Everyone’s missing the point of the Tesla Vision vs. LiDAR Wile E Coyote video
A video came out last week comparing two approaches to autonomous vehicles: cameras and LiDAR. The video was fun, as YouTube videos are wont to be, but the fallout from it has been anything but fun, with pretty much everyone missing the point of the video in the first place.
The video was posted by YouTuber Mark Rober, who typically does science & engineering related stunts. It was essentially a comparison test between Tesla’s camera-only autopilot/FSD system and LiDAR systems, with the LiDAR vehicle running Luminar’s system.
The experiment tested whether the cars could react to seeing a child in the road in six circumstances: standing, running into the road by surprise, fog, rain, bright lights, and standing behind a comical Wile E. Coyote style wall with a picture of a road painted on it.
Clearly, one of these things is not like the others. Five of the tests gave us potentially meaningful results about the world around us, and the sixth was just for fun.
The test results showed the LiDAR doing better overall, primarily due to its better performance in fog and rain. But each vehicle produced impressive results on some of the tests – like the child jumping out in front of the car and the bright lights tests, both of which seemed quite difficult (the latter especially for a vision system).
But even in the rain and fog tests, these were quite biblical levels of rain and fog. For more realistic light fog or lighter rain, the cameras likely would have fared better.
There are a few other downsides of vision-only, such as that it can have trouble looking into lights (though it did well in the bright light test), and Tesla has in the past had a hard time with crossing trucks or overpasses being hard to distinguish from billboards, both of which can be solved with the ranging functions of LiDAR or radar.
So all told, these results track with the technical limitations of cameras when compared to LiDAR. Since cameras are passive and LiDAR is active (sending out laser pulses to reflect off of objects), LiDAR is able to “see through” certain things that cameras can’t.
And this is a debate which EV fans have heard plenty about – it’s the fundamental difference between Tesla’s approach and the approach of just about everyone else. Tesla is going vision-only, but most other companies are using a hybrid approach with some mix of vision, LiDAR, radar, ultrasonics, etc.
Tesla actually did used to have sensors other than vision, as early Tesla cars had radar in addition to cameras. But CEO Elon Musk directed the company to remove radar (over the objection of engineers) because he figures if humans can drive with two eyes and no lasers, cameras should be able to do the same. (He isn’t alone, though – Andrej Karpathy, Tesla’s former head of AI and a well respected person in the field, agrees that vision-only is the right approach).
So the tests showed us that LiDAR has some capability that vision doesn’t, but we already knew that. What are the benefits of vision-only?
First, there are clear advantages on cost and complexity, because you need less sensing equipment. LiDAR has been expensive, though costs are dropping rapidly, so this may be less of a factor going forward.
Also, LiDAR sensors used to be huge spinning rigs attached to vehicles, but now they often take the form of a “taxi bump” that looks a bit like a taxi light on the top of the car, just above the windshield – but this still does restrict the design of a vehicle and a lot of people don’t like the look.
Second, vision-only could potentially make for a simpler software solution because you don’t have to reconcile the input from multiple sensing methods to figure out the reality in front of you.
This is something that held Tesla back in the early days of vision + radar, because there were a lot of false positives and negatives from weird situations (e.g. curved metal objects like soda cans could look bigger than they should, stationary vehicles were hard to distinguish, etc.). While the data was more robust because there were multiple sensing methods, it was proving itself harder to interpret.
And, while it’s not an inherent benefit of vision-only, the specific benefit for Tesla is that the company has a LOT of vision data it can use for training. This is a big advantage that it has over every other company by several orders of magnitude, since millions of Teslas have been driving around collecting data for years now, whereas companies like Waymo only have a few hundred cars.
So, we know a bit about the differences in technology, their strengths and weaknesses, and the long-time industry debate that motivated this test. Nothing seems all that unreasonable about what we’ve heard so far, and the test turned out about as expected. There’s still an open question over what the best path forward is, though the general consensus is that more sensing data is better than less, and that Tesla is making a risky move with its vision-only system.
So, why so much drama?
Okay, well, it’s the internet. So that’s reason number one. Everyone else here is chasing the same thing Rober chases: views. And so that’s probably the only thing we need to say, alright, article over, moving on.
