正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

FSD V14: Nighttime Emergency Avoidance Challenge pt4: What happens when pure-vision FSD V14 encounters a completely transparent object at night? At 40 mph, FSD V14 was able to come to a complete stop before impact. At 45 mph, it significantly reduced speed but was unable to stop completely before... show more

BigHu-L5

2,236 subscribers

11,264 次观看 • 1 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

How fast is FSD V14, really? Can it dodge a tire flying toward the vehicle at highway speeds? Can it safely reverse around a flock of sheep? Can it navigate a narrow cliffside road above the clouds? This compilation contains some of the most extreme real-world scenarios you may have never seen before. FSD V14 continues to push the boundaries of autonomous driving. Its capabilities may exceed your imagination. More professional extreme tests coming soon! #FSD Ashok Elluswamy Elon Musk Sawyer Merritt Whole Mars Catalog Edge Case TSLA99T

How fast is FSD V14, really? Can it dodge a tire flying toward the vehicle at highway speeds? Can it safely reverse around a flock of sheep? Can it navigate a narrow cliffside road above the clouds? This compilation contains some of the most extreme real-world scenarios you may have never seen before. FSD V14 continues to push the boundaries of autonomous driving. Its capabilities may exceed your imagination. More professional extreme tests coming soon! #FSD Ashok Elluswamy Elon Musk Sawyer Merritt Whole Mars Catalog Edge Case TSLA99T

BigHu-L5

53,798 次观看 • 1 个月前

They said Elon Musk should watch this because this might be the first time he notice FSD V14 can even do this. The car in the video is a rear-wheel-drive Model Y. The mountain road was extremely slippery after the rain, and this road is usually almost unused, so the ground was covered with moss. Even when FSD V14 encountered a situation where the drive wheels completely lost traction, it still kept trying and did not give up.

They said Elon Musk should watch this because this might be the first time he notice FSD V14 can even do this. The car in the video is a rear-wheel-drive Model Y. The mountain road was extremely slippery after the rain, and this road is usually almost unused, so the ground was covered with moss. Even when FSD V14 encountered a situation where the drive wheels completely lost traction, it still kept trying and did not give up.

JacksonS

21,963 次观看 • 2 个月前

Tesla FSD V14 Lite in my Tesla Model Y with AI3 parking at a Supercharger. I'm am blown away by the performance of V14 Lite compared to V12.6. It's night and day.

Tesla FSD V14 Lite in my Tesla Model Y with AI3 parking at a Supercharger. I'm am blown away by the performance of V14 Lite compared to V12.6. It's night and day.

Nic Cruz Patane

69,969 次观看 • 17 天前

Check out FSD V14 handling one of the stupidest, most dangerous on-ramps you'll ever see. A complete stop before you then need to immediately proceed up to highway speeds. The "pre-roll" is really good here.

Check out FSD V14 handling one of the stupidest, most dangerous on-ramps you'll ever see. A complete stop before you then need to immediately proceed up to highway speeds. The "pre-roll" is really good here.

Dirty Tesla

40,269 次观看 • 5 个月前

Sprinkle of Cybertruck FSD mishaps. FSD v14.2.1. FSD was getting ready to make a left turn. In fairness, I pushed the pedal as there still was time to make the turn before the oncoming car. However, I took the foot off and the truck came to a stop. Then when the turn was almost complete, FSD threw the red hands and the message said "Aborted with a system error." If you are wondering why I looked at the camera in between, I wanted to make sure it was recording the situation. I have hours of video footage I recorded while driving on FSD 14.2 and 14.2.1.

Sprinkle of Cybertruck FSD mishaps. FSD v14.2.1. FSD was getting ready to make a left turn. In fairness, I pushed the pedal as there still was time to make the turn before the oncoming car. However, I took the foot off and the truck came to a stop. Then when the turn was almost complete, FSD threw the red hands and the message said "Aborted with a system error." If you are wondering why I looked at the camera in between, I wanted to make sure it was recording the situation. I have hours of video footage I recorded while driving on FSD 14.2 and 14.2.1.

