you rebalance your portfolio, you will need to pay short-term capital gains taxes on any gains, as opposed to an ETF in which you simply pay for the gains when you sell your stock which can be years/decades from now. This alone will reduce your average expected earnings by 20% over a 10 year period eviscerating whatever tiny advantage you think you'll get from saving a few bucks in fees.

Furthermore, assuming you rebalance your portfolio monthly, which is the minimum you need to rebalance in order to remain even somewhat aligned with QQQ, you're basically going to be paying a MINIMUM of 30-40 bucks a month in commissions to Interactive Brokers, or 400 dollars a year. And on top of IBKR's commissions you then need to pay the pass through fees of about 5-10 dollars a month for a total of around 500 bucks a year.

Compare that to QQQ which only costs you 18 dollars a year for every $10000 invested.

I've read some incredibly foolish investment advise on HackerNews, but I think this one just about takes the cake.

IBKR has payment for order flow if you use the Lite service, so it actually wouldn't be $30-40 a month.

You still are paying the capital gains taxes with the ETF, they are just rolled into the management fees.

You can avoid a lot of the short-term capital gains taxes by only rebalancing within certain thresholds and being ok with being "close enough" to QQQ instead of being completely aligned with QQQ.

ETA:

Looked it up, looks like I was wrong about the taxes being rolled into the fees. There's some extra weirdness associated with tax efficiency of ETFs.

I still think some of the numbers the parent provided were a bit handwavey and bullshit, but I'll acknowledge I was mostly wrong in my response.

>You still are paying the capital gains taxes with the ETF, they are just rolled into the management fees.

There is just so much wrong with this statement and several others that I don't even know where to begin.

At the end of the day... if you are having fun doing what you're doing, then by all means go for it, my main concern is that people might read what you're saying and actually get misled by it or believe that you're saying something that is true. Your statement seems sophisticated enough that someone could read it, think you have actual knowledge of this topic, and come away with the idea that this is actually a remotely good idea.

For those people... please understand that tombert has no idea what he's talking about, his reasons for what he's doing are not actually because he's trying to save any fees, or because there is anything optimal or rational behind it or he's in anyway outsmarting actual institutional ETFs.

His genuine reason for this appears to be entirely whimsical and for his own amusement and enjoyment, and honestly that is fine, people can do what they want with their own money and there is nothing inherently immoral about this. My main issue is him not being upfront about his actual incentive and instead misleading people into thinking that there is some kind of economic advantage behind this.

Yeah I was wrong, I actually updated my comment right before you posted your response so I understand why you didn't see it.

I was definitely wrong; I misunderstood something about ETFs. ETFs probably are more tax efficient after all, or maybe some kind of direct indexing thing if I want to avoid Tesla and/or SpaceX.

I'll acknowledge that there's some validity in "doing things for my amusement". I do think that if I avoid selling things and instead only buy to rebalance, that could avoid a lot of tax bullshit, but that's definitely not what I was suggesting before so I'll acknowledge that I was absolutely in the wrong.

ETA:

I actually think I agree with you for the most part. I don't think it's the worst financial advice on HN but it's definitely not good financial advice either.

It's too late to edit the root comment directly but I did email HN support to ask if they could amend it for me.

> you will need to pay short-term capital gains taxes on any gains

Stating the obvious here, but only in a taxable account.

I rebalance frequently and on small divergences in the IRA, which has no trading fees and obviously no tax consequences.

In a taxable account I try to favor growth over dividends and rebalance very rarely.

If short-term capital gains taxes are the main concerns, perhaps this pseudo QQQ strategy can be done in a Roth IRA account using brokers that offer free commission?

The poster was mostly right, and I was mostly wrong, I don't like admitting that but that's just what it is.

I updated the skill I wrote to make it so that rebalancing is "buy-only", as in rebalancing will just buy shares for the underweight things instead of selling the overweight. I don't think buying is a taxable event so I don't think that's going to make me have an absurd tax burden then.

I will say that I think Maxatar was a bit misinformed about Interactive Brokers though; they've had PFOF/"commission-free" trading with their free Lite package for awhile. Of course you still pay the bid/ask spread, but if something is popular enough to be on the NASDAQ-100, the spread is usually on the order of a cent or two.

