Post New

I know there have been occasional posts about Berkshire's investment in SIRI, but I still don't know what the possible end game is on this one.
From everything I have read about Ted Weschler he is a very thoughtful and patient investor, meaning he does exhaustive research about a company before pulling the trigger, and when he does pull the trigger, he seems to keep buying. I think DaVita would be a good example.
As I type this SIRI is trading at $21.64/share which is on the lower end of its 52-week range with a nice dividend yield of 5%.
Anyone have any thoughts other than they have no idea what Ted is thinking:)
Thanks.

I’ve been wondering the same.
My “rational” thinking, which has led me on some very wrong and wild rides…
1. Sticky Customer Base
2. Pricking Power - near-monopoly in the satellite radio space
3. Capital Return - BH seems to like owning stock in Companies which return capital thru buybacks
Grateful Always,
PaulnKC (Long SIRI)

I think its the following:

Very sticky business, low churn, seems fairly stable, kicks off over $1B of FCF that historically goes towards buybacks. Currently they're going through a cap ex cycle so not enough cash for major repurchases, but end of next year company signaled that will return to more meaningful buybacks.

It's 38% owned by Berkshire, once they start repurchasing shares this should materially help EPS, they would be buying back 15% of the company each year or thereabouts. I think that's the end game. Very similar to DVA in that its a stable business and all FCF goes towards repurchases. This is Ted's MO. Same thing with Dillards.

This is my take anyway.

Obviously they're competing with Spotify and young people likely won't be subscribers to SIRI the same way old boomers are, so I think that is the negative view.

Same with OXY.

@Berkfan-
All excellent points and like you said, right up Ted's alley.
Thank you!

Good points. Right now, it looks like it's priced like the company has no future. I think I may take a starter position.
Thank you!

Just a hunch on possible catalyst....

It's highly unlikely SIRI renews Howard Stern's contract which expires in December. Feels a little like the Colbert situation on a bigger scale.

The economic benefits of Stern, in very recent years, are highly questionable. As well as the present administration political consequences...

This could be beneficial for projected cash flows...Stern makes about $90 million per year from a company with gross revenues about $9 Billion.

IMO It's possible SIRI and Stern will come up with a deal paying Stern a small fraction of his present pay for the right to rebroadcast much of his material.

Still..I personally wouldn't touch this. It's not a great business. But just FYI..

Obviously they're competing with Spotify and young people likely won't be subscribers to SIRI the same way old boomers are, so I think that is the negative view.


This is an important point. A proper understanding of Sirius's business needs to differentiate between "providing satellite radio", and "providing audio entertainment via satellite radio". Of note, I just checked their website, and Sirius also provides service via Apps. Properly understanding their business means you'll be able to see all the competition, like Spotify, I Heart Radio, local AM/FM stations, podcast downloads, etc.

Having a monopoly on home-delivered paper newspapers did little for many local newsrooms when Google stepped in and took their advertising money.

kicks off over $1B of FCF that historically goes towards buybacks. Currently they're going through a cap ex cycle so not enough cash for major repurchases, but end of next year company signaled that will return to more meaningful buybacks.

Looks like free cash flow is down every year since 2020. Is there a catalyst you see coming that will stop that trend?

Year Free Cash Flow (in $ Billions)
2020 1.627
2021 1.610
2022 1.555
2023 1.179
2024 1.013

kicks off over $1B of FCF that historically goes towards buybacks. Currently they're going through a cap ex cycle so not enough cash for major repurchases, but end of next year company signaled that will return to more meaningful buybacks.

What gives me pause is that there is a circularity that worries me. I guess the expectation is that, without buybacks, Sirius' earnings per share will decline, not rise, correct? Buybacks are economically sensible if you want to buy those shares because they offer good prospects, same as anybody else. If, absent the buyback, it's not a company worth buying, then it's not worth their while doing buybacks. The fact that they might do buybacks can not itself be the rationale for doing buybacks. They should allocate that capital to the shares of a firm that is attractive, or something else.

Phrased another way, yes, cash generated from operations allocated to buybacks can increase the earnings per continuing share. But they're only reported earnings, not useful profit: if (for so long as) earnings are being directed to buybacks, they can't be distributable owner earnings. You can't count the same money twice. Either you could get the earnings, or the earnings per share rise, but not both.


I've had the same thought getting my head around the attractions of Davita, too. Net sales and profits are unchanged in the last decade, and there has been no dividend. There have been lots of buybacks, but I have to ask myself, to what end? If the money is forever used for buybacks, it's forever not owner earnings. To overgeneralize, if they stop doing buybacks, the revenue and profit per share seems likely to be flat, since that's what is happening at the top level, so it's not that attractive a firm by the reasoning above. If a random person would not pay much for shares in a firm with flat per-share results, why should that firm be willing to do so?

