Welcome to Tesla Motors Club
Discuss Tesla's Model S, Model 3, Model X, Model Y, Cybertruck, Roadster and More.
Register

Tesla, TSLA & the Investment World: the Perpetual Investors' Roundtable

This site may earn commission on affiliate links.
Dave Lee's video does a nice job reviewing the anticipated new "unboxed process" @1:30 that will be fundamental to reducing costs and changing the factory floor redesign. This is a very significant step change on it's own.

What the video suggests will be fascinating over the next few years to follow. To what extent will Dave's take on using humanoid robots (Optimus) in the factory come true. Will dividing up the car components as Dave describes allow for a fundamental change in leveraging humanoid robots working "around the car's components" enabling Optimus robot usage much earlier in the Optimus development. If yes, the disruption to the manufacturing process will be massive. Only time will tell and kudos to Dave for sharing this potential insight.

 
You do not, and no one is saying so. Increasing voltage by 4x reduces current by 4x.
Ohmic heat losses in the wire are reduced 16x. (I^2*R)

End of melodrama
Um. Yep: Go up by 4X in V, down by 4X in I, and, yup, in that same size wire, P goes down by 16X, as you nicely point out.

Yessa butta: The whole point of the exercise is to go to a smaller size wire and so use less copper. Smaller wires have resistance that goes up as the cross-sectional area goes down. So, given that Tesla wants to drop the mass of copper being lugged around the landscape, they'll play engineering follies to determine exactly what gauge wire. They'll probably not use a new copper wire with cross-sectional area that's 1/16 the original, but the choice of losses in wire vs. efficiency of moving the car around will be a fun one for them.
 
Predictions for investor day:

  • Tesla mainly says stuff we already know (via crowdsourced knowledge sharing) and they just blatantly spell it out (i.e. the ROIC on their factories, vertical integration, raw material contracts) for an institutional investor audience
  • Tesla probably talks about financial impact of TWh growth (again, stuff we already know) and that's how to think of the company
  • All this is wrapped up within Master Plan Part 3, which essentially boils down to a 2030 projection of how they'll create a bunch of TWh that will feed into their product mix
  • Potential to be extra screwed in shareprice short term if Tesla says "redistribution of TWh is more important than # of cars produced, 20 million not as important as deploying TWh in areas like Semi and Megapack" and TMCers/Stephenson/Warren all try to swoop in and spin a positive narrative to that while Wall Street says "Tesla backs off long-term 50% growth target!" (for the record I'm okay with this, but if this statement comes true in the short term it could really tank the stock)
  • .Tesla talks about generation 3 platform from manufacturing standpoint, maybe cost standpoint, but does NOT reveal a small compact car. Only talks about it in abstract levels (maybe "we can do this whenever we want") because they don't want to osbourne 3 sales
  • Yes, your standard high-level overview of Dojo, Optimus, FSD, which no institutional investors care about because they're so far away from material financial impact (and looking at the agenda, not enough time to really cover these)
  • Maybe a robotaxi reveal (which would actually be bad for share price, "omg Tesla commiting capex to a car when FSD is never gonna happen"). Maybe a van / delivery vehicle reveal? Something's gonna be revealed that they're building in Mexico.
  • And like Autonomy Day, Battery Day, AI Day 1, AI Day 2, immediate disappointment followed-up by a flurry of Youtube videos / paragraphs on why what Investor Day said was revolutionary and why everyone so stupid for missing out on the breadcrumbs!!!
Hope I'm wrong lol.
Well…I was right. Sigh.
 
The tunnel can be as long as needed, and I can't think of any fundamental reason it can't go under mountains.

The thing not being accounted for is how many miles would you like your "new" car to have on the odo when you pick it up?

If trucking to the rail is good enough for GigaTexas, it should work for GigaNuevoLeon.
 


1677902780884.png

At least they're trying 🥴
 
Last edited:
Oh well .. (such confidence while being wrong, ChatGPT!)

Me: What is Tesla's Master Plan 3?