…. But no, really. The actual drama is over the differentiation between “Autopilot” and “Full Self-Driving,” and over the behavior of Teslas when activating or deactivating the system, specifically on the headline “Wile E. Coyote” test.
Most discussion has focused on this particular test, because, well, it’s the most fun one. Rober is one of the most popular YouTubers on the planet, after all, so he should know a thing or two about how to make a compelling video (and the intro sentence of the video is quite a doozy):
As Rober said in the very first line of the video, he had his Tesla on Autopilot, not Full Self-Driving, during this test.
Some criticism has focused on the title of the video, which is “Can You Fool A Self Driving Car?”, suggesting that the test would use Tesla’s “Self-Driving” system.
These are two separate systems, and FSD is more sophisticated than Autopilot. However, Autopilot has long colloquially been referred to as self-driving (often to the chagrin of Tesla defenders), and while Tesla does refer to FSD as “self-driving,” it very much isn’t. Both of the systems are classed as “level 2,” which means the driver is still responsible for the vehicle at all times, even though FSD can be activated in more situations than Autopilot. And many more Teslas have Autopilot than FSD, so it makes sense to test the more common one.
Luminar’s LiDAR can be “self-driving,” insofar as there are level 3+ systems that use Luminar’s sensing technology (such as Mercedes’ DRIVE PILOT).
So the title is not technically incorrect, does use similar colloquialisms in both cases, and is, after all, a youtube video, and we’re all hopefully aware of how YouTube titles need to be crafted to fit Google’s algorithm and hopefully can get beyond the title and into the literal first frame of the video for the more accurate description of what’s happening here.
And we’ve covered a final criticism before, which is a screenshot showing that Rober didn’t have the system active in the video. This is previously-documented as “normal” Autopilot behavior, where the system turns itself off about a second before a definite crash. The screenshots were taken during this second. Rober also responded mentioning that the video used different takes to keep it compelling, and posted the full uncut footage on Twitter.
Another criticism focuses on the subsequent stock surge seen by Luminar (LAZR). The company’s stock went up from 5.05 to 8.35 over the course of the week after the video, a rise of 65%. This has raised some eyebrows, but I expect that the main explanation here is that prior to the video, only pretty dedicated EV/self-driving folks knew about Luminar, and now it’s been exposed to people associated with the most traded stock on the planet for several years running, TSLA. This is naturally going to drive a ton of volume to a small stock (with ~0.03% of TSLA’s market cap).
We’ve also seen others trying to recreate the video, with more success for the Tesla.
But these criticisms focus mainly on the Wile E. Coyote test, which everyone acknowledges is not a realistic situation. That test was for the youtube video – the real meat of it was the other 5 tests that actually could happen in the real world.
And even on those 5 tests, people are getting overexcited about the differences shown. The fog and water were both significantly heavier than what would most often be experienced in real life. In more “real world” weather circumstances, a camera may have worked plenty well enough (assuming the cameras aren’t obscured by water or condensation – which is certainly an issue). And if the inclement weather is as bad as shown in the video – maybe it’s time to stay home (or, uh, head straight to the hurricane evacuation center).
All in all, it felt like a fun test for a YouTube video, which described technology in a simple way to a crowd that hadn’t heard about it, was generally accurate about the strengths and weaknesses of the compared systems, but just overstated a lot of things “for content.”
There’s a discussion to be had there about content requiring more and more extreme stunts these days to be compelling, but the level of the reaction has gone well overboard. But then, that’s to be expected for anything on the internet, especially about Tesla.
And the discussion over which approach is correct will continue – companies like Luminar think that LiDAR is superior, and Tesla thinks cameras are enough. Time will tell who’s right, but most professionals in the field tend to place their bets on the former, rather than the latter.
Charge your electric vehicle at home using rooftop solar panels. Find a reliable and competitively priced solar installer near you on EnergySage, for free. They have pre-vetted installers competing for your business, ensuring high-quality solutions and 20-30% savings. It’s free, with no sales calls until you choose an installer. Compare personalized solar quotes online and receive guidance from unbiased Energy Advisers. Get started here. – ad*
FTC: We use income earning auto affiliate links. More.
