When Tesla Robotaxi is going to approved?

And I'm confident that will be available in many cities in The US by the end of this year.

Great. Thank you very much. The next question is, is Tesla still on track for releasing more affordable mode…
Show more


And I'm confident that will be available in many cities in The US by the end of this year.

Great. Thank you very much. The next question is, is Tesla still on track for releasing more affordable models this year, or will you be focusing on simplified versions to enhance affordability similar to the rear wheel drive Cybertruck?

Yeah. We're still planning to release models this year. As with all launches, we're working through, like, the last minute issues that pop up. We're knocking them down one by one. At this point, I would say that ramp maybe might be a little slower than we had hoped initially, but there's nothing, you know, just kinda given that turmoil that exists in the industry right now. But but there's nothing that's blocking us from starting production within the next, within the timeline laid out in in the opening remarks. And I will say it's important to emphasize that, as we've said all along, the full utilization of our factories is the primary goal for these new products. And so flexibility of what we can do within the form factor and and, you know, the the design of it is really limited to the what we can do on our existing lines rather than building new ones. But we've been targeting the low cost of ownership. Monthly payment is the biggest differentiator for our vehicles, and that's why we're focused on bringing these new models with the, you know, the lowest price, to the market, within the constraints I just highlighted.

Great. Thank you very much. The next question is, does Tesla see Robotaxi as a winner take most market? And as you approach the Austin launch, how do you expect to compare against Waymo's offering, especially regarding pricing, geofencing, and regulatory flexibility? Well, okay.
Show less

Fantastic. Thank you very much, Prabhup. Now we will move on to investor questions. We will start with questions from say.com. First question is, what are the highest grits highest risk items on the c…
Show more


Fantastic. Thank you very much, Prabhup. Now we will move on to investor questions. We will start with questions from say.com. First question is, what are the highest grits highest risk items on the critical path to Robotaxi launch and scaling?

And is that a stroke?

Yeah. We've got a stroke on. Sure. Well, just to we're just backed by the disam disambiguate the cyber cat from Robotaxi once again. So the when will the the Teslas because the the Teslas that will be fully autonomous in June in Austin are fully model wise. So that is that's that's currently on track to to be able to do paid rides fully autonomously in Austin in June and and and then to be in any other cities in The US by the end of this year. It's it's very difficult. It's difficult to predict the exact ramp sort of week by week and month by month, except that will ramp up very quickly. So it's gonna be like some basically an s curve where it's very difficult to predict the intermediate slope of of the s curve, but you kinda know where the s curve is gonna end up, which is the vast majority of the Tesla fleet being autonomous. So that that's why I feel confident in predicting large scale autonomy around the middle of next year, but, you know, certainly the second half of next year. Meaning, I I break that there will be millions of Teslas operating autonomously fully autonomously in the second half of next year.

Yeah. But but it it just it just seem increasingly likely that there will be a localized parameter set of batch sort of you know, like, that that that If we especially for places that have, say, very snowy weather, like, say, you're in the Northeast or something, that that like, this, you can think of it's kinda like a human. Like, you you know, if you so you you could be a very good driver in California, but are you gonna be also a good driver in a blizzard in Manhattan?
Show less

[Music] [Music] [Music] good afternoon everyone and welcome to Tesla's second quarter 2024 Q&A webcast my name is Travis axad head of investor relations and and I'm joined today by Elon Musk the teda …
Show more


[Music] [Music] [Music] good afternoon everyone and welcome to Tesla's second quarter 2024 Q&A webcast my name is Travis axad head of investor relations and and I'm joined today by Elon Musk the teda and a number of other Executives our Q2 results were announced at about 3 p.m. central Time in the update deck we published at the same link as this webcast during this call we will discuss our business Outlook and make forward-looking statements these comments are based on our predictions and expectations as of today actual events or results could differ materially due to a number of risks and uncertainties including those mentioned in our most recent filings with the SEC during the question and answer portion of today's call please limit yourself to one question and one followup please use the raise hand button to join the question Q before we jump into Q&A Elon has some opening remarks Elon thank you so to recap uh we we saw large uh adoption acceleration EVS um and then a bit of a hangover as other struggle to make uh compelling EVS um so there been quite a few um competing electric vehicles that have entered the market um and mostly they have not done well but they have discounted their EVS very substantially which um has made it bit more difficult for for Tesla uh we don't see this as a long-term issue but but really as fairly short term um and uh we still OB firmly believe that EVS are best for customers and that the world is headed for fully electrified transport uh not just of cars but also of uh aircraft and boats um despite many challenges the Tesla team did a great job executing um and we did achieve record quarterly revenues energy storage deployments reached an all-time high in Q2 uh leading to record profits for the energy business and uh we're investing in many future projects including uh AI training and and inference and uh great deal of infrastructure to support future products um we we won't get too much into the product road map here because that is uh reserved for product announcement events U but we are in