ChatGPT: Tesla's Master Plan 3 (also known as "Tesla's Master Plan, Part Deux") was announced by Elon Musk, CEO of Tesla, in July 2016. The plan focuses on expanding Tesla's product offerings beyond electric cars and becoming a sustainable energy company.

The main components of the plan are:...

Me: Not master plan 2, I want no know master plan 3.

ChatGPT: I apologize for the confusion in my previous response. As of my knowledge cutoff in September 2021, Tesla has not officially announced a "Master Plan 3." The last known master plan from Tesla was "Master Plan, Part Deux," which was announced by Elon Musk in 2016 and included the goals of producing more affordable solar power and expanding the company's electric vehicle lineup to include trucks, buses, and other forms of transportation.

It is possible that Tesla may announce a new master plan in the future, but as of my cutoff date, there has been no official announcement. If a new master plan is announced, I will be happy to provide an update.
 
“Scout” Is VW.

IMO it’s good timing to reinvent that brand. The classic scout has good lines… not sure about it’s reputation, but it was a decent looking truck.

For VW, a good way to get into both pickups and improve their EV presence in the US. They just have to figure out those pesky profitability issues and compete with Cybertruck.

Maybe not good timing after all.


EDIT: Ugh. I forgot what this looked like. And people whine about the Cybertruck’s looks?

1677904515720.jpeg
 
“Scout” Is VW.

IMO it’s good timing to reinvent that brand. The classic scout has good lines… not sure about it’s reputation, but it was a decent looking truck.

For VW, a good way to get into both pickups and improve their EV presence in the US. They just have to figure out those pesky profitability issues and compete with Cybertruck.

Maybe not good timing after all.


EDIT: Ugh. I forgot what this looked like. And people whine about the Cybertruck’s looks?

View attachment 913628
The original IH Scout had a very strong following. It was a close competitor with Jeep, Bronco, etc. Smart move by VW to cash in on that branding, even if it's been collecting cobwebs for quite some time.
 
Tesla estimates that $125 - $150B of remaining CapEx is required to get to 20M veh/yr and 1 TWh of scale. Why isn’t this getting more attention?

1677904429430.png


Zach said “Maybe this total investment looks large. I actually think it’s quite small relative to our ambitions”. That’s an extremely modest way of saying it. The ROIC on these investments will be crazy.

At 20M cars and 1 TWh per year, Tesla could easily earn this much per year, and probably much more. That is without Solar ever providing significant earnings and without autonomous driving, Optimus or any other AI stuff. Conservatively, something like $7k gross profit car and $40/kWh gross profit for batteries would yield approximately $125-150B net income post tax. Tesla could probably do double or maybe even triple these numbers.

That’s means the entire investment will be recouped with the cash flow from a year or less of full-scale production. Actually, in reality it’ll get quickly recouped while the growth is happening because of the ridiculous IRRs on factory construction Tesla will be getting, so on a net basis most of the cumulative CapEx spend will have already paid for itself by the time full-blown 20M & TWh scale is reached. That’s why Zach was saying this will all comfortably be funded with free cash flow along the way.

I’ve written about Tesla’s amazing return on investment on factory CapEx before but the Gen 3 platform might do even better than these numbers. I’m getting IRR estimates of like 100% per year. Not a typo, 100% internal rate of return.

For about 17 years, Tesla was a cash flow negative company because their investments in growth were exceeding their operating cash flow. Then in 2021 it started to flip sharply into the opposite situation, when the arrival of Giga Shanghai and the Model Y vaulted Tesla’s cash generation to a new level at the same time as their CapEx per unit of production capacity was being slashed aggressively by like 50% or more. Now Tesla’s doing it again with Gen 3 and GigaMex.

Let’s do some math. They have 2M veh capacity right now. Even if we’re as pessimistic as possible and assume all of that $150B goes into cars instead of batteries, then that’s $150B / (20-2)M = $8.3k / car per year of capacity. Now, Tesla is going to be earning roughly this much gross profit per car. Something like $30k avg price and $22k avg cost. Depending on how fast we assume the factory is built and ramped, this yields an IRR of around 50-80%. If the actual investment for car factories is maybe $100B of that overall $125-150B estimate, then that’s $5.3k per car per year of capacity and the IRR goes to approximately 100%.