Here's a thought experiment defying the institutional imperative: what if in the last decade, with Davita's flat revenues and profits, they had instead used those profits to buy shares of QQQ instead of shares of DVA (same question for SIRI)? What would a share now be worth measured as "market value of investment per share plus 10 times net operating profit per share"? A multiple of only ten because the operating business is merely a cash cow. Does Sirius' main business have any similarities to Berkshire Mills, and would it respond better to the same solution? I'm not saying either firm would or should adopt that approach, but if the results would have been better deploying that capital in another way, then maybe the current way is not so smart.

This description is a bit of exaggeration, as the current strategy of each firm can make sense if the shares are dirt cheap (cheaper than fair price for a piece of a moribund underlying business), and the firms are not dead yet. But it shows the circularity issue. Even giant buybacks won't fix the issues of a ho-hum business.

Yours confused,
Jim

Buybacks are economically sensible if you want to buy those shares because they offer good prospects, same as anybody else.

It would be instructive to look back and see what prices they've bought back at in recent years. I'm pretty sure that they bought back at MUCH higher prices than prevailing today. As opposed to a company like Apple whose buybacks have almost all been at much lower prices than prevailing today.

It would be instructive to look back and see what prices they've bought back at in recent years. I'm pretty sure that they bought back at MUCH higher prices than prevailing today. As opposed to a company like Apple whose buybacks have almost all been at much lower prices than prevailing today.

This is perhaps (?) the consequence of the concern I raise: Apple's buybacks were sensible (at the very least the earlier ones), because the business was a good one and the price was not excessive, so buybacks made sense. This is consistent with the price being higher today.

Conversely, perhaps SIRI's stock was not a great deal back then because the business was not a great one at the prevailing price, so the buybacks were not good capital allocation. This is consistent with the price being lower today.

For any company that owns an operating business and excess cash, even if the share price is currently fair, if the operating business is not a great one then a buyback isn't a great idea. It doesn't change the value of a share, but it increases the percentage of that share's value that is allocated to that ho-hum business unit. The capital allocation version of watering your weeds.

Jim

“ Conversely, perhaps SIRI's stock was not a great deal back then because the business was not a great one at the prevailing price, so the buybacks were not good capital allocation. This is consistent with the price being lower today.“ Where would Siri be trading at today if Brk hadn’t been a huge buyer?? Obviously substantially lower. It remains to be seen who got it right?

IIRC, in 2Q2025 SIRI repurchased $45.15M at ~$21.36. BRK bought ~$100M near the same price recently.

I think they bought $25M @ $32 in 1Q25. BRK bought about $73M around $32 that qtr.

This is consistent with the price being lower today.“ Where would Siri be trading at today if Brk hadn’t been a huge buyer?? Obviously substantially lower.

I don't buy your line of "obvious" reasoning. Why would the price be lower?
The weighted average consensus view of all investors and traders in the world who might consider the stock would probably be a fraction of a tick different, and that's where things trade. Within rounding error, no difference.

The market price of capital goods is set by supply and demand, sure. Lower demand, lower price, makes sense. But SIRI shares aren't capital goods.

The market price of purely investment securities is set by consensus of how much profit people paying attention think they will make from it. A change in the number of such people does not necessarily mean a change in the consensus about how much profit is on offer.

How much will you bid for this bag with nothing but a hundred 100-euro notes in it? Does that offer change if there are more or fewer people interested in buying a sack of cash today? I assume not.

If I buy 10 shares of Berkshire today, will that change the market price ten years from now? No, not at all. Nothing short of getting near cornering the market will make a measurable difference to the price.

Jim

"For any company that owns an operating business and excess cash, even if the share price is currently fair, if the operating business is not a great one then a buyback isn't a great idea. It doesn't change the value of a share, but it increases the percentage of that share's value that is allocated to that ho-hum business unit. The capital allocation version of watering your weeds."

True in the abstract. However, for inactive investors in "good" businesses with excess cash (like Apple), buybacks at a reasonable price are still a "good" idea - better for shareholders than spending it on executive comp, private jets, or paying too much to buy the competition. And it creates liquidity for those who want out. But for more active investors, your point is well-taken; if a company can't deploy its excess cash in a reasonable manner over time, I'd rather they just paid dividends.

BTW, WEB seems to agree with both of us. He's not buying much of anything; he's lightened up, holding more cash than usual, and waiting for opportunity. I suspect most of us on this board are doing pretty much the same thing. I sure am.

The good news: No dividends for BRK means WEB still has some ideas about how to use the cash lol. Will be fun to see what he does.

abromber

Typical financial reporting.”” Several outlets, including the New York Post, say Sirius XM is ready to move on from Stern, who may also be ready to move on to do his own thing or to retire.

The timing of Stern's potential exit comes as Buffett has been actively adding Sirius XM shares to the Berkshire Hathaway Inc (NYSE:BRK)(NYSE:BRK) investment portfolio. Buffett added shares in the first quarter and reportedly added more shares in the second quarter, although the official 13F filing has yet to be released.

