-
Want to remove ads? Register an account and login to see fewer ads, and become a Supporting Member to remove almost all ads.
I did a little of my own investigation on the API change comment - at least, in what's returned by the various rest calls. I didn't see anything significant between the current API and what was returned back in 2017.28 from my car. In the /data call, the only difference I saw is the appearance of a new parameter under vehicle_config, called can_actuate_trunks. Not sure what it means, for my car the value is False and I have powered liftgate.
Last edited:
It's time to bring in the Gimp!
TexLaw
Member
HookBill
Member
Okay as I said I'm in for $100 betting that at least one new actual feature for autopilot is released by Dec 31. Yes I've walked back my claim and this is where I stand on it - no more changes allowed to my bet. I wish I'd said Jan 31 at this point but too late. Donated to charity.
This is a very sticky point for me. I've come very close to ordering one of the "last call" S75s in the past weeks, but I have pretty serious uncertainty about the future of AP2, and that is my main interest in driving a Tesla over other manufacturers. The vague allusions to upcoming features by company leadership are not very inspiring. If they even released a plausible timeline or list of features being worked, that would have gone a long way in getting me off of the fence.
Seems like there's quite a lot of interest. Maybe we should start a separate thread for this? Perhaps you'd like to organise it, if you have time?
lunitiks
Cool James & Black Teacher
Ya, and make a "leaderboard" (poll) while you're at it
As we say in aviation - what's your mission, if I may ask? And how long do you plan to keep the car? Personally I think if you look at the progress of AP2 in year one it has been spectacularly fast and should encourage you not discourage you.
Stop focusing on Elon's imaginary timeframes. Stop listening to the hater brigade for a minute and start paying attention to people like @verygreen who bring real knowledge, and look at the actual progress rate of AP2/2.5. Do some reading about neural nets and reinforcement learning and what is happening on the cutting edge. Remember that learning involves lots of struggle with no visible progress and then breakthroughs in performance happen. Remember that the brain of AP 2/2.5 is a swappable board. Finally, remember that Tesla is still, one year later, betting the company on vision and selling the FSD option. They are ramping up the Model 3 with a vision based autonomy system. This says something. Also remember a lot of progress is likely happening in traffic logic simulation that we know nothing about.
The simpletons here on TMC believe that "No me car turn by itself! Been one year! Me angry! Me car no workie! Me angry! Elon dumb! This impossibowl! See Waymo! See big spinning dome! Dat key! Me want spinning dome too! Why Elon dum?"
For me, my mission is driving long distances on highways for business. AP 2 suits this mission perfectly in current 0.42 form.
To believe the software will NOT improve drastically from here you have to buy into several ridiculous claims:
1 - The autopilot team suddenly stops making progress.
2 - Tesla mysteriously becomes the only self driving player unable to teach traffic logic to its cars, despite having a world class AI team and having the largest fleet of vehicles in the world by orders of magnitude, gathering image data for learning.
3 - Despite the fact that vision plus radar is already reliable for lane keeping and cruise control, for no apparent reason Tesla is unable to make the cars turn left and right without hitting things.
At this point vision is great and getting better. The real problem is traffic logic - that's where the hard part is and that has nothing to do with sensor tech. That's stuff like "If I cut one lane over what will the guy two lanes over do?"
George Hotz gives a great talk on this recently where hen points out that sensing is the easy part - the hard part is decision making and that has zero to do with sensors.
Also remember that reinforcement learning is bleeding edge tech and Karpathy is an expert at it.
For other stunning reinforcement achievements see Alpha Go Zero's recent crushing of the original Alpha Go. @verygreen gives some good comments elsewhere here recently on the challenges of reinforcement learning for driving.
But if you want guarantees that the current setup will take us to Level 5 - I think you're asking too much. Very robust L3/4 I think is the likely outcome. Lack of rear radar or a camera high off the ground is my concern.
However even during a recent rainstorm I was able to discern incoming vehicles from behind on the rear camera despite it being covered in vision distorting water drops.
I can see us getting to a system that alerts you to take over if it loses confidence in its rear vision. So a Level 4 that requires frequent cleaning of the rear camera (maybe a quick wipe before each departure and then a touch up wipe every few hrs).
I agree to let oktane be the judge. Even he won't be able to spin this one. Either the feature is released or it isn't. It may have restrictions like "operates only at 15 mph or below on sunny days in July within a 5 mile radius of Fremont HQ" but it will still count.I’m very impartial against AP2 and volunteer to be the judge.
ahkahn
Active Member
Thank you for being the voice of reason. Often times the mob gets in the way of true facts....
powertoold
Active Member
It's great that some people here are optimists, and judging from the improvements in AP2 lately, we should be optimistic.
But there are two camps in these kinds of discussions, optimists and people who believed Elon. If you believed Elon about AP2, then you would feel somewhat disappointed at the current reality vs. what Elon said almost a year ago. Since then, Elon has actually backtracked on his EAP and FSD confidence. About 6 months ago during an earnings call, he said he's confident the current AP2 hardware will lead to FSD, but now, he's saying the AP2 hardware will probably lead to almost human performance. It's difficult to predict how much further he is going to backtrack.
I think some people here are happy that there IS improvement in AP2, but others are simply focusing on what Elon said and why it has yet to become reality.
But there are two camps in these kinds of discussions, optimists and people who believed Elon. If you believed Elon about AP2, then you would feel somewhat disappointed at the current reality vs. what Elon said almost a year ago. Since then, Elon has actually backtracked on his EAP and FSD confidence. About 6 months ago during an earnings call, he said he's confident the current AP2 hardware will lead to FSD, but now, he's saying the AP2 hardware will probably lead to almost human performance. It's difficult to predict how much further he is going to backtrack.
I think some people here are happy that there IS improvement in AP2, but others are simply focusing on what Elon said and why it has yet to become reality.
What is there to disagree on? The bet is not about quality it's simply about feature release yes/no.
No it isn't. Where is the data showing that quantifiable customer satisfaction numbers are lower than 12 or 24 months ago? As for AP improvements (or lack thereof) - are you familiar with the last 12 months of AP progress, starting from zero AP with a system Tesla has created from scratch? AP is moving very very fast - faster than anything any competitor has - and it is still the most capable and robust L2 system available for purchase.
Tjhappel
Member
I too drive long distances for work, typically 150-200 miles a day and would be ecstatic if they could get just the freeway portion nailed. On good clean marked roads it’s alreasy good enough for what I need but carpool lane on 5/405 freeways is pretty bad, like I won’t use it if anyone else is in the car.
Really really hoping we get a large update soon but I’m still willing to bet 100 that we don’t get any additional cameras before the end of the year.
Really really hoping we get a large update soon but I’m still willing to bet 100 that we don’t get any additional cameras before the end of the year.
