I agree that Tesla's biggest mistake was doing Cybertruck before the $25k car. But if they solve autonomy and/or succeed with Optimus then everything else becomes irrelevant.
I agree, but these are moonshot announcements that should sit isolated from the core business.
The same thing that Google (ironically) did with X - which led to Waymo, which now already has autonomous taxis[0]
You can't keep perpetually hyping tomorrow when the next Q is due.
I have an affinity for Tesla since it's named after someone from a village my mums family is from (and who I'm named after), and I like environmentalist, decarbonise, and electrify Elon.. but sometimes he makes it hard.
[0] on that note - not only have I seen better taxi demos than today, also seen better robot demos from Boston Dynamics.
The question is how much does a Boston Dynamics robot full of complex hydrolics cost vs a Tesla bot that full of electric actuators. Boston Dynamics robots aren't really design to be produced in numbers and are designed for a different use-case.
Boston Dynamics' humanoid robots thus far have been R&D platforms so the cost isn't all that important. That said, they released a quick teaser for the next gen of Atlas which seems to be all electric.
Yeah Boston Dynamics is way better at locomotion, but their advantage in manipulation is smaller. You also won't see 50 at the same time like Optimus today. Tesla's advantage will be manufacturing.
Optimus has improved quickly. Gen 3 should be better. They showed Gen 3 hands today that looked pretty good.
I don't think Tesla have an advantage in manufacturing. China today is what Japan was in the 70s and their processes are so fucking good.
You can't win on manufacturing - this is, after all, a nation that is now building Volvo's better than the Swedes did.
Tesla fell into the China partnership trap, where the gov subsidises you and you open a "partnership" there, meanwhile they take your IP and knowledge for the benefit of the state (I was in that situation in '07 with Tencent and turned it down).
Hence now $10k Chinese cars - and Biden introducing tariffs to protect local industry (including Tesla - which Elon doesn't seem to appreciate)
On AI at Elon's recent recruitment event he put X.ai in Tier 1 with OpenAI and Anthropic and didn't even mention Meta. To me, as someone who applies these models across industries every day X.ai has never even come up.
That tells me he isn't informed on what Meta are doing (and that is - undercutting the commercial AI industry).
I'm hesitant to think it but there's a ton of hand waving and investor pumping happening here. Which is a shame, because a company with that market cap can do _a lot_ better.
I wasn't impressed by a single thing I saw today. I've seen the same autonomous car demo in a closed environment at my own uni 25+ years ago. I've seen better robots from Boston. I've also seen much better presentations than someone who looked like they are reading the text for the first time.
They have the capital, the mindshare, and the means and they're wasting it.
Tesla's advantage over Boston Dynamics will be manufacturing. Over China, it will have to be innovation and software. China is going to be much harder to beat than Boston Dynamics for sure. But remember that Tesla is no stranger to competing with Chinese companies and they are doing OK vs BYD today and not just in the US, with the bestselling car model in the world and in China. I think the "partnership trap" was more relevant years ago; today China has a lot less need to steal tech, at least in the domain of car manufacturing (note that Tesla is not manufacturing Optimus in China).
It's hardly new news that Elon is an awkward presenter and it isn't relevant to future performance of Tesla. You have to look at the pace of improvement of what Tesla is doing. Among humanoid companies that started in 2021 or later Tesla is the furthest along and improving much faster than the likes of Boston Dynamics. While they are still far behind, they have the time and the funding to catch up.
The Cybercab demo was an amusement park ride (and Elon explicitly billed it as such), however Tesla's FSD is released to the public and can be directly evaluated. While it is not yet near Waymo it is impressively good as of this month and the rate of improvement is very fast now. It just drove me across town for 20 minutes and I didn't have to touch the steering wheel a single time. It was incapable of that on that specific drive just two months ago. And I have the less powerful older variant of the Autopilot computer.
> I agree that Tesla's biggest mistake was doing Cybertruck before the $25k car.
While a $25k EV seems to be what we all want and is almost guaranteed to be a massive hit, there is no evidence such a thing can be done yet without losing money on every sale.
Why isn’t any other car company doing it?
Rivian are losing money on every car sold at 4 times the price.