Now guess what, economically it doesn’t make any sense to get 100% ROI and just stop there. What that means is you should keep investing in MORE growth until diminishing returns kick in and the ROI on each additional project drops to closer to the discount rate (10% or whatever you want to use, but nobody is using a 100% discount rate in the real world). It would make no sense with respect to Tesla’s finances nor mission to stop growth at the stated target levels, *if* the margins can be maintained and *if* these CapEx projections are even remotely accurate. What does make sense in the long run is to drop prices even lower, expand volume massively to more than compensate for the thinner margins, and basically take over a huge swath of the market. Tesla with Gen 3 will be able to offer great value for prices so low that customers just can’t resist and competitors are incapable of matching. The numbers presented by Tesla suggest that growth will continue far beyond the 20M and 1 TWh level.
 
Last edited:
The original IH Scout had a very strong following. It was a close competitor with Jeep, Bronco, etc. Smart move by VW to cash in on that branding, even if it's been collecting cobwebs for quite some time.
I thought so until I saw the concept render.

No idea what they were thinking. But it is otherwise good timing reviving a brand with a good reputation. With VW’s reputation and dealer network plus the Scout branding, should be a winner.

Just… that render. Ugh.
 
  • Like
Reactions: SmokyPeat
I thought so until I saw the concept render.

No idea what they were thinking. But it is otherwise good timing reviving a brand with a good reputation. With VW’s reputation and dealer network plus the Scout branding, should be a winner.

Just… that render. Ugh.
You know how renders are- the actual product might be much more palatable. Even without the favorable Scout branding, the Scout name has a lot more appeal than ID 7, or ID Shizizzle, or whatever name the VW think tank would probably come up with otherwise.
 
Tesla estimates that $125 - $150B of remaining CapEx is required to get to 20M veh/yr and 1 TWh of scale. Why isn’t this getting more attention?
Honestly?

I think the numbers Tesla paints cause analysts eyes to roll into the backs of their heads. It’s pretty hard for people to get their heads around a single company making these kinds of profits. If they posted these sort of estimates, they would probably face a million questions. These guys spend day and night looking at 10-20 different companies each. They look at how many orders of magnitude Tesla is projected to be beyond their typical company and their Excel discounted cash flow models melt down.

The analysts who do take anything Tesla says at face value walk into their bosses office and present their numbers and get fired. Nobody on Wall Street wants to stick out too much, if you are over 20% and wrong, it’s a Career Limiting Activity (CLA). If you miss estimates by -10% every quarter and just revise next quarter estimates upwards each quarter, you are usually only ever be “off” by 10% and keep your job.



Fundamentally the problem is that none of these guys are paid or evaluated based on long term accuracy so it’s easier to stick with the herd.
 
Tesla estimates that $125 - $150B of remaining CapEx is required to get to 20M veh/yr and 1 TWh of scale. Why isn’t this getting more attention?

View attachment 913626

Zach said “Maybe this total investment looks large. I actually think it’s quite small relative to our ambitions”. That’s an extremely modest way of saying it. The ROIC on these investments will be crazy.

At 20M cars and 1 TWh per year, Tesla could easily earn this much per year, and probably much more. That is without Solar ever providing significant earnings and without autonomous driving, Optimus or any other AI stuff. Conservatively, something like $7k gross profit car and $40/kWh gross profit for batteries would yield approximately $125-150B net income post tax. Tesla could probably do double or maybe even triple these numbers.

That’s means the entire investment will be recouped with the cash flow from a year or less of full-scale production. Actually, in reality it’ll get quickly recouped while the growth is happening because of the ridiculous IRRs on factory construction Tesla will be getting, so on a net basis most of the cumulative CapEx spend will have already paid for itself by the time full-blown 20M & TWh scale is reached. That’s why Zach was saying this will all comfortably be funded with free cash flow along the way.

I’ve written about Tesla’s amazing return on investment on factory CapEx before but the Gen 3 platform might do even better than these numbers. I’m getting IRR estimates of like 100% per year. Not a typo, 100% internal rate of return.