Andy ze German

14,174 次观看 • 7 个月前

I was leaving a parking lot and witnessed this. 🤔 The car in front of me stops at the line, and FSD of course stops behind them. But when the person in front me goes, FSD doesn't come to a full stop again. Is this a rolling stop or the system didn't know to stop again?

I was leaving a parking lot and witnessed this. 🤔 The car in front of me stops at the line, and FSD of course stops behind them. But when the person in front me goes, FSD doesn't come to a full stop again. Is this a rolling stop or the system didn't know to stop again?

Martha 🌑🚀

16,721 次观看 • 5 个月前

I’m really looking forward to these upcoming Tesla FSD updates: • FSD V14 “Lite” for HW3 owners: Can’t wait to try it, even as a daily HW4 user. It’s expected to release at the end of this month and include the same features as HW4 V14. • Pothole Avoidance: This will be very welcome, especially for Teslas with lower-profile tires. It will be a game changer for me. • FSD Remembering Your Parking Preferences: Elon Musk says future FSD releases will remember your parking preferences when arriving at a destination. Great for garages, work spots, etc. • Grok Voice Commands for FSD: Elon Musk says the ability to prompt FSD with language is coming within ~3 months. You’ll be able to use your voice to tell the car what to do or where to go. This will be incredibly cool. CANT WAIT.

Nic Cruz Patane

60,146 次观看 • 29 天前

The crash analysis below shows AI3 FSD v12.6.4 biggest safety weakness: late reaction. This video uses official dashcam crash footage synchronized with the vehicle’s official telemetry logs obtained from Tesla and visualized in CamCutApp. The telemetry shows FSD waiting about 0.67 seconds after the lead vehicle’s brake lights illuminate before it begins braking. From the moment the lead vehicle starts braking until Automatic Emergency Braking intervenes is about 1.5 seconds. During that time, the Tesla slows by only 4 mph, from 62 mph to 58 mph. By the time AEB takes over, only 132 feet remain before impact. There simply isn’t enough distance left to avoid the collision. Millions of AI3 vehicles are still running FSD v12.x. Situations like this require the driver to intervene before it becomes obvious that FSD isn’t braking quickly and aggressively enough, and that’s not always easy to judge in real time. Tesla today announced AI3 v14 Lite which includes “significantly improved safety.” When I get a chance to evaluate v14 Lite, this is exactly what I’ll be testing first. In my opinion, it’s the most important and critical improvement the system needs.

The crash analysis below shows AI3 FSD v12.6.4 biggest safety weakness: late reaction. This video uses official dashcam crash footage synchronized with the vehicle’s official telemetry logs obtained from Tesla and visualized in CamCutApp. The telemetry shows FSD waiting about 0.67 seconds after the lead vehicle’s brake lights illuminate before it begins braking. From the moment the lead vehicle starts braking until Automatic Emergency Braking intervenes is about 1.5 seconds. During that time, the Tesla slows by only 4 mph, from 62 mph to 58 mph. By the time AEB takes over, only 132 feet remain before impact. There simply isn’t enough distance left to avoid the collision. Millions of AI3 vehicles are still running FSD v12.x. Situations like this require the driver to intervene before it becomes obvious that FSD isn’t braking quickly and aggressively enough, and that’s not always easy to judge in real time. Tesla today announced AI3 v14 Lite which includes “significantly improved safety.” When I get a chance to evaluate v14 Lite, this is exactly what I’ll be testing first. In my opinion, it’s the most important and critical improvement the system needs.

Edge Case

140,091 次观看 • 18 天前

FSD V14.1.7 Takes me downtown to see a show with the push of a button. It's absolutely incredible what a Tesla is capable of on V14. This is a ~50 minute drive and it ends in an underground parking garage and it was 100% handled by FSD, all I did was press a button.

FSD V14.1.7 Takes me downtown to see a show with the push of a button. It's absolutely incredible what a Tesla is capable of on V14. This is a ~50 minute drive and it ends in an underground parking garage and it was 100% handled by FSD, all I did was press a button.