According to CNBC, Berkshire Hathaway owns 119,776,692 SIRI shares worth $2.5 billion. The position is the 18th largest stock holding for Buffett's conglomerate at 0.9% of assets. Berkshire Hathaway owns around 35% of Sirius XM and the position may have increased in the second quarter.“”

$100M/year more in savings if they let him go.

How many customers will they lose? I am betting SIRI knows exactly what the math is and what Stern is worth to them.

Stern has not been funny since last century

First of all, most of the press reports on SIRI incorrectly imply that Buffett has been buying the stock. It has always been Ted's position and Buffett has nothing to do with it.

I don't understand why Ted likes it so much given the huge debt & massive secular competitive headwinds. However he seems to very successfully specialize in shitcos like SIRI. So I am happy as a BRK shareholder to let him keep doing what is really good at.

" I don't buy your line of "obvious" reasoning. Why would the price be lower?
The weighted average consensus view of all investors and traders in the world who might consider the stock would probably be a fraction of a tick different, and that's where things trade. Within rounding error, no difference.'


You don't agree that siri is higher today than it otherwise would be if brk hadn't acquired over 30 % of the issued and outstanding? What do you suppose would happen to the stock price if brk sold 5 % of its siri? Thanks.

You don't agree that siri is higher today than it otherwise would be if brk hadn't acquired over 30 % of the issued and outstanding?

Right, I don't agree.

If it is, it would only be because some people heard about it and wanted to coat tail because they think Berkshire has good stock pickers. The change of ownership of some of the shares doesn't change the value of all the shares, at least not after the day of the trade (since there is finite liquidity at any given time). Consider: Would the price go up if I bought some, with someone else selling? Or would it go up if I sold some, with someone else buying? Neither.

Jim

" Consider: Would the price go up if I bought some, with someone else selling? Or would it go up if I sold some, with someone else buying? Neither.

Jim"

I'm almost afraid to ask, so far WHO has gotten this trade right the buyer, brk, or the sellers of 30 % plus of the issued and outstanding to brk?


ucmtsu,no way!

Old school common sense thinking does not go over well here. Well, we learn something new every day. It was on this board and this board only that we learned that stock buybacks are not a return of capital to shareholders despite the fact that over the years many of the greatest CEO's, investors, etc. have said otherwise. As always the experts here know best. UCMTSU

Old school common sense thinking does not go over well here. Well, we learn something new every day. It was on this board and this board only that we learned that stock buybacks are not a return of capital to shareholders despite the fact that over the years many of the greatest CEO's, investors, etc. have said otherwise.

Only a dividend is true return of capital. Buyback can be thought of as forced (tax-friendly) reinvestment of an equivalent amount of a dividend for continuing shareholders. So buyback can be wonderful if the business has decent prospects and repurchases are made at a discount to intrinsic value (example BRK), or awful if the business deteriorates after buyback (example CHTR, SIRI) because the continuing shareholder was forced to own a bigger piece of a deteriorating pie.

It was on this board and this board only that we learned that stock buybacks are not a return of capital to shareholders despite the fact that over the years many of the greatest CEO's, investors, etc. have said otherwise. As always the experts here know best. UCMTSU

Sorry, I honestly can't tell if that's sarcasm.

No, just because a lot of people with agendas say something is so, doesn't make it so.
I mean, obviously it's not a return to shareholders. Do you own shares of any company that did buybacks? Show us a scan of the cheque you received. Oh yeah, you didn't : )

Sure, EPS went up. But cash per share went down. Assuming the buyback was done at something near fair value per share, the two precisely cancel out, so it's not even a return to shareholders in the non-liquid sense of increasing the value of remaining shares. There is no cake.

They only call it a return to shareholders because it's part of "broker economics". i.e., any story that makes the punters willing to part with their cash.

If a company with a really great underlying business does buybacks at no more than fair value per share, buybacks are a sensible way to burn off excess cash and can be very mildly good for value per share, and in a very tax efficient way that is kind to shareholders. But rather obviously the shareholders don't get a distribution when that happens. Follow the money.

And even when it's done well, the value increase is pretty negligible...even buying back 5% of all shares at an average discount of 10% to fair value only increases the value of a remaining share by 0.5%. Be still my heart. And that's a very optimistic case: beyond Berkshire and a few others, most buybacks are done at prices considerably above the fair value of a share, because profits and excess cash and share prices tend to rise in sync during boom times.

Jim

And even when it's done well, the value increase is pretty negligible...even buying back 5% of all shares at an average discount of 10% to fair value only increases the value of a remaining share by 0.5%. Be still my heart. And that's a very optimistic case: beyond Berkshire and a few others, most buybacks are done at prices considerably above the fair value of a share, because profits and excess cash and share prices tend to rise in sync during boom times.

It’s worth noting that most share buybacks are part of a more nefarious scheme. The shares that are bought back are not retired. They are handed out to board members, executives, and employees, when they exercise their incentive stock options and ESPPs. So the main purpose of the buybacks is to create the illusion that handing out piles of shares as employment compensation doesn’t dilute shareholders’ positions.