track to develop to deliver a more affordable model in the first half of next year um the the big really by far the biggest differentiator for Tesla is autonomy um in addition to that we we have scale economies and we're the most efficient electric vehicle producer in the world so uh this this any while while others are pursuing different parts of the AI robotic stack we are pursuing all of them this allows for better cost control more scale quicker time to Market and a superior product uh applying not to not just to autonomous vehicles but to autonomous humanoid robots like Optimus uh regarding full driving and rubo taxi uh we we we've made a lot of progress with wh driving in Q2 and with version 12.5 beginning roll out uh we think customers will experience a step change Improvement in uh how well supervised felf driving Works uh version 12.5 has five times the parameters of 12.4 and will mer finally merge the highway and City Stacks um so the the highway stck is so at this point is pretty old um so of issues people encounter are on the highway but uh with 12.5 we we finally moed the two stacks um I still find that that um most people actually don't know how good the system is and I would encourage anyone to understand the system better to simply try it out and let let the car drive you around um one of the things we're going to be doing just to make sure people actually understand the cap abilities of the car is when delivering a new car um and when picking up a car for service to just show people how to use it and just DPP them around the block uh once people use it at all that they they tend to continue using it so it's uh it's very compelling and um and and this I think will be a massive demand driver even unsupervised full self driver will be a massive demand driver um and as we increase the miles between intervention it will transition from supervised full self driving to unsupervised full self- driving and we can unlock uh massive potential in the f um we postponed the sort of robot tax the S product uh unveil by a couple months where we're it's shifted to 1010 so the 10th of October um and this is I wanted to make some important changes that I think would improve the the vehicle the sort of the robot taxi the thing that thing that the main thing that we're going to show and and we're also going to show off a couple of other things um so moving back moving it back a few months allowed us to improve the the robot taxi as well as add in a couple other things for for the product unveil um we're also nearing completion of the South expansion of Giga Texas which will house our largest CL training cluster to date uh this will be an incremental 50,000 h100s plus 20,000 of our Hardware 4 or ai5 Tesla AI computer um with with Optimus Optimus is already performing tasks in our Factory um and uh we expect to have Optimus production version one and in limited production starting early next year uh this will be for Tesla consumption uh it's just better for us to iron out the issues ourselves um but we we expect to have several thousand Optimus robots um produced and doing useful things by the end of next year in the Tes of factories and then in 2026 ramping up production quite a bit um and at that point we'll be providing Optimus robots to uh outside customers that that'll be production version two of Optimus for the energy business uh this is growing faster than anything else uh this is we are really um demand constraint rather than production constraint so we're ramping up production in our us Factory as well as building our building me mega Factory in China that uh should you roughly double our output more than double maybe triple potentially so um in conclusion we're super excited about the progress across the board um we're changing the Energy System how people move around how people approach the economy the undertaking is massive but I think the future is incredibly bright uh you know I really just can't emphasize just the importance of autonomy uh for the vehicle side and for Optimus um although the numbers sound sound crazy um I think Tesla producing at volume with with uh unsupervised MSD essentially enabling enabling the fleet to operate like a giant autonomous Fleet um and it takes the valuation I think to some pretty crazy number arest thinks on the order of $5 trillion I think they're probably not wrong um and long-term Optimus I think is achieves valuation several times at um I want to thank the Tesla team for strong execution and looking forward to exciting years end great thank you very much Elon and vov has opening remarks as well thanks as Elon mentioned the Tesla team Rose to the occasion yet again delivered on all fronts with some notable records in addition to those records we saw our Automotive deliveries go sequentially I would like to thank the entire Tesla team for their efforts in delivering a great qu on the auto business front affordability remains a top of mind for customers and in response in Q2 we offered attracting financing options to offset sustain High interest rates these programs had an impact on Revenue per unit in the quarter these impacts will persist into Q3 as we have already launched similar programs we're now offering extremely competitive financing rates in most parts of the world this is the best time to buy a Tesla I mean if you're waiting on the sidelines come out and get your car we had a record quarter on regulatory credits revenues and as well on net our Auto margins remain flat sequentially this is important to note that the demand for regulatory credits is dependent on other oem's plans for the kind of vehicles they're manufacturing and selling as well as changes and regulations we pride ourselves to be the the company with the most americanmade cars and are continuing our journey to further localize our supply chain not just in the US but in Europe and China as well for the respective factories as always our focus is on providing the most compelling products at a reasonable price we have stepped up our efforts to provide more trims that have estimated range of more than 300 miles on a single charge we believe this along with the expansion of our supercharging network is the right strategy to combat range anxiety since the revision of FSD pricing in North America we've seen adaption rates increase meaningfully and expect this