Devin Olsen

87,672 次观看 • 8 个月前

Chinese influencer Da Hu flew to Korea to test FSD v14, since it’s not yet available in China. He shared this clip showing FSD navigating a narrow country road and stopping at a T-intersection where the view to the left was blocked by a parked truck. FSD patiently waited until the second approaching vehicle completed its right turn and the road was fully clear before making a left turn. Even more impressively, before reaching the intersection, FSD had already detected the two vehicles from a distance and appeared to anticipate whether they would turn right or continue straight—even though, from the point where the Tesla stopped, those vehicles temporarily disappeared from view behind the truck. The system handled the scenario exceptionally well, showcasing strong real-world inference and prediction capabilities that left the influencer highly impressed.

Chinese influencer Da Hu flew to Korea to test FSD v14, since it’s not yet available in China. He shared this clip showing FSD navigating a narrow country road and stopping at a T-intersection where the view to the left was blocked by a parked truck. FSD patiently waited until the second approaching vehicle completed its right turn and the road was fully clear before making a left turn. Even more impressively, before reaching the intersection, FSD had already detected the two vehicles from a distance and appeared to anticipate whether they would turn right or continue straight—even though, from the point where the Tesla stopped, those vehicles temporarily disappeared from view behind the truck. The system handled the scenario exceptionally well, showcasing strong real-world inference and prediction capabilities that left the influencer highly impressed.

Ray

47,872 次观看 • 2 个月前

Another user Carnasis submitted this crash footage of his Tesla being T-boned while FSD was engaged. Raw video analyzed using CamCutApp telemetry visualization. The other driver was ultimately found at fault after entering the roadway and colliding with the Tesla while FSD v14.2.2.5 was engaged. What makes this crash interesting is that there appear to be multiple contributing factors: • The driver was pressing the accelerator before the collision, causing the vehicle to accelerate to roughly 40 mph. Had the throttle not been overridden, FSD may have approached the area at a lower speed. • A portion of the striking vehicle was visible between the stopped cars before it fully emerged into the roadway. FSD did not react until the vehicle entered its path, leaving only a few hundred milliseconds to respond. By the time emergency braking began, there simply wasn’t enough distance left to avoid the collision. The other driver caused the crash, but it’s an interesting example of how throttle overrides, speed, and anticipation of partially occluded vehicles can all influence the outcome. Tesla AI

Another user Carnasis submitted this crash footage of his Tesla being T-boned while FSD was engaged. Raw video analyzed using CamCutApp telemetry visualization. The other driver was ultimately found at fault after entering the roadway and colliding with the Tesla while FSD v14.2.2.5 was engaged. What makes this crash interesting is that there appear to be multiple contributing factors: • The driver was pressing the accelerator before the collision, causing the vehicle to accelerate to roughly 40 mph. Had the throttle not been overridden, FSD may have approached the area at a lower speed. • A portion of the striking vehicle was visible between the stopped cars before it fully emerged into the roadway. FSD did not react until the vehicle entered its path, leaving only a few hundred milliseconds to respond. By the time emergency braking began, there simply wasn’t enough distance left to avoid the collision. The other driver caused the crash, but it’s an interesting example of how throttle overrides, speed, and anticipation of partially occluded vehicles can all influence the outcome. Tesla AI

Edge Case

62,489 次观看 • 1 个月前

Have you ever played a parkour game? FSD is now pulling off a perfect run through one of the hardest parkour levels imaginable — in the real world. To those who still doubt Tesla's vision-only approach: it's time to stop. FSD V14 glides smoothly along an ultra-narrow mountain road in dense fog, handling conditions that would make most human drivers nervous. In Mad Max mode, it maintains impressive speed while effortlessly avoiding rocks and debris scattered across the road from landslides hidden in the fog. This isn't a simulation. This is reality. 🚗💨🌫️🏔️ Ashok Elluswamy Whole Mars Catalog Edge Case Tesla AI Tesla Elon Musk