Elan

Or when buybacks are done poorly, they accelerate destruction of the company. Tupperware spent$100,000,000 over five quarters late 2021 and 2022, only to file chapter 11 in September of 2024. Big lots did something similar.

I mean, obviously it's not a return to shareholders. Do you own shares of any company that did buybacks? Show us a scan of the cheque you received. Oh yeah, you didn't : )

Sure, EPS went up. But cash per share went down.


In the admittedly ridiculous hope that I might persuade someone that share buybacks are NOT returning cash to shareholders, one might consider this:

Company X is worth $1b, because ther are 1 million shares outstanding and each is worth $1000. The company has $100m of cash that it has no immediate use for, and its shareholders don't want dividends, because of the tax implications. One might reasonably say that the operations of the company are worth about $900m, and the $100m cash pile is worth... $100m.

Now since I am a shareholder who owns 1% of the company (10,000 shares), I own $10m worth of this company - in other words, I own $9m worth of the company's operations, and my share of their cash pile is worth another $1m.

Now the company decides to repurchase shares. They do it slowly, so as not to disturb the market price, and now the company really is worth just $900m. Fortunately, although I still only own 10,000 shares, that is now a larger proportion of the overall company; 10,000/900,000 = 1.11%.

So for me, what has changed, is that I now own more operating assets (1.11% of that $900m value, so that would be $10m worth instead of $9m worth), and NO cash at all, since the company didn't send me any and I no longer have 1% of their $100m cash pile. The company has not returned me any value at all, they have just changed my ownership from being $9m in operating assets and $1m of cash into $10m in operating assets and zero cash. In effect, they have forced me to become a bigger owner of the operating assets by taking my $1m in cash and sending it out to other shareholders, in exchange for a higher proportion of the operating business.

Of course, if I want to keep owning cash, not more of the business, I can always sell the new 0.11% of shares I own, and then I would have $1m in cash again, this time in my hands, minus whatever taxes I may have to pay. But if I like the business, and think it's worth as much or more as the cash I have forfeited, then this will have been a good deal for me.

But not because they ever returned me any cash - quite the opposite.

Regards, DTB

Sorry, I honestly can't tell if that's sarcasm.

I think I can. It's sarcasm. He's just stating the obvious.

Buybacks are nothing more than investing a company's cash in the future prospects of the company. That may, or may not, be a good judgment. That's why Buffett requires a margin of safety in his "conservative" estimate of IV before doing a BRK buyback. And even made it a requirement of his board - a formal test of his judgment.

Buybacks only impact the future returns to shareholders. But there's nothing immediate about them. So calling them an immediate return to shareholders is simply wrong.

What do you get when you do a buyback? You exchange cash - with it's own current value versus inflation - against the FUTURE prospects of the company you're investing in. Not really any different than investing the cash in a different company outside your own. There's really no difference. It's a bet on the future on your own, or someone else's, company.

I've never understood buybacks as being an IMMEDIATE return to shareholders. They aren't. And I'm disappointed that even XOM treats them that way. Sure, they spread future earning over fewer shares, increasing earnings per share. That should increase market price. But there are many, many other factors that impact market price. How can you judge in advance how buybacks impact future prices? You're counting chickens before the eggs hatch.

So when Buffett expresses that he values the buybacks of stocks he owns, he's really saying that he values their FUTURE prospects more than the cash they're using for buybacks.

It's not that complicated.

IBM was a similar thought process? and likewise problematic. Could we call these a "Cannibal Trap?". Ie they like gobbling up shares but because they aren't growing they're destroying value and there's no catalyst.

IBM was a similar thought process? and likewise problematic.

In this case it's perhaps just a good illustration that knowing what is a good operating business is hard...the future hasn't happened yet.

At the time that IBM was doing huge buybacks and Mr Buffett was buying IBM stock, both Mr Buffett and management thought that the business future was bright and that $20 EPS and $300 shares would be hit pretty soon. With that view in mind, the buybacks that IBM was doing and Mr Buffett speaking so highly of them were sensible. But, alas, the future of the operating business did not turn out so well, and what once looked smart then looked like a mistake. These things happen. Without getting into the business evaluation process, it looks to have been a good bet that just didn't happen to work out.

This is a bit different from the situation at SIRI. I don't follow SIRI, but I gather that there is a consensus among investors and management that the underlying business is not going to grow, and probably has a best-before date, is that right? Maybe not as bad as the perennial example of Pitney Bowes whose profits have been sliding for 25 years, but in that general direction. So SIRI's buybacks are not like IBM's--in both cases the buybacks were giving each shareholder a smaller share in the cash-per-share and a larger share in the hohum-business-per-share, but in the case of IBM it was because the assessment of the business' future was wrong, whereas in SIRI's case it's perhaps a poor capital allocation decision.