to be a driver of vehicle sales as the feature set improves further cost per vehicle declin sequentially when we remove the impact of Cy Tru while we are experiencing material cost Turing down note that there is latency on the cost side and such reductions would show up in the p&l when the weight built with these materials get delivered additionally as we get into the second half of the year it is important to note that we are still ramping cyber truck and model 3 and are also getting impacted by varying amounts of tariffs on both raw materials and finish Goods while our teams are working feverously to offset these unfortunately it may have an impact on the cost in the near term we previously talked about the potential of the energy business and now feel excited that the foundation that was laid over time is bearing the expected results energy storage deployments more than doubled with contribution not just in from megapack but also power wall resulting in record revenues and profit for the energy business energy storage backlog is strong as discussed before deployments will fluctuate from period to period with some quarters seeing large increases and other seeing a decline recognition of Storage gwatt hours is dependent on a what variety of factors including Logistics timing as we send units from a single Factory to markets across the world customer Readiness and in case of EPC projects on construction activities moving on to the other parts of the business service and other gross profits also improved sequentially from the Improvement in service utilization and growth in a collision repair business the impact of our recent reor is reflected in restructuring other on the income St just to level said this was about $622 million of charge which got recorded in the period And I want people to remember that we've called it out separately on the financials sequentially our operating expenses excluding such charges reduced despite an increase in spend for AI related activities and higher legal and other cost on the capex run while we saw a sequential decline in Q2 we still expect the year to be over 10 billion in capex as we increase our spend to bring a 50k GPU cluster online this new cluster will immensely increase our capabilities to scale FSD and other AI initiatives we rted to positive free cash law of 1.3 billion in K2 this was despite restructuring payments being made in the quarter and we ended the quarter with over 30 billion of cash and Investments once again we begun the Journey towards the next phase for the company with the building blocks being placed it will take some time but will be a rewarding experience for everyone involved once again I would like to thank the entire Tesla team for their efforts great thank you very much bov uh now let's go to investor questions the first question is uh what is the status on the Roadster uh with respect to the Roadster we've completed most of the engineering and um I think there's still some upgrades we want to make to it uh but uh we expect to be in production with Ros for next year great it'll be something special like a whole of Famer I think fantastic uh the next question is about timing of Robo taxi event which we've already covered uh so we go we will go to the next question uh when do you expect the first Robo taxi ride um I guess that that's really just question when do I expect the first when can we do unsupervised for self-driving um it's difficult obviously my optim my my predictions on this have been overly optimistic in the past so um I mean based on the current Trend it seems as though we we should get miles between interventions uh to be high enough uh that it's PR far enough in excess of humans that you could do unsupervised possibly by the end of this year I would be shocked if we cannot do it next year so next year seems highly probable to me based on point simply plots the points in the curve of miles between intervention that Trend exceeds uh [Music] humans for sure next year so yeah thank you very much um our third question is the Cyber truck is an iconic product that uh Wows everyone who sees it do you have plans to expand the Cyber vehicle lineup to a cyber SUV or cyber van I think we want to limit um product announcements to when we have a special specific product announcement event rather than earnings calls great thank you our next question is uh what is the current status of 4680 battery cell production and how was the ramp up progressing yeah U 468 production ramped strongly in Q2 delivering 51% more cells than q1 while reducing Cog significantly uh we currently produce more than 1,400 typ of trucks of 4680 cells per week and we continue to ramp output as we drive cost down further towards the cost parity Target we set before the end of the year we've built our first validation Cy truck with dry cathode process made on our mass production equipment which is a huge technical milestone and super proud of that uh we're on track uh for production launch with dry cathod um mq4 and this will enable sell cost to be significantly below available Alternatives which was the original goal of the 468 program great thank you very much the next question is any update on dojo yeah so so Dojo um uh I should preface this by saying I'm incredibly impressed by nvidia's execution and the capability of their Hardware um and what we are seeing is that um the demand for Nidia Hardware is so high that uh it's often difficult to get the gpus um and uh there just seems there's I I guess I'm quite concerned about actually being able to get state of the Nvidia gpus when when we want them um and uh I think this therefore requires that we um put a lot more effort on dojo in order to have in order to ensure that we've got the training capability that we need uh so we are going to double down on dojo uh and we do see a path to being competitive with Nvidia with with dojo and I think we kind of have no choice because um the demand for ined is so high and the the it's it's obviously their their obligation essentially to raise the price of gpus to whatever the market will bear U which is very high so I think we we've um we've really got to make Dojo work and we will great uh the next question is what type of accessories will be offered with Optimus there's Optimus is intended to be a journalized humanoid robot with a lot of intelligence