It was a creative use of AI to essentially fork your own version of QQQ, which is definitely interesting! It probably doesn’t work with a US based retail account but some Roth IRA account holders or expats in Hong Kong trading US stocks might appreciate your idea

But he avoids SpaceX and Tesla, which I think is probably the driving factor in not using QQQ. Maybe he values that more than $500

If that was his genuine concern, then instead of trying to balance a portfolio of 103 stocks... you simply buy QQQ and short Tesla at 3.53% worth of your QQQ holdings.

You pay interest when you short stock.

And if we want to talk about "bad financial advice", I think telling people to try and time the market with a short is considerably worse than "buy the same shares that QQQ does".

You pay interest on the margin you put up for shorts net profits from the position itself and cash or other assets you place inside investment accounts. You're also usually being charged interest at only a few basis points above the RFRR so this isn't "interest" in the sense of a loan.

> I think telling people to try and time the market with a short is considerably worse

Nobody is trying to time the market. If you want QQQ but don't want the Tesla exposure in it, it's a lot cheaper net to simply hedge against your Tesla exposure with a short position counteracting your long position. If you're worried about margin rates interfering with your profits, you can model all of these and come up with the optimal short needed to hedge your risk. This is standard financial practice.

Shorting doesn't have anything to do with timing the market, the reason why pop investing communities think that shorting and timing the market are synonymous is because as a whole asset prices are expected to keep pace with the RFRR assuming they at least hold their value, so taking a short position is going against the "default" market direction.

The GP did not try to time the market. He suggested a sensible strategy to exclude a tiny subset from an index (less expensive than maintaing the alternative index yourself).

Its not timing the market if it is exactly offset by the position in the etf

Yeah, I guess this entire thread has been an inadvertent exercise in Cunningham's Law, and maybe Dunning Kruger as well.

I thought I understood this stuff more than I actually do. Guess I have some stuff to learn over the weekend!

I'm unsure what SpaceX's weighting would be in QQQ but with Tesla being <3.54% weighting it would take both companies being 0s within a year to offset the cost in taxes from reweighting...

Everyone keeps saying this but I'm a little confused; you're still paying the reweighting taxes with QQQ, it's just rolled into the management fees.

https://www.fidelity.com/learning-center/investment-products...

Yeah I just looked it up myself. I was wrong; taxes are definitely more efficient with ETFs.

Now this idea is sounding pretty stupid. Damn.

tombert should instead long QQQ and short the bits they don't like

You pay interest on shorting, and it requires trying to time the market, which people are famously bad at doing.

You don't need AI for this though. I was doing something like this with a python script and a crypto meta etf I created years ago. I even had some simple heuristics for selecting what coins and quantity to purchase given trading volume and spot price. Its like 175 lines of python. Probably could be a lot leaner too.

I agree I don't need it, I actually wrote a program to automatically buy and sell stuff years ago using Alpaca [1].

I just found it a bit of a pain in the ass to manage a service to do that automatically, vs thirty seconds of chatting and getting results immediately, and having something that can be supplemented by RAGs in the process.

[1] I swear I had a blog post about how I did it somewhere but I seem to have misplaced it.

It sounds like you are just pulling weights of qqq and buying based on that though. What more management do you have to do? Just pull and parse the weights wherever they might be stored, break the investment up based on that weight. Should work until the heat death of the universe.

and then you want to track orders states, and then you want to track exit strategies - trailing stops that are sometimes internal, sometimes sent to the order book - profit targets, and then you want to track settlement statuses as balances change on margin, and how you get filled

all while dealing with different and complex broker APIs and routing to different exchanges that have their own rules and limitations

on the other hand, agents just do it and handle edge cases themselves

Right, AI agents famously never make any mistakes.

So does procedural code, the architecture supporting it and the humans writing it. I am capable of playing devil’s advocate as well

Do you have an actual strongly held opinion or counterpoint on what I wrote?