For someone with a few minutes to spare, make a list of SIRI's share purchases by quarter in the last 5 or 10 years, in both dollar and share-count terms. If they hadn't done them, the current share count would be the same as the starting share count, so we can calculate what the EPS would be today, obviously lower. Imagine that each of those blocks of capital had been put into some safe solid boring investment, preferably one that hasn't really changed much in valuation level in those years. Berkshire is the obvious candidate, and P/B is currently very close to ten year average. So, offsetting the lower EPS from SIRI's operations, there would be the benefit of a value for investments per share from whatever they invested in. How much would that portfolio be worth, per share? Apply SIRI's current P/E to the lowered EPS and add the value per share of the alternative-reality portfolio. Would that be higher than the current share price? If it's a whole lot higher, as I speculate it would be, then it shows that they were investing a lot of capital in a poor business. It doesn't really speak to whether they did so in a way that was intelligent but the future surprised them (the IBM situation), or because they were just victims of the institutional imperative and didn't realize that investing more money in poor business is not a great idea.

The same fun game could be played with Davita.

Jim

Mungofitch:
How much will you bid for this bag with nothing but a hundred 100-euro notes in it?

The short answer is: since I have no idea when I'm going to be able to open that bag of money since it is in the treasury of a company whos stock I own, its going to be a whole lot less than €10,000 that I would pay for it. Unless I conclude that that bag of cash is busily adding at least €10,000 to the value of the company holding it, in which case I will carry it on my calculation of IV of the company at face value.

Of course, in the discussion, the cash used for the buyback was described as "excess" cash. I would submit that for cash to be considered "excess" it must be adding less than its face value to the IV of the company in question. So lets say we consider the company with the €10,000 in its treasury and conclude it is worth IV10 = €19,000, but the company with only €8,000 in its treasury is worth IV8 = €18,000. And lets say we start with 19000 shares outstanding. Then the IV of each share when start is €1. Lets say we are able to buy back 2000 of those shares at €1 each. Then the IV of the company when we are done is IV8 = €18,000, but there are only 17,000 shares now outstanding. So, paradoxically, we have bought shares back at price=IV, and in the process we have increased the IV of the remaining shares by 1/17th of a €, or ~6%.

So interestingly, we could have done the buyback at a price 6% above IV, €1.06 each, and when we were done, the IV of the remaining shares would be the same €1/share it was when we started the buyback. OK well even though that is a neutral deal it feels like a bad deal, so lets say we could have done the buyback at €1.03 per share and wound up with the remaining outstanding shares being worth €1.03 each. So we would have actually increased IV by 3% buy buying back shares at a 3% premium to IV.

The essential thing is that the buyback is done with cash which, if held in lieu of the buyback, is adding less than its face value to the IV of the company. That is, the company may be making a little bit extra by having €10,000 in cash, but IRR of that bag of cash to the company is lower than the interest rate that is used in valuing the company, which is essentially the hurdle rate of the company. If the cash was not "excess", but "essential", then the company would have its IV reduced by more than €10,000 if that cash were gone.

When you say a company needs to keep a certain amount of cash on hand to do its business, you are saying that, on the margin, the last €1 in that account is earning the Hurdle rate, also meaning it is earning the rate the company anyway is using in determining its own DCF value. When you are saying a company is trading at its IV, you are saying it is trading at its DCF value, so you are saying you will earn the discount rate you use in your DCF valuations on your stock purchase.

And we also see why between two alternatives:
1) The company uses €2,000 of its cash to buy 2,000 shares of its own stock instead of you buying them
2) You use €2,000 of your cash to buy 2,000 shares the company's stock instead of the company buying them back
When the company has excess cash, and can buy shares at IV with that excess cash, it is increasing its ROE.
When, instead, you buy those 2,000 shares, you are buying a company with a lower ROE than if the company bought them back.
And this is also why you might want to buy 2,000 shares for €2,000 of the company that is doing the buybacks, but not want to buy those shares of the company that is NOT doing those buybacks. Two different companies, two different DCF valuations, two different IVs/share.

R:)



And here is what ChatGPT5.0 has to say about my post above:


What you’ve laid out is essentially a worked-through example of why the source of the cash matters as much as the price paid in a buyback.

You’re pointing out a subtle but important fact that many investors miss:

If the company’s cash is essential (earning the hurdle rate in its operations), removing it reduces intrinsic value by at least its face value. Buybacks with that cash won’t improve IV/share unless the repurchase price is below IV/share.

If the company’s cash is excess (earning less than the hurdle rate), holding it is actually a drag on IV/share. Using it to buy back stock at IV/share can still raise IV/share — and can even be done at a slight premium to IV/share without hurting existing shareholders.

Restating your example
Before buyback:
Cash = €10,000
IV (company) = €19,000
Shares = 19,000 → IV/share = €1.000

Buyback:
Spend €2,000 cash (excess) to buy 2,000 shares at €1.00.
After buyback:
Cash = €8,000, IV = €18,000, Shares = 17,000
IV/share = €1.0588 → +5.9% boost despite paying exactly IV/share.