so it's like saying what kind of accessories would we offer with a human it's it's really intended to be able to be backwards compatible with human tasks so it would you know use any accessories that a human would use um yeah thank you uh the next question is do you feel you're cheating people out of the joys of owning a Tesla by not advertising uh we are doing some advertising so yeah I'll say something uh you know our fundamental belief is that we need to be providing the best products at a reasonable price to the consumers just to give you a fact in us alone in Q2 or two-thirds of our sales were to deliveries were to people who had never owned a Tesla before and which is encouraging we've spent money on advertising and other awareness programs and we have adjusted our strategy we're not saying no to advertising but this is a dynamic play and we know that we have not exhausted all our options and therefore plan to keep adjusting for in the later half of this year as well great thank you very much uh the next question is on energy growth which we already covered in opening remarks so we'll move on to the next one uh what is the updated timeline for Giga Mexico and what will be the primary Vehicles produced initially well we we we currently are pause on gig Mexico um I think we need to see just where things stand after the election um Trum Trump has said that uh he will put heavy tariffs on vehicles produced in Mexico so it doesn't make sense to um invest a lot in Mexico uh if that is going to be the case so we we kind of need to see where things play out politically um however we are increasing capacity at our existing factories quite significantly and I should say that the the Cyber taxi robber taxi will be will be produced um here at our headquarters at G Texas all right thank you as well and as will Optimus um uh towards the end of next year for Optimus production version to the high volume version of Optimus will also be produced here in Texas great thank you just a couple more um is Tesla still in talks with an oem to license epsd uh there are a few major oems that have expressed interest in licensing Tesla or Tesla full stop driving and I suspect there will be more over time um but we can't comment on the details of those discussions all right thank you and the last one um any updates on investing in xai and integrating Gro into Tesla software should said Tesla is loaring quite a bit from xai it's been actually helpful in advancing full self driving um and in building up the the new Tesla data center uh with regarding investing in X I think we need to have a shareholder approval of any such investment um uh but I'm I'm certainly supportive of that if shareholders are but we probably I think we need to vote on that and um there I think that there are opportunities to integrate Gro into Tesla software yes all right thank you very much and now we will move on to analyst questions uh the first question comes from will Stein from truest uh will please go ahead and unmute yourself great thanks so much for taking my question and this relates a little bit to the last one that was asked uh Elon I share your uh strong enthusiasm about Ai and and I recognize Tesla's opportunity to do some great things with the technology but um there are some concerns I have about Tesla's commercialization and and that's what I'd like to ask about specifically there were some new stories through the quarter that indicated that you redirected some AI compute systems that were destined for Tesla instead to uh xai or perhap perhaps it was to X I'm not sure and similarly a few quarters ago if you recall I asked about your ability to hire engineers in this area and you noted that um there there was a great desire uh for for some of these Engineers to work on projects that you were involved with but some of them weren't at Tesla they were Instead at xai or perhaps even X again so the question is when it comes to your capital Investments your AI R&D your AI Engineers how do you make allocation decisions among these various Ventures and how do you make Tesla owners comfortable that you're doing it in a way that really benefits them thank you yeah I mean I think you're referring to a very like an old article um regarding uh gpus uh um I think that's like six six or seven months old uh Tesla said we have had no place to turn them on so it would have been a waste of Tesla Capital because we would just have to order h100s and have no place to um turn them on so it was just there was this this wasn't a let's pick X XII of a of a Tesla there there was no the Tesla data centers were full there was no no place to actually put them um the we we're we've been working 24 7 to complete the South Extension on the Tesla big Factory here in Texas that South South Extension is what will house the 50,000 h100s um and we're um we're beginning to move the h100 server ax uh into place there but uh we really needed we needed that to be complete physically you can't just you know order Compu order gpus and turn them on with no you need a data start it's not possible so I want to be clear that was um in Tesla's interest not contrary to Tesla's interest does Tesla no does Tesla no good to have use that account turn on um the Split Second the that South Extension is able to take gpus uh which is really just this week um we are moving gpus in there and we'll bring them online um with regard to to uh X the um there there are people that that only want to work on AGI um so what I was Finding was that when trying to people to to Tesla they they they were they were only interested in working on AI not not t specific problems um and uh and they want to start a do a startup um so it was case of either they go to a startup or uh and I'm involved or they do a startup and I'm not involved those are the two choices um this wasn't uh oh they were they would come to Tesla they were not going to come to Tesla under any circumstances um so um yeah yeah I mean I would even add that you know AI is a broad spectrum and there are a lot of things which you know we are focused on full cell driving as Tesla and also Optimus but there's the other spectrum of AI which we're not working on and that's the kind of work which other other companies are trying to do in this case xai so you have to keep that in in mind that it's a broad spectrum it's