Environment
‘Bitcoin Family’ hides crypto codes etched onto metal cards on four continents after recent kidnappings
The Taihuttus on a ski trip to Sierra Nevada in southern Spain. They sold everything they owned in 2017 to bet on bitcoin — and now travel full-time as a family of five.
Didi Taihuttu
A wave of high-profile kidnappings targeting cryptocurrency executives has rattled the industry — and prompted a quiet security revolution among some of its most visible evangelists.
Didi Taihuttu, patriarch of the so-called “Bitcoin Family,” said he overhauled the family’s entire security setup after a string of threats.
The Taihuttus — who sold everything they owned in 2017, from their house to their shoes, to go all-in on bitcoin when it was trading around $900 — have long lived on the outer edge of crypto ideology. They travel full-time with their three daughters and remain entirely unbanked.
Over the past eight months, he said, the family ditched hardware wallets in favor of a hybrid system: Part analog, part digital, with seed phrases encrypted, split, and stored either through blockchain-based encryption services or hidden across four continents.
“We have changed everything,” Taihuttu told CNBC on a call from Phuket, Thailand. “Even if someone held me at gunpoint, I can’t give them more than what’s on my wallet on my phone. And that’s not a lot.”
CNBC first reported on the family’s unconventional storage system in 2022, when Taihuttu described hiding hardware wallets across multiple continents — in places ranging from rental apartments in Europe to self-storage units in South America.
The Taihuttu family dressed up for Halloween in Phuket, Thailand, where they recently moved homes after receiving disturbing messages pinpointing their location from YouTube videos.
Didi Taihuttu
As physical attacks on crypto holders become more frequent, even they are rethinking their exposure.
This week, Moroccan police arrested a 24-year-old suspected of orchestrating a series of brutal kidnappings targeting crypto executives.
One victim, the father of a crypto millionaire, was allegedly held for days in a house south of Paris — and reportedly had a finger severed during the ordeal.
In a separate case earlier this year, a co-founder of French wallet firm Ledger and his wife were abducted from their home in central France in a ransom scheme that also targeted another Ledger executive.
Last month in New York, authorities said, a 28-year-old Italian tourist was kidnapped and tortured for 17 days in a Manhattan apartment by attackers trying to extract his bitcoin password — shocking him with wires, beating him with a gun, and strapping an Apple AirTag around his neck to track his movements.
The common thread: The pursuit of crypto credentials that enable instant, irreversible transfers of virtual assets.
“It is definitely frightening to see a lot of these kidnappings happen,” said JP Richardson, CEO of crypto wallet company Exodus. He urged users to take security into their own hands by choosing self-custody, storing larger sums on hardware wallets, and — for those holding significant assets — exploring multi-signature wallets, a setup typically used by institutions.
Richardson also recommended spreading funds across different wallet types and avoiding large balances in hot wallets to reduce risk without sacrificing flexibility.
That rising sense of vulnerability is fueling a new demand for physical protection with insurance firms now racing to offer kidnap and ransom (K&R) policies tailored to crypto holders.
But Taihuttu isn’t waiting for corporate solutions. He’s opted for complete decentralization — of not just his finances, but his personal risk profile.
As the family prepares to return to Europe from Thailand, safety has become a constant topic of conversation.
“We’ve been talking about it a lot as a family,” Taihuttu said. “My kids read the news, too — especially that story in France, where the daughter of a CEO was almost kidnapped on the street.”
Now, he said, his daughters are asking difficult questions: What if someone tries to kidnap us? What’s the plan?
One of the steel plates the Taihuttu family uses to store part of their bitcoin seed phrase. Didi etched it by hand using a hammer and letter punch — part of a decentralized storage system spread across four continents.
Didi Taihuttu
Though the girls carry only small amounts of crypto in their personal wallets, the family has decided to avoid France entirely.
“We got a little bit famous in a niche market — but that niche is becoming a really big market now,” Taihuttu said. “And I think we’ll see more and more of these robberies. So yeah, we’re definitely going to skip France.”
