正在加载视频...

视频加载失败

FSD didn't handle this situation well. The driver had to step on the accelerator to get past a car blocking the lane, and FSD didn’t return to the correct lane afterward. I added English subtitles for key conversations.

246,151 次观看 • 1 年前 •via X (Twitter)

11 条评论

Aaron Li 的头像
Aaron Li1 年前

Source: Douyin 影音时光

TurboScribe 的头像
TurboScribe1 年前

What REAL customers say about TurboScribe's unlimited AI transcription 👇 🇺🇸 "Thank you for developing such a fantastic AI tool." - Kathleen 🇮🇹 "The AI transcription tool I've been waiting for." -Luca 🇷🇴 "It's so accurate that it's scary!" - Cosmin

Anth 的头像
Anth1 年前

@alojoh These edge cases are good. Hopefully the feedback makes it way back to Tesla to fix.

ShenYu 的头像
ShenYu1 年前

That is the case Tesla wants to collect.

Lucille Chadwick 的头像
Lucille Chadwick1 年前

It noticed that there are crazy things happening on the right lane so it decided to use left

CJDGiesen 的头像
CJDGiesen1 年前

Not saying it handled that correctly, but if you look closely this LOOKS like a vehicle with flashing lights blocking a lane. And you would usually see that at construction in which case FSD did the completely correct thing to not use that lane, as it would have workers on it. This is actually a very interesting edge case that shows why non-neural network approaches will never succeed. The real world is weird.

MokGrok 的头像
MokGrok1 年前

@aelluswamy

Better Humanity 的头像
Better Humanity1 年前

Why the left lane is wrong lane if it’s one way road. Maybe not the preferred lane for the driver but not that wrong. If another car come on same lane behind then the FSD will go to right lane.

tayyare79 的头像
tayyare791 年前

Good Videos thanks for the effort

AGI - Tech Gone Wild 🤖❤️‍🔥⚔️ 的头像
AGI - Tech Gone Wild 🤖❤️‍🔥⚔️1 年前

@alojoh Nice new data 🤗 @aelluswamy @Tesla_AI

FSD_Europilot 的头像
FSD_Europilot1 年前

They printed should have disengaged, otherwise it is harder for the model to learn

相关视频