not just one specific thing yeah and once again I want me just repeat myself here I tried to recruit them to Tesla uh including to say like you can work on AGI if you want and they refused only then was X cre I I really appreciate that clarification if I can ask one followup it relates to uh the new uh vehicles that you're planning to introduce next year I understand this is not the venue for uh product announcements but when we think about the focus I've heard on the one hand that the f focus is on cost reduction on the other hand you also said that the Roadster would uh would come out should we expect other maybe more limited variants like um similar to the cars that you make today but with you know some changes or improvements or different um some other variability in the form factors it should we expect that to be a significant part of the strategy in the next year or two I I don't want to get into the details of product announcements um and um and we have to be careful of the Osborne effect here so you know if you start announcing some great thing it affects our near-term sales um we're we're going to um make great products of future just like we have in the past and a story great um the next question comes from Ben callow from be uh Ben please go ahead and unmute yourself hi uh thanks for taking my question uh when we think about Revenue contribution and with energy growing so quickly and you know optimists on the come how do we think about you know the overall segments longer term and then do you think that auto Revenue will fall below 50% of your overall revenue and then my follow up is just on the last call you talked about uh Distributing compute on your new hardware could you just update us and talk a little bit more about that the timeline for it and you know how you would reward uh customers for letting you use their their compute power in their cars thanks yeah I mean as I've said a few times I think the long-term value of Optimus will exceed that of everything else Tesla combined so um it's simply You're Something consider the usefulness utility of a humanoid robot uh that can do pretty much anything you ask of it um I think everyone on Earth is going to want one there 8 billion people on Earth so that's 8 billion right there then you've got uh all of the industrial uses which is probably at least as much if not way more so I suspect that the long-term demand for general purpose humanoid robots is an excess of 20 billion units um and Tesla is has the most advanced human robot in the world uh and is also very good at manufacturing which these other companies are not and we've got a lot of experience with the most experience with with the world leaders in real world a so we have all of the ingredients we I think we're unique in having all of the ingredients necessary for large scale High utility generally humanoid robots um that's why you know my rough estimate longterm is in accordance with the AR invest analysis of You Know M cap of on the order of 5 trillion for maybe more for aous transport um and it's several times that number for general purpose humanoid robots I mean that point I'm not sure what money even means um but uh you know in the benign AI scenario we are headed for an age of abundance where there is no shortage of goods and services every anyone can have pretty much anything they want it's a it's a wild very wild future we're heading for on the distributed compute yeah distributed compute um that seems like a pretty things to do um I I think the where the distributed compute becomes interesting is with our next Generation Tesla AI CH which is Hard 5 what we're calling ai5 which is um from from the standpoint of inference stability uh compartible to a b200 an ided v200 um and we're able to have that uh in production at the end of next year and scale production in 26 um so it just just seem like if you've got even if you've got autonomous vehicles that are operating for 50 or 60 hours a week there 168 hours in a week so you have somewhere above uh I think 100 uh uh uh neural net Computing I I think we we need a better word than GPU because GPU means graphing in unit so there's a 100 hours plus per week of AI compute AI inance compute from the fleet from the vehicles and probably some percentage from the humanid robots that it would make sense to do distributed inance and if you there's a fleet of you at some point 100 million vehicles with ai5 and Beyond you have ai6 and 7 and whatnot um and there may be billions of humanoid robots that is just a staging amount of of inferus Compu or that that could be used for general purpose Computing it doesn't have to be used for the hum drove a for the car so I think you that just that that's that's a pretty obvious thing to say like well it's more useful than having to do nothing um all right thank you uh the next question comes from Alex Potter from Piper uh Alex please go ahead and unmute yourself perfect thanks um I wanted to ask a question on FSD licensing you mentioned that in passing previously was just wondering if you can elaborate maybe on the mechanics of how that would work um I guess presumably this would not be some sort of simple plug-and playay proposition presumably an oem would need I don't know several years to develop its own vehicle platform that's based on FSD I I I imagine they would need to adopt Tesla's electrical architecture compute uh sensor stack so I correct me if I'm sort of misunderstanding this but if you had a Cooperative agreement of some kind with another omm then presumably it would take you several years before you'd be able to recognize licensing revenue from that agreement is that the right way to think about that U yes the not move fast um there's not really a sensor Suite it's just cameras uh but uh they would have to integrate our AI computer and have cameras with with a 360 degree view and um at least the Gateway like the what what talks to the internet and communicates with the Tesla system what that you need kind of a Gateway computer too so it's really Gateway computer with the cellular and Wi-Fi connectivity the Tesla AI computer and seven cameras or enough cameras to get a 360 Dee view but this will give given the speed at which uh the Auto industry moves it would be several years before this you see this volume okay good that's that's more or less what I expected