Even in Thailand, Taihuttu recently stopped posting travel updates and filming at home after receiving disturbing messages from strangers who claimed to have identified his location from YouTube vlogs.
“We stayed in a very beautiful house for six months — then I started getting emails from people who figured out which house it was. They warned me to be careful, told me not to leave my kids alone,” he said. “So we moved. And now we don’t film anything at all.”
“It’s a strange world at the moment,” he said. “So we’re taking our own precautions — and when it comes to wallets, we’re now completely hardware wallet-less. We don’t use any hardware wallets anymore.”
To throw off would-be attackers, Didi Taihuttu encrypts select words from each 24-word seed phrase — then splits the phrases into four sets of six and hides them around the world.
Didi Taihuttu
The family’s new system involves splitting a single 24-word bitcoin seed phrase — the cryptographic key that unlocks access to their crypto holdings — into four sets of six words, each stored in a different geographic location. Some are kept digitally through blockchain-based encryption platforms, while others are etched by hand into fireproof steel plates using a hammer and letter punch, then hidden in physical locations across four continents.
“Even if someone finds 18 of the 24 words, they can’t do anything,” Taihuttu explained.
On top of that, he’s added a layer of personal encryption, swapping out select words to throw off would-be attackers. The method is simple, but effective.
“You only need to remember which ones you changed,” he said.
Part of the reason for ditching hardware wallets, Taihuttu said, was a growing mistrust of third-party devices. Concerns about backdoors and remote access features — including a controversial update by Ledger in 2023 — prompted the family to abandon physical hardware altogether in favor of encrypted paper and steel backups.
While the family still holds some crypto in “hot” wallets — for daily spending or to run their algorithmic trading strategy — those funds are protected by multi-signature approvals, which require multiple parties to sign off before a transaction can be executed.
The Taihuttus use Safe — formerly Gnosis Safe — for ether and other altcoins, and similarly layered setups for bitcoin stored on centralized platforms like Bybit.
Didi Taihuttu during a recent visit to Sierra Nevada, Spain. The family’s lifestyle — unbanked, nomadic, and all-in on bitcoin — makes them outliers even in the crypto world.
Didi Taihuttu
About 65% of the family’s crypto is locked in cold storage across four continents — a decentralized system Taihuttu prefers to centralized vaults like the Swiss Alps bunker used by Coinbase-owned Xapo. Those facilities may offer physical protection and inheritance services, but Taihuttu said they require too much trust.
“What happens if one of those companies goes bankrupt? Will I still have access?” he said. “You’re putting your capital back in someone else’s hands.”
Instead, Taihuttu holds his own keys — hidden across the globe. He can top up the wallets remotely with new deposits, but accessing them would require at least one international trip, depending on which fragments of the seed phrase are needed. The funds, he added, are intended as a long-term pension to be accessed only if bitcoin hits $1 million — a milestone he’s targeting for 2033.
The shift toward multiparty protections extends beyond just multi-signature. Multi-party computation, or MPC, is gaining traction as a more advanced security model.
Didi, Romaine, and their three daughters live largely off-grid, managing crypto through decentralized exchanges, algorithmic trading bots, and a globally distributed cold storage system.
Didi Taihuttu
Instead of storing private keys in one place — a vulnerability known as a “single point of compromise” — MPC splits a key into encrypted shares distributed across multiple parties. Transactions can only go through when a threshold number of those parties approve, sharply reducing the risk of theft or unauthorized access.
Multi-signature wallets require several parties to approve a transaction. MPC takes that further by cryptographically splitting the private key itself, ensuring that no single individual ever holds the full key — not even their own complete share.
The shift comes amid renewed scrutiny of centralized crypto platforms like Coinbase, which recently disclosed a data breach affecting tens of thousands of customers.
Taihuttu, for his part, says 80% of his trading now happens on decentralized exchanges like Apex — a peer-to-peer platform that allows users to set buy and sell orders without relinquishing custody of their funds, marking a return to crypto’s original ethos.
While he declined to reveal his total holdings, Taihuttu did share his goal for the current bull cycle: a $100 million net worth, with 60% still held in bitcoin. The rest is a mix of ether, layer-1 tokens like solana, link, sui, and a growing number of AI and education-focused startups — including his own platform offering blockchain and life-skills courses for kids.