Have you ever played a parkour game? FSD is now pulling off a perfect run through one of the hardest parkour levels imaginable — in the real world. To those who still doubt Tesla's vision-only approach: it's time to stop. FSD V14 glides smoothly along an ultra-narrow mountain road in dense fog, handling conditions that would make most human drivers nervous. In Mad Max mode, it maintains impressive speed while effortlessly avoiding rocks and debris scattered across the road from landslides hidden in the fog. This isn't a simulation. This is reality. 🚗💨🌫️🏔️ Ashok Elluswamy Whole Mars Catalog Edge Case Tesla AI Tesla Elon Musk

BigHu-L5

27,238 次观看 • 1 个月前

Found myself in a WILD FSD edge case this morning-- the start of a police-escorted lane closure across 4 lanes of traffic. Convoy was moving left across traffic with arrows indicating all traffic needed to flow to the right. I should have let FSD continue to monitor behavior but got nervous when it was trying to overtake the convoy on the left (which wouldn't have been possible by the time I took over but was awkward nonetheless). Traffic was also coming to a grinding halt behind me from 70+mph to 30mph. FSD 14.3.3 would have absolutely figured it out after the fact, but it didn't have the foresight to understand to FOLLOW THE RIGHT ARROW on the convoy. All in all, imo this is adequate behavior for this edge case but some polishing would be highly preferred.

Found myself in a WILD FSD edge case this morning-- the start of a police-escorted lane closure across 4 lanes of traffic. Convoy was moving left across traffic with arrows indicating all traffic needed to flow to the right. I should have let FSD continue to monitor behavior but got nervous when it was trying to overtake the convoy on the left (which wouldn't have been possible by the time I took over but was awkward nonetheless). Traffic was also coming to a grinding halt behind me from 70+mph to 30mph. FSD 14.3.3 would have absolutely figured it out after the fact, but it didn't have the foresight to understand to FOLLOW THE RIGHT ARROW on the convoy. All in all, imo this is adequate behavior for this edge case but some polishing would be highly preferred.

The Cybertruck Guy

12,879 次观看 • 1 个月前

Chinese FSD testers were blown away and couldn’t believe what happened. FSD was looking for road entrance in a big open lot. No markings on the ground. No signs. FSD recognized not going off the edge of the lot. It almost looked like FSD AI was conscious, sort of knowing what it needed to do to get back to the road. Truly incredible. Tesla AI Ashok Elluswamy

Chinese FSD testers were blown away and couldn’t believe what happened. FSD was looking for road entrance in a big open lot. No markings on the ground. No signs. FSD recognized not going off the edge of the lot. It almost looked like FSD AI was conscious, sort of knowing what it needed to do to get back to the road. Truly incredible. Tesla AI Ashok Elluswamy

Ray

1,556,066 次观看 • 1 年前

At a product launch event last year, Li Bin, ceo of NIO, said “those who think of LiDARs being useless are either dumb or evil. LiDARs can make up for the weakness in vision-only perception”, followed by a short clip showing that LiDAR is able to recognize the obstacle (a stack of tires) in pitch dark and come to a full stop. That was his comment made before FSD rolled out in China. Pretty sure he has watched plenty of FSD videos and wonder what he has to say now.

At a product launch event last year, Li Bin, ceo of NIO, said “those who think of LiDARs being useless are either dumb or evil. LiDARs can make up for the weakness in vision-only perception”, followed by a short clip showing that LiDAR is able to recognize the obstacle (a stack of tires) in pitch dark and come to a full stop. That was his comment made before FSD rolled out in China. Pretty sure he has watched plenty of FSD videos and wonder what he has to say now.

Ray

70,152 次观看 • 1 年前

Did a lot of V14 highway testing today. Major, major improvements. Follow distance is way more comfortable and dynamic based on speeds. The car always gets to the left when it can as cars merge onto the highway. Way faster reactions to speed changes and way sooner. There was a broken down car blocking the right lane, and FSD shifted left before I even noticed it. I hated how closely V13 followed cars in fast moving, dense traffic. I also hated that I’d see traffic pattern changes ahead before the car seemed to notice. All of these anxiety triggers are completely gone now. Highway driving has been magic so far. Here’s a clip of FSD safely and flawlessly handling the shortest merge lane of all time.