so then the followup here is if you did sign an FSD licensing agreement with another automaker when do you think you would disclose that would you do it right when you sign the agreement or only after that multiple years has passed and the vehicle is ready to be rolled out I think it depends on on me you I guess would be happy either way um yeah it depends on you know what kind of arrangement we enter into a lot of those things are we've not ired those out yet so we'll make that determination as and when we get to that point right and the kind of deals that that are obviously relevant are only if you know some omem is willing to do this in a million cars a year or something significant it's not if it's like 10,000 or 100,000 cars a year we could just make that ourselves all right thank you uh the next question comes from Dan Levi from parlays uh Dan please go ahead and unmute yourself I good evening thanks for taking the questions first wanted to start with a question on Shanghai you've leveraged Shanghai as a as an export Center really due to its low cost that makes sense um maybe you can just give us a sense of how the strategy changes if at all given uh the implementation of tariffs in Europe also to what extent uh your uh import of batteries from China into the how that might uh change given the tariffs thank you yeah I think uh I covered some part of it in my opening remarks but just to give you a little bit more just on the Tariff side the European authorities did sample certain other oems in the first round to establish the tariffs for cars being imported from China into Europe while we were not picked up in our individual examination in the first round they did pick us up in the second round they they visited our Factory we worked with them provided them all the information you know as a result we we are adjusting our import strategy out of China into Europe but and you know one other thing to note is in Q2 itself we started building rightand model wise out of Berlin and we also delivered it in UK and you know we're adjusting as needed but you know we will keep adjust we're still importing model 3es into Europe out of shinan and you know we are still evaluating what is the best alternate to M manage all this just on the examination by the European authorities like I said we cooperated with them well we are confident that they we should get a better rate than what what they have imposed for now but this is literally evolving and we are adjusting as fast as we can with this it is I would also add that you know because of this you've seen the impact that Berlin is doing more Imports into places like Taiwan as well as you know UK I just mentioned so it will keep changing and we will keep adapting as we go about it thanks yeah thank you um as as a follow up wanted to ask uh about uh the the rotac the strategy and specifically the the shareholder deck here notes that the release is going to be one of the gating factors is regulatory approval so maybe you could help us understand um you know which regulations specifically are the ones that we should be looking for is it fmvss that's uh standard and then you know to what extent does the strategy shift you've done with FSD more of a a nationwide uh no boundary approach is the robotaxi approach one that's more geofence so to speak and is more driven by uh a state byst state approach I mean a solution is a generalized solution un like what everybody else has if you see like weo and whatnot they they have a very localized solution that requires high density mapping it's not it's quite fragile um so you know that their ability to expand rapidly is is limited um you know our solution is a is a general solution that works anywhere it would even work on a different Earth so if you rendered A New Earth it would work on a new Earth um so it's there's there's capability I think in in our experience once we demonstrate that something is safe enough or significantly safer than human uh we find that Regulators are supportive of deploy deployment of that capability um it's difficult to argue with if if you got um a large number of you if you got billions of miles that show that um in the future unsupervised FSD is safer than human what what regulator could really stand in the way of that um they would they're morally obligated to approve so I don't think regulatory approval will be um a limiting factor um I should also say that you know the the self-driving capabilities of that um are deployed outside of North America are far behind that in in North America so with the with version 12.5 um and maybe it's 12.6 but but pretty soon um we will ask for regular regulatory approval of the uh Tesla supervised FSD in uh Europe China and other countries and I I think we're likely to receive that uh before the end of the year thank you which which there will be a helpful demand driver in those regions thank you just just that Tris in ter in terms of like you know as Elon said in terms of regulatory approval you know the vehicles are governed by fbss in the US which is nit which is the same across all 50 states the world rules are the same across all 50 states so creating a generalized solution gives us the best opportunity to deploy in all 50 states reasonably of course there are State and even local you know Municipal level regulations that may apply to you know being a transportation company or deploying taxis but you know as far as getting the vehicle on the road that's that's all federal and that's very much in line with what you know was just suggesting about the data and the vehicle itself and and to add to the technology point the N2 and network basically makes no assumption about the location um like you could add data from different countries and just like perform equally well there uh there's like almost like close to zero us specific um code in there it's all just the data that comes from us yeah to to that end the sh it's like you know we can go as humans to other countries and drive with some reasonable amount of assessment in those countries and and that's how you design the FSC software yeah exactly great thanks guys uh the next question comes from George from Kord George please go ahead and unmute yourself hi everyone uh thank you for taking my questions uh maybe just to expand on the regulatory question for a second and I I could