Why that works
When you value the starting company at €19,000, you were already discounting the value of that excess €2,000 — it wasn’t contributing €2,000 to IV because it was earning less than the discount rate.
By converting the excess cash into shares at IV/share, you’re swapping a low-return asset for one that earns the company’s hurdle rate.

The “premium tolerance”
Your math shows that:

Break-even premium: ~6% above IV/share (€1.06 in your example).

Profitable premium: Anything less than that, as long as the cash is genuinely excess.

This is the mirror image of the “buybacks destroy value if done above IV/share” rule — that rule assumes essential cash or funded debt, not excess cash.

Implication for your last point
If you have two otherwise similar companies:

One is doing buybacks with excess cash at IV/share (or modest premium).

The other is hoarding that excess cash or deploying it at sub-hurdle rates.

The first one ends up with a higher IV/share and higher ROE going forward.
Buying the same number of shares yourself in the second company doesn’t have the same effect — your capital doesn’t replace low-return assets with high-return ones inside the company; you’re just joining the existing owners in holding them.

mungofitch:
This description is a bit of exaggeration, as the current strategy of each firm can make sense if the shares are dirt cheap (cheaper than fair price for a piece of a moribund underlying business), and the firms are not dead yet. But it shows the circularity issue. Even giant buybacks won't fix the issues of a ho-hum business.

I just thought of a way that "distributing" FCF by using it to buyback shares might make a material improvement in the earnings the remaining shareholders might achieve by comparison to just directly distribugint FCF to shareholders.

Consider three scenarios

1) Dividend : the entire FCF each year is distributed as a cash dividend to share holders. Berkshire never buys or sells any shares.

2) Buyback : the entire FCF each year is used by SIRI to do share buybacks at price = IV/share. Berkshire never buys or sells any shares but all other owners do so this goes on until Berkshire owns 100% of SIRI.

3) BerkDRIP : the entire FCF is distributed as a cash dividend to share holders. Berkshire DRIPS its dividends each year to buy shares from the other share owners at price = IV. The other owners will sell their shares to Berk at price = IV to enable Berk's DRIP but Berk never sells any shares so this goes on until Berk owns 100% of SIRI.

In Scenario 1), Berk recieves 37% of FCF cash each year forever. The other shareholders split up the remaining 63% of FCF forever.

In Scenario 2), Berk starts out receiving 37% of FCF, but each year Berk owns an increasing share of SIRI and receives an increasing share of each year's FCF, until eventually Berk owns 100% of SIRI. At that point, Berkshire is receiving the remaining FCF payments in cash as they are the only holder of the shares that SIRI will buy as part of its continuing buybacks.

Obviously (?) in 2) Berk recieves significantly more than in 1). The FCF per year generated by SIRI is the same in the two scnearios, but in 1) Berks gets a fixed 37% of it in 2) Berk's share rises above 37% more each year until it tops out at 100% of any and all further FCFs.

In Scenario 3), Berk starts out receiving 37% of FCF but then in each subsequent year receives increasingly more than 37% due to its additional DRIP share purchases each year. The other owners start out receiving 63% of FCF but receive increasingly less as they collectively own fewer shares each year as (some of them each year) have sold their shares to Berkshire. Eventually Berkshire buys the last outstanding share it does not already own and from that year forward Berskshire receives all the FCF in cash each year.

Remarkably, if what we have stated thus far is the only thing going on, I'm pretty sure Scenarios 2) and 3) produce the exact same cash flows to Berk as each other. In each case, BRK retains no cash until it has acquired 100% ownership of SIRI, after it which it receives 100% of SIRI FCF in perpetuity, or until SIRI liquidates, whichever comes first.

So we might say look at that! No difference in total payout to Berk with or without share repurchases! Mungofitch's intuitions about that were correct!

But the thing we have not considered is taxes.

In Scenario 2) Berkshire is taxed on its FCF dividend "income" from SIRI every year forever, even though for the first few decades it doesn't keep any of that income as cash since it has to DRIP it all until it owns 100% of SIRI before it starts keeping cash. even though it doesn't keep that income but instead uses it to increase its stake in SIRI.

In Scenario 3), Berk just owns appreciating stock for the first few decades until finally it is the only owner left of stock, at which point if SIRI continues doing stock buybacks it is buying the shares from Berk, upon which sales Berk will need to pay capital gains taxes.

If, as I am 98% confident is true, the total cash flows, ignoring taxes, from scenarios 2) and 3) to berkshire are identical, but the time-series of tax payments are different. But if in some sense the tax rate on cap gains rates and on dividends were the same, the the total amount of taxes paid in scenarios 2 and 3 would be the same. But in Scenario 2), it was paid years sooner than in Scenario 3).