Did a lot of V14 highway testing today. Major, major improvements. Follow distance is way more comfortable and dynamic based on speeds. The car always gets to the left when it can as cars merge onto the highway. Way faster reactions to speed changes and way sooner. There was a broken down car blocking the right lane, and FSD shifted left before I even noticed it. I hated how closely V13 followed cars in fast moving, dense traffic. I also hated that I’d see traffic pattern changes ahead before the car seemed to notice. All of these anxiety triggers are completely gone now. Highway driving has been magic so far. Here’s a clip of FSD safely and flawlessly handling the shortest merge lane of all time.

Mike P

27,042 次观看 • 9 个月前

Here’s my first drive on Tesla FSD V14.2. For the first time on V14, I had zero hesitation or braking issues all day, and no interventions. From a driving perspective, and after 85 miles on and off-camera on V14.2 today, it now feels as comfortable, if not more so, than V13 did, but with all the capabilities of V14. What’s new in FSD V14.2: • Self-Driving stats section that tells you exactly how many Self-Driving miles you’ve driven and the percentage of FSD miles • You can now select speed profiles and parking preferences while in park • Upgraded the neural network vision encoder, leveraging higher resolution features to further improve scenarios like handling emergency vehicles, obstacles on the road, and human gestures • Big improvement (in my experience) to overall everyday driving comfortability • Slightly less strict attention monitoring at times In my opinion, V14.2 is good enough to be sent to every AI4 owner where FSD is legal, and for Tesla to encourage non-FSD owners/subscribers to try it. FSD did have a couple weird navigation decisions it made in my video, but that’s my only complaint. Overall, great version of FSD. 4K YouTube version of my video in thread below:

Here’s my first drive on Tesla FSD V14.2. For the first time on V14, I had zero hesitation or braking issues all day, and no interventions. From a driving perspective, and after 85 miles on and off-camera on V14.2 today, it now feels as comfortable, if not more so, than V13 did, but with all the capabilities of V14. What’s new in FSD V14.2: • Self-Driving stats section that tells you exactly how many Self-Driving miles you’ve driven and the percentage of FSD miles • You can now select speed profiles and parking preferences while in park • Upgraded the neural network vision encoder, leveraging higher resolution features to further improve scenarios like handling emergency vehicles, obstacles on the road, and human gestures • Big improvement (in my experience) to overall everyday driving comfortability • Slightly less strict attention monitoring at times In my opinion, V14.2 is good enough to be sent to every AI4 owner where FSD is legal, and for Tesla to encourage non-FSD owners/subscribers to try it. FSD did have a couple weird navigation decisions it made in my video, but that’s my only complaint. Overall, great version of FSD. 4K YouTube version of my video in thread below:

Sawyer Merritt

144,763 次观看 • 7 个月前

Tesla FSD gives this person the chance to get behind the wheel for the first time in 10 years! But this is EXTREMELY IRRESPONSIBLE, it’s called FSD (Supervised) for a reason because the driver needs to be able to take over in case of an emergency. Yes, the software is great, but it’s not fully ready for hands free and eyes off the road driving yet…

Tesla FSD gives this person the chance to get behind the wheel for the first time in 10 years! But this is EXTREMELY IRRESPONSIBLE, it’s called FSD (Supervised) for a reason because the driver needs to be able to take over in case of an emergency. Yes, the software is great, but it’s not fully ready for hands free and eyes off the road driving yet…

Parker

187,155 次观看 • 2 年前

FSD V14.1.1 Drive Thru V2 Last night I posted a video of FSD V14 handling a drive through perfectly. I rolled up the window after each 'stop' and held my hand out of the window at the end to try and keep the car from moving. Well this time I did none of that, and the car actually did better than last time. Incredible stuff - how do you all think Tesla AI has managed to do this?

FSD V14.1.1 Drive Thru V2 Last night I posted a video of FSD V14 handling a drive through perfectly. I rolled up the window after each 'stop' and held my hand out of the window at the end to try and keep the car from moving. Well this time I did none of that, and the car actually did better than last time. Incredible stuff - how do you all think Tesla AI has managed to do this?

Devin Olsen

70,792 次观看 • 9 个月前