be comparing apples and oranges but you know GM cancelled their pedalless wheeless vehicle and according to the company this morning their decision was driven by uncertainty about the regulatory environment um and from what we understand and again maybe I'm wrong here but the robo taxi that been you know shown at least in images of the public is also pedalist and wheeless is there a different regulatory concern just if you deploy a vehicle like that that doesn't have a pedal pedals or a wheel and that may that be different from uh just regular FSD on a traditional Tesla vehicle thank you well obviously the real reason that they canel it is because JM can't make it work not because The Regulators they blaming Regulators um that's that's misleading to do so um because weo is doing just fine in those markets so it's it's just that their technology is not up far right um and maybe just as a followup I think you mentioned that FSD take rates were up materially after you reduced the price is there any way you can help us quantify what that means exactly thank you yeah I mean you know we've shared the that how that there we've seen a meaningful increase I don't want to get into specific because we started from a low base and but we we are seeing encouraging results and and the key thing here is like Elon said you need to experience it because words can't describe it till the time we actually use it and that's why we are trying to make sure that every time a car is getting delivered people are being showed how this thing is working because when you see it working you realize how great it is I mean just to give you one example so again there's a bu example but I have a more than 20 M commute into the factory almost every day I have zero interventions on the latest St and the car just literally drives me over and especially with the latest version wherein you know we're also tracking your ey movement the steering wheel nag is almost not there as long as you're not ring some well we're fixing the sunglasses thing it's coming soon so you will be able to drive it will you will be able to have sunglasses on and have the car drive yeah um so um but you know there sure number of times I've talked with smart people who uh like live in New York or maybe downtown Boston and um don't ever drive um and then are asking me about FSD I'm like you can just get a car and try it um and uh if if you're if you're not doing that you have no idea what's going on thank you um the next question comes from Pierre from New Street Pierre please unmute yourself hey guys thank you for taking my question um so it's on on Robo taxi um again and I completely get it that with a universal solution we will get like regulatory approval we get there eventually clicking clicking up miles and compute Etc and my question is more um how you think about deployment because I'm still like I'm thinking once you have a car that can drive everywhere that can replace me um it can replace um a taxi but then to do the ride hailing service you need a certain scale uh and that means a lot of cars on the road and so you need an infrastructure to to just maintain the cars take care of them Etc and so my question is are you already working on that do you have already an idea of what like your plan to deploy looks like and is that like a t Tesla only plan or are you looking at Partners local Partners Global Partners um to do that and I'll have a quick phot no this this would just be the Tesla Network you just literally open the Tesla app and summon a car and and we send a car to pick you up and take you somewhere um and the you can our we'll have a fleet that's I on order of 7 million that are capable of autonomy soon um you know years to come it'll be over 10 million and over 20 million uh this this is immense scale um and and the car is able to operate 247 unlike the human driver so uh the capability to like there's this basically instant scale with a software update um and now this is for a customer on fleet um so you can think of that as being a bit like Airbnb like um you know you you can choose to allow your car to be used by the fleet or you know cancel that and bring it back you can be used by the fleet all the time uh used by the fleet some of the time and then Tesla would take would share on the revenue with the customer but you can think of the giant Fleet of Tesla vehicles as like a giant sort of Airbnb equivalent Fleet Airbnb on Wheels um I mean then you know in addition we would make uh some number of cars for Tesla that that would just be owned by Tesla and be added the fleet I guess that would be a bit more like uber um but this this would all be a Tesla Network um and and there's an important close we've put in in every Tesla purchase which is that the Tesla vehicles can only be used in the Tesla Fleet they cannot be used by a third party for aony okay and and do you think that scales like progressively so you can start in a city with just a handful of cars and you you grow the number of cars over time or do you think there is like a critical mass you need to get to to be able to offer like a service that is of competitive quality compared to what like the like uber would be typically delivering already and I guess I'm not I'm not conveying this cly the entire Tesla Fleet basically becomes active um you know this is obviously maybe there's some number of people who don't want their car to earn money but I think most people will it's instant scale thank you uh our next question comes from Colin from Oppenheimer Colin please unmute yourself sorry about that guys um you know I've got two questions around energy storage you know with the the tight Supply on the stationary storage can you talk about your pricing strategy and how you're thinking about saturation and given geographies given that you know some of these larger systems are starting to shift wholesale power markets in a pretty meanful way quickly so yeah I mean you know we are working with a large set of uh players in the market and you know our pipeline is actually pretty pretty long and there's actually a very there's actually long end in terms of where you into a contract where delivery started starts happening and so far we have good Rising leverage and I'll have Mike chime in on this too yeah I mean there's there's a lot of competition from Chinese oems just