Time to market, covering bases, lower maintenance and things to keep track of all represent the utility

Have you actually put together trading strategies by having the agent drive? I've never trusted it that far and I use agents a lot at my job right now. The way I usually do it is, I break out pen and paper to do an analysis of what I want mathematically. I then have the agent build out some Python that lets me backtest and analyze my work. I read through the code (which is usually fairly compact since numpy/scipy and various finance libraries do most of the heavy lifting for me), make any changes as needed, then run my analysis. Then I run it in a production setting if I like it. But the actual strategy is something I come up with on pen-and-paper.

I have, and agents come up with the strategy and execution based on my contribution of what sectors to look at and alternative data sources I tell them to look at a certain way. My time horizons are quarters, as well as signal conversion into a variety of single and multi leg options trades

I am not sure I would trust a LLM agent to do this either. I would use an LLM to help write the script but not execute the trades.

I feel like you could probably have the AI write a script that uses the API to do the same thing, except this time you have code you can test rather than relying on the probabilistic machine every time you do a trade.

I did that first actually.

I don't let it buy anything without confirming, and I will load the CSV into Google Sheets to make sure that the numbers more or less correspond to what I think they will. It's just easier to directly use the MCP and set up some custom skills for what I want to do.

Dunno, it seems to work fine.

I have thought about this but snag on rebalancing, because it would create a taxable event, or be drawn out over months/years.

Although maybe a bit spicier, VGT is half the cost of QQQ, so that is what my "NASDAQ" has been. I also blend in VTI to cut the volatility a bit, which is 1/3 the cost of VGT.

I'm doing the same strategy for rebalancing that QQQ does, and I figure that the headache of tax time is a "Tom in 11 months from now"'s problem :)

Some tax software nowadays will allow you to simply upload the tax documents with all the transactions and it will tabulate everything for you, so I don't think it will be too hard for me.

I'll admit that there's primarily just kind of a coolness factor to be able to say that I ripped off and copied QQQ without any fees, but I do genuinely like the idea that I can avoid companies that I think are terrible in the process.

I love how you needed an LLM to remove "passive" from "passive investing".

On a more serious note, why do you need an LLM for this at all? It's an excel spreadsheet difficulty level task.

This is fair use, but an average person will just spam LLM with "give me money making strat"....

QQQ gets the leverage from, among other things, swap agreements and futures. I don’t think what you have could be reasonably considered “pseudo-QQQ”. It’s like copying a cake recipe, but leaving out the flour and eggs because they are too expensive.

Even given that, I don't see any reason I couldn't also just mimic what QQQ does with the MCP.

Real question, where are you going to buy the swap agreements?

If you're asking about the average person, no.

I am in the "false confidence" stage of Dunning Kruger Syndrome for finance stuff, so I personally would do swap agreements, but I'm not an average case.

I realize I might have been mixing up QQQ with ultra pro QQQ… anyway, yeah, you can replicate QQQ. I was thinking of Ultra Pro QQQ.

I mean, even still, my point stays the same; if you have access to their strategies, I don't see why you can't just get the MCP to directly mimic that.

Because it is not possible for you (personally) to buy the underlying components of leveraged ETFs.

Yeah, actually I think I was getting confused on some of the terminology. It looks like you're right.

Still, as you said, just mimicking regular QQQ is achievable.

It’s achievable. It’s called “direct indexing”, and there are some extra costs associated with it, so for most investors, I think it is cheaper to get QQQ. You can flip that around with tax loss harvesting but I don’t understand that strategy and I can’t explain it.

You also don’t need AI to do this. Before AI, the main barrier to direct indexing was the amount of capital you need. That is still true.

I have enough capital to where I can do everything with the incremental share threshold of Interactive Brokers; as such I don't have to deal with the fees associated with normal direct indexing.

Sure, but I wasn’t thinking of the brokerage fees. Things like the spread.

QQQ?

NASDAQ-100 following ETF. Until recently, the only one that tracked the NASDAQ-100, which is a tech heavy index.

Too late to edit my comment, but some of the responses here were right; this is a actually a bad idea, at least with the naive way I was describing it. There's a lot more tax stuff that you avoid with ETFs compared to the makeshift thing I'm describing.

@dang if possible can you add this to my comment because I genuinely do not want to mislead anyone and have them repeat my mistakes.

Reply on news.ycombinator.com