FSD error reporting by voice

[EtherMN]

With all the safety in mind, can anyone believe there isn’t a voice command to report an FSD incident?

 

[diplomat33]

With all the safety in mind, can anyone believe there isn’t a voice command to report an FSD incident?

I thought saying "bug report" was the voice command for reporting a FSD issue.

 

[JulienW]

Can it edit?

God da$$ you piece of sh$% FSD what the fu$$ing hel$ were you thinking? Holy Shi$ you almost hit that dumb a$$ so$ of a Bitc$ that pulled out in fu$$ing front of you. Are you mother fuc$ing blind and stupid? What a dic$ head, pis$ as$ poor response that was.

EDITED version:
Peace FSD team, not sure what my car was thinking. It failed to properly slow and change lanes to avoid a car that pulls out. Did not seem to image the offending car or respond as expected in a timely fashion.

 

[EtherMN]

I thought saying "bug report" was the voice command for reporting a FSD issue.

I think that reports general issues with the car. Nothing for FSD issue reporting by voice...

 

[JulienW]

The entire premise is based on what is probably an incorrect assumption. That being Tesla has 100s of engineers sitting around watching 1000s of video clips all day. In all likelihood the clips go into software that analyzes, sorts, prioritizes and aggregates most (or maybe they just go into a black hole). I bet at most only a small percentage (probably >0.5%) are actually deemed important/unique enough to be analyzed by a human.

That means there is no place for voice descriptions.

 

[EtherMN]

So are you saying that hitting the video report button for FSD issues is pretty much pointless?

 

[VanFriscia]

The entire premise is based on what is probably an incorrect assumption. That being Tesla has 100s of engineers sitting around watching 1000s of video clips all day. In all likelihood the clips go into software that analyzes, sorts, prioritizes and aggregates most (or maybe they just go into a black hole). I bet at most only a small percentage (probably >0.5%) are actually deemed important/unique enough to be analyzed by a human.

That means there is no place for voice descriptions.

Most likely you're correct in your first paragraph. However, the way I interpreted the OP's question wasn't to include a verbal description of why you took the snapshot; it was simply to take the snapshot, period, so you didn't have to fiddle with finding and pressing the button. Sounds handy to me.

 

[EVNow]

The entire premise is based on what is probably an incorrect assumption. That being Tesla has 100s of engineers sitting around watching 1000s of video clips all day. In all likelihood the clips go into software that analyzes, sorts, prioritizes and aggregates most (or maybe they just go into a black hole). I bet at most only a small percentage (probably >0.5%) are actually deemed important/unique enough to be analyzed by a human.

That means there is no place for voice descriptions.

I don't expect engineering hours spent on this.

Tesla has a 1,000 labelers. I expect them to be looking at reports, classifying them, labelling them etc. After it all goes through auto-labelling.

Still, 25k cars, 10 reports per day means 1,000 labelers will have to look at 250 reports daily. They have to also look at and analyze disengagements. That is probably too much, even at 1 minute per report. So, they will have to do some kind of auto-filtering.