like there is in the vehicle space so we're we're in close contact with our customers and making sure that we're remaining competitive in where they're needing to be competitive to to secure contracts to sell power and energy in the markets um we had a really strong contract in quarter and Contin to build our backlog for 2025 and 2026 um so we feel pretty good about where we are in the market we realize that um competition is strong but we have a pretty strong value proposition with you know offering a fully integrated product with our own power electronics and sight level control so yeah and again the aspect which people Miss do not fully understand is that there's also a whole software stack which comes with mega back right and that that is a unique proposition which we have which is only available to us and we're using it with other stuff too but that gives us a much more of an edge as compared to the competition yeah yeah we find customers that they can sort of put together a hodg Podge solution um and and then sometimes they'll pick that solution um and then that that doesn't work um and then they come back to us yeah we're not really seeing saturation like on a global scale there's there's little pockets of saturation in different markets but we're more seeing that there there's markets opening up given Demand on the grid just continues to increase more than anyone expects um so that just opens up markets you know really across the world in different Pockets yeah I mean just just even on the AI computer side right these these uh gpus are really powerful way and the amount of you know new pipeline which we're getting for people for data center back up and things like that is increasing at a pretty large scale yeah thanks and then the follow here the 4680 uh process technology you know and the RO to roll process you know you there's some news around your your equipment suppliers you know can you talk about how far long you were in in potentially qualifying an incremental supplier around some of that those critical uh process technology steps yeah I can I can talk about that um you know as you're probably referring to to the the lawsuit that we have with one of our suppliers look I don't think this is going to affect our ability to to roll out 4680 you know we have very strong IP position in the technology and you know the majority of the equipment that we use is in-house designed and and some of house buil um and so we can we can take our our um IP stack and and have someone else build it if if we if we need to so that's not really a concern right now yeah I think people don't understand just how much demand there will be for grid storage um they really just like the people I think are underestimating this Demand by prob ERS magnitude um so that the actual um energy total energy output of say the US grid is is if if the power plants can operate uh at steady state is at least two to three times uh the amount of energy it currently produces uh because there are a huge gaps there there's a huge difference in the um from Peak to trough in terms of of energy or power generation so uh in order for a grid to not have blackouts it must be able to support the load at the worst minute of the worst day of the year the coldest or hottest day which means that for the rest of the time the rest of the year it's got massive excess um Power Generation capability but it has no way to store that that energy um once you add battery packs you can now run the power plants um at steady state steady state means that you know basically any given grid anywhere in the world can um produce in terms of cumulative energy in the course of a year at least twice what it is currently producing in some cases maybe three times right thank you this is a very profound thing thank you Elon uh the next question comes from Colin Langan from Wells Fargo Colin please unmute yourself oh great um thanks for uh thanks for taking my questions um do you me yeah yeah oh sorry um I guess we G ask you know if if Trump wins there's a higher chance that Ira could get cut I think Elon you had commented online that Tesla doesn't survive on EV subsidies but but when Tesla lose a lot of support if Ira goes away I think model y 3 and Y get Ira help for customers and I think your batteries get production tax credits so so just one can you clarify if the end Ira ends you know would it be a a a negative of your profitability in the near term why might it not be a negative and then you know any framing of the the current you know support you get Ira related um I guess that there would be like some impact but I think it would be devastating for our competitors but and it would slightly um but longterm probably actually helps Tesla would be my guess um yeah um but and I've said this before calls uh it the value of Tesla overwhelmingly is autonomy um these other things are in the noise relative to autonomy so I recommend anyone who doesn't believe that's has a vehicle autonomy should should not hold Tesla stock they should sell at Tesla stock um if you believe Tesla will solve autonomy you should buy Tesla stock and all these other questions are um in the noise yeah I mean I'll this just just to clarify a few things that at the end of the day when we are looking at our business we've always been looking at it whether or not I is there and we want our business to grow grow healthy without having any you know subsidies coming in whichever way you look at it and that's the way we have always modeled everything and that is the way internally also even when we're looking at battery cost yes Ira there are manufacturing credits which we get but we always drive ourselves to say okay what if there's no Ira benefit and how do we operate in that kind of an environment like Elon said we definitely have a big Advantage as compared to a competition on that front we've delivered it and you can see it in the numbers over the years like so that there is you you cannot ignore the fundamental sides of the business and then on top of it once you add autonomy to it like Elon said it becomes meaningless to you and think about the the sh okay um I think that's unfortunately all that we have for today uh we appreciate all of your questions we look forward to talking to you next quarter thank you very much and goodbye [Music] thanks I've this vision
Show less