For about 17 years, Tesla was a cash flow negative company because their investments in growth were exceeding their operating cash flow. Then in 2021 it started to flip sharply into the opposite situation, when the arrival of Giga Shanghai and the Model Y vaulted Tesla’s cash generation to a new level at the same time as their CapEx per unit of production capacity was being slashed aggressively by like 50% or more. Now Tesla’s doing it again with Gen 3 and GigaMex.

Let’s do some math. They have 2M veh capacity right now. Even if we’re as pessimistic as possible and assume all of that $150B goes into cars instead of batteries, then that’s $150B / (20-2)M = $8.3k / car per year of capacity. Now, Tesla is going to be earning roughly this much gross profit per car. Something like $30k avg price and $22k avg cost. Depending on how fast we assume the factory is built and ramped, this yields an IRR of around 50-80%. If the actual investment for car factories is maybe $100B of that overall $125-150B estimate, then that’s $5.3k per car per year of capacity and the IRR goes to approximately 100%.

Now guess what, economically it doesn’t make any sense to get 100% ROI and just stop there. What that means is you should keep investing in MORE growth until diminishing returns kick in and the ROI on each additional project drops to closer to the discount rate (10% or whatever you want to use, but nobody is using a 100% discount rate in the real world). It would make no sense with respect to Tesla’s finances nor mission to stop growth at the stated target levels, *if* the margins can be maintained and *if* these CapEx projections are even remotely accurate. What does make sense in the long run is to drop prices even lower, expand volume massively to more than compensate for the thinner margins, and basically take over a huge swath of the market. Tesla with Gen 3 will be able to offer great value for prices so low that customers just can’t resist and competitors are incapable of matching. The numbers presented by Tesla suggest that growth will continue far beyond the 20M and 1 TWh level.
Yes, perhaps the most disappointing part of the presentation is Tesla only talks about capex but not the expected revenue and net income generated from such investments. It's hard for analysts to put the two together because you have bears who will plug in a gross margin of zero and bulls plugging in a gross margin of 40%+ so the fight continues on how valuable Tesla should be even though it's obvious that this will be the first trillion dollar revenue company.
 
You do not, and no one is saying so. Increasing voltage by 4x reduces current by 4x.
Ohmic heat losses in the wire are reduced 16x. (I^2*R)

End of melodrama
Why not both? One can reduce both loss in wire and wire size.

4x V, to load (12 to 48)
1/4 x I, to load (loadPower / (4*V))
4x R, of wire (1/4 mass, cross-section)
Results in:
1/4 x W, power loss in wire: ( W=I^2 * R : (1/4 I)^2 * (4 R) = 1/4 I^2*R)

 
Gen 3:

No paint suggests plastic outer panels or pressed stainless steel (thinner and less hard than CT).

Assuming stainless steel, the unboxed process would most likely need the main 3 sections to be welded to one another and then to to outer panels. Is this realistic given that seats are installed etc.?
 
  • Helpful
Reactions: Artful Dodger
Just so we are on the same page. Gen 3 to be half cost. Assuming 20% gross profit for entry vehicles. Cost of US M3 today is $43k sales price minus ~20% = $36k (Munro is at $35k). Halved equals $18k cost for gen 3. Plus 20% equals $22k or $14.5k to the customer with IRA incentives. That is a target perhaps that won't quite be hit and I would much rather Tesla don't sell them at that price (or any price for that matter).

Troy's number is $25k to the customer with IRA incentives...

What is the origin of the $25k car?
 
Some translation of the mexican gigafactory announcements:
Demand problems?
Troy makes compelling arguments if you read the whole thread. I wouldn’t be surprised if margins are at 15% by the end of the year.
60k GBP for a Model Y sounds like more than 15% margins to me...

But anyway, from the thread:

Model Y Long Range price in France
• 64,990€ before 12 January 2023
• 53,990€ after 12 January 2023
• 50,750€ now


I guess Tesla adjusted the prices to match their growing production with demand. Still think margins are really good at these prices, they probably cost the same as Model 3 to produce. Competition will not be happy with this. Might take a while for consumers to figure out how much they save by buying a Tesla instead of anything else, but eventually they will...