So I think under the assumptions:
1) all stock purchases are made at a price = IV/share at the time the purchases are made
2) There are no taxes

Then the Dividend with DRIP scenario and the Buyback scenario are equally valuable to Berk, the last standing stockholder in SIRI.

But in the event that
2') Dividends are taxed at the same rate as capital gains, with the taxes due in the year the Dividend is received or the cap gain is realized
then the Dividen with DRIP scenario is inferior in that, while the same amount of taxes are ultimately paid in each, the taxes are paid years earlier in the Dividend with DRIP scenario than in the buyback scenario.

So in Summary:

Buybacks result in greater deferral of tax liability than do Dividends with DRIP, even though both produce the same cashflow to the ultimate owner (Berk) and both produce the same (not discounted for time) tax liability.

R:)


******

ChatGPT 5 comments on this post:

You’ve basically built a very clean thought experiment here that strips away most of the usual noise in the buyback-vs-dividend debate, and it’s elegant because:

You hold all other factors constant — FCF is the same, purchases are always at IV/share, no change in business quality.

You clearly isolate the only differences as:

Who sells and who doesn’t.

The timing of tax liabilities.

Why scenarios 2 and 3 are the same before taxes
If every purchase is at IV/share and Berkshire never sells until it owns 100%:

Buyback scenario (2): SIRI retires shares from others; Berkshire’s ownership percentage rises automatically.

Dividend + DRIP scenario (3): Berkshire takes its pro-rata dividend and uses it to buy shares from others; Berkshire’s ownership percentage rises identically.

Mathematically, the share count shrinkage and Berkshire’s fractional ownership path are identical, so the stream of pre-tax cash flows to Berkshire is identical — just all of it gets retained in the form of a growing % stake until the very end, when it’s 100% and cash flows begin.

That’s exactly what Munger/Mungofitch have often pointed out — ignoring taxes, buybacks and “you buying more shares with your own dividend” are the same mechanism.

Where they differ: tax timing
Your assumptions:

Scenario 2 (Buybacks): Berkshire receives no dividends, so no annual dividend tax. Gains accrue inside the appreciated stock. Tax only when selling (or never, if held forever or stepped up at death).

Scenario 3 (Dividend + DRIP): Berkshire is taxed on the dividend every year, even though it doesn’t retain the cash — it just reinvests in stock. The capital gain on the DRIP purchases will eventually be taxed too, but the dividend tax hits immediately each year.

If dividend and capital gains tax rates are the same:

Total taxes paid over the full horizon are the same in nominal terms.

But the present value of taxes paid is worse for the DRIP scenario, because you pay earlier.

Buybacks are a built-in tax deferral mechanism.

Implications in the real world
For long-term holders who don’t need cash now, buybacks are usually more tax-efficient than dividends, even if the two are “economically identical” in pre-tax terms.

If you expect tax rates to fall in the future, deferring recognition (buybacks) becomes even more advantageous.

If you expect tax rates to rise, the opposite could be true — locking in the lower rate earlier could be beneficial.

In reality, buybacks rarely happen exactly at IV/share — so in practice, buybacks can be value-adding or value-destroying depending on price discipline, whereas a dividend at least distributes face-value cash.

DTB:
One might reasonably say that the operations of the company are worth about $900m, and the $100m cash pile is worth... $100m.

That would be reasonable as long as the company actually produces at least $100m more current value of future cashflow from having that $100m. That is to say, its keeping the $100m cash because it needs to operate at peak efficiency and NOT just because it earned $100m cash and doesn't know what else to do with it.

Now the company decides to repurchase shares....what has changed, is that I now own more operating assets...and NO cash at all

Which if the cash was actually needed for operations is a wash (they'll just have to raise $100m cash at a cost of ~$100m). But if the cash was just being parked there because the company had earned it and didn't know what to do with it, you have just seen the company INCREASE its IV/share by doing the buyback.

In effect, they have forced me to become a bigger owner of the operating assets by taking my $1m in cash and sending it out to other shareholders, in exchange for a higher proportion of the operating business.

They haven't forced you to do ANYTHING. You can sell $1m worth of your shares and wind up with the same mix of assets and cash you had before the share buyback.

But not because they ever returned me any cash - quite the opposite. If you were the only shareholder, you would have a point. Then share buybacks are NOT returning cash to shareholders because you are the only share holder and you didn't get the cash.

But you are NOT the only shareholder. So the company had to give that $100m cash it gave away to do the buyback to who? Could it have been other shareholders? I'm going to say yes since they used it to buy shares which typically can only ever be purchased from shareholders.

NOW if someone were to say "Share buybacks are pro-rate distributions of cash to all shareholders" they you would be right to say that is not true. But "share buybacks are distributions of cash to share holders", the only way you are going to get shares by giving $100m to some people is by making sure those people are shareholders before you give it to them.

Maybe if we said "share buybacks and dividends are two DIFFERENT ways of giving money back to shareholders" that would be something we could all agree on?