Lately, he’s also considering stepping back from the spotlight.
“It’s really my passion to create content. It’s really what I love to do every day,” he said. “But if it’s not safe anymore for my daughters … I really need to think about them.”
WATCH: ‘Bitcoin Family’ tracks moon cycles to make crypto investment decisions
Tesla’s head of Optimus humanoid robot, Milan Kovac, announced that he is leaving the automaker after 9 years.
It leaves just as CEO Elon Musk claimed that the humanoid robot is going to make Tesla a”$25 trillion company.”
Electrek first reported on Tesla hiring Kovac back in 2016 to work on the early Autopilot program. At the time, we noted that the young engineer had an interesting background in machine learning.
He quickly rose through the ranks and ended up leading Autopilot software engineering from 2019 to 2022.
In 2022, he started working on Tesla’s Optimus humanoid robot program.
Late last year, he was promoted to Vice President in charge of the complete Optimus program, as CEO Elon Musk began to tout the program as critical to Tesla’s future.
Musk claimed that Optimus could generate $10 trillion in revenue per year and make Tesla a $25 trillion company. These claims are largely unsubstantiated as the humanoid robot market is still in its infancy.
Most market research firms currently estimate the size of the humanoid robot market to be in the low single-digit billions of dollars, with growth projections through 2032 ranging from $15 billion to $80 billion.
That would represent impressive growth, but nowhere near what Musk is touting to investors.
Today, Kovac announced that he is leaving Tesla for personal reasons:
This week, I’ve had to make the most difficult decision of my life and will be moving out of my position. I’ve been far away from home for too long, and will need to spend more time with family abroad. I want to make it clear that this is the only reason, and has absolutely nothing to do with anything else. My support for Elon Musk and the team is ironclad – Tesla team forever.
Kovac has been regarded as one of the top new technical executives at Tesla, which has seen a significant talent exodus of top engineers.
The company has made progress with the Optimus program over the last year. Still, many have been skeptical, as Tesla has been less than forthcoming about using teleoperation in previous demonstrations.
Kovac is not the only Optimus engineer to leave Tesla recently.
Figure, another company developing humanoid robots, has recently poached Zackary Bernholtz, a 7-year veteran at Tesla and most recently a Staff Technical Program Manager.
Electrek’s Take
This is a significant loss for Tesla. Kovac was one of Musk’s top technical guys and literally the head of the program he claimed would bring Tesla to the next level – although I think most people have been understandably skeptical about these claims.
I’ve been bullish on humanoid robots, and I could see Tesla being a player in the field, but it’s nowhere near the opportunity that Musk is claiming, and there’s also plenty of competition with no clear evidence that Tesla has any significant lead, if any.
In China, Unitree has been making impressive progress, and it is already selling a humanoid robot.
In the US, Figure has also been making a lot of progress lately:
I think it’s a smart space to invest in for manufacturing companies like Tesla, but there’s going to be a lot of competition.
It’s too early to say who will come out on top.
As for Kovac leaving, I’m sure his personal reason is correct. However, we often see people claim that and then they quickly turn up at another company.
If he believed that his product would soon become a multi-trillion-dollar opportunity, I doubt he would be leaving, but you never know. 9 years at Tesla is some hard work and it’s impressive for anyone. Congrats.
FTC: We use income earning auto affiliate links. More.
-
Sports3 years ago‘Storybook stuff’: Inside the night Bryce Harper sent the Phillies to the World Series
-
Sports1 year agoStory injured on diving stop, exits Red Sox game
-
Sports2 years agoGame 1 of WS least-watched in recorded history
-
Sports2 years agoMLB Rank 2023: Ranking baseball’s top 100 players
-
Sports4 years ago
Team Europe easily wins 4th straight Laver Cup
-
Environment2 years agoJapan and South Korea have a lot at stake in a free and open South China Sea
-
Environment2 years agoGame-changing Lectric XPedition launched as affordable electric cargo bike
-
Business3 years agoBank of England’s extraordinary response to government policy is almost unthinkable | Ed Conway