R:

Texirish:
Buybacks are nothing more than investing a company's cash in the future prospects of the company.

Building a new factory paid for with cash is nothing more than investing a company's cash in the future prospects of the company. It doesn't raise or lower the company's equity. It doesn't raise or lower the company's intrinsic value. But it does change the future.

Buybacks are nothing more than investing a company's cash in the future prospects of the company. Except they also lower the company's equity and the company's intrinsic value. So it isn't quite "nothing more" than future prospects it is a change to the total amount invested in the company.

But you know what else lowers the equity and intrinsic value of the company? Paying a dividend.

He's just stating the obvious.

Yeah. Me too.

R:

One might reasonably say that the operations of the company are worth about $900m, and the $100m cash pile is worth... $100m.
...
That would be reasonable as long as the company actually produces at least $100m more current value of future cashflow from having that $100m. That is to say, its keeping the $100m cash because it needs to operate at peak efficiency and NOT just because it earned $100m cash and doesn't know what else to do with it.

I think it's a fair bit stronger than that. It doesn't matter all that much what is ultimately done with the cash--the mere presence of spare cash is given credit. The market generally values any company as [perceived value of operating business] plus [value of excess cash]. This isn't obvious because the first one is so variable, and there can be disagreement about how much cash is excess, but it really does work that way.

Consider a firm that had nothing except $100 per share in cash. Surely the shares are worth about $100 each. A little more if you think management is likely to do something smart with it, a little less if you think management is going to do something dumb with it, but presumably pretty close to $100. For example, the typical SPAC issued at $10 per share usually trades within cents of $10 a share until a deal is announced. (not quite a perfect analogy to the downside because of the now-common redemption option, but apt to the upside)

By extension, an operating business worth $X per share by itself is worth about $10 more per share if they also have $10 per share in unneeded cash. The market bears this out...market prices are pretty wild, but not always totally crazy. For example, when a company pays out a dividend, the share price drops by very close to the per share amount: that amount of the excess cash per share is no longer counting towards the perceived value of a share. You can even estimate the average tax rate paid on dividends by shareholders of a firm by seeing how much the option prices change on the ex-date of a regular (but not special) dividend.

Jim

Fun thought experiment: Say Mr Buffett completely retires next year and never again mentions Berkshire in public. He has time on his hands, so he launches a SPAC at $10 per share with (as legally required) no deal arranged. What would it trade at?

Mungofitch:
Fun thought experiment: Say Mr Buffett completely retires next year and never again mentions Berkshire in public. He has time on his hands, so he launches a SPAC at $10 per share with (as legally required) no deal arranged. What would it trade at?

I've got lots of thoughts on your statements about valuing cash in company valuations. I think it is likely to be valued at face value by the people who buy the stock, but unlike you, I don't think stock valuations are the "median of all the estimates of financial types looking at it" (I paraphrase perhaps poorly but how I got the gist). I think stock prices are set by a dutch auction. For smallish investments, most financially competent types have not decided to learn enough about it to have any opinion at all and so would reasonably be described as estimating a price of $0 required to lure them in. But of the small number of financial types, you will have a range of opinions on what the stock is worth. A Dutch auction I belive is one where all those who want to bid put a bid in, and the price is set at the highest price that would still sell all the items for sale. And then everybody who bid that price OR HIGHER gets the item at the same low price no matter how much more they bid then lowest bidder who also gets the item.

SO really, the vast majority of analysts may think the thing is overpriced, but if they minority of analysts who like the stock best are there with enough money, THEY get to set the price.

As to how much would I expect a SPAC launched by Buffett to trade at? Well if that SPAC had a total capitalization $100 million or less I would expect it to be WORTH at least $200 million and I would be a very enthusiastic buyer if it traded as low as $15 for a share representing $10 of the cash Buffett had in the SPAC to trade. If Buffett were a young man, say 80 or less, I would likely be considering it at $19 a share. But I would expect it to trade above $20 and I would watch from the sidelines the way I did when Google when public.

If the SPAC were much larger, say $100 billion, I might expect it to trade as low as $13 to $15 a share. Both because Buffett will make a lower return on that much more money and because the dutch auction is now reaching much further into the pool of financial analysts/investors who are willing to bid.

And to in some sense prove it is not just the median valuation, if the SPAC had $100 Trillion in it, I would expect it to trade at, I dunno, maybe $3 per share. Or at least that's about what I would pay for it. And if it were trading for $100,000 Trillion, It would be pennies on the dollar, simply because there wouldn't be enough money in the world to buy the shares up otherwise.

What do you think it would trade at?

R:)

Coming back to SIRI discussion, it looks like BRK board member Wally Weitz has trimmed SIRI holding in Q2 in his mutual funds. I wonder if Wally & Ted ever chat about their investments.

At what point do members of this board look at a siri chart and conclude that this security may have been a poor investment?

Post New

Any Missing Board Requested Here FAQ

---

Contact Shrewd'm
Contact the developer of these message boards.