#Fly By Wire Model (5 Sep 2025)
93 messages · Page 1 of 1 (latest)
Installing
In a parking lot. Grabbing now.
This one torq made a pr like 6 hours ago at almost midnight pacific time
wild
Hopefully fly by wire means experimental gonna be fast
They were just waiting for the red diff sprint to be over, and bam-bam-bam 🤣
I have an 80 mile drive on the interstate today for work, which model should I test first? gWMv4 or Fly by Wire?
Holy acceleration. they want us to fly to the moon
Has anyone tried this model? How it compared to gWM 4?
Is it so good that someone doesn’t want to finish the test drive for an hour?😂
I haven't even got to try Firehose yet 🥲
good thing firehose merged to master before these two came out, so these are likely firehose data too from now on
Try it!
Vibes from a highway drive to work.
Low speed torque requests are less than firehose, but recentering still seems to be good.
Highway lat is good, on par with firehose.
This models seems to identify cars further out more reliably and match speed quicker. With a lead it sat below the set speed and slowly crept up on them going around 70mph.
Have not came up behind anyone that has been stopped but I think this model will probably be better at long than previous models, will be interested to see what everyone else experiences. Will run again on the way home before trying gWMv4
Almost a wow on lat. aggressive curves. Occasional left biasy on some straight s for my taste. Not as planted as gwm 4
Just did 26 miles on this one. I agree with @brave oriole it seems to detect leads from a further distance, long felt real safe. I ran full experimental in city and speeds are still too inconsistent but I used it for all the city driving. Curves felt good it did go over the white line a bit on the inner side of the curves but I don’t think it went too deep into the neighboring lane.
as i make the video i realized how inconsistent it is. so its an 8 https://youtu.be/XSvVCOWU1EU
hmm I dunno if I'm using this wrong but this has been horrible for me
not going around parked cars much just wanting to go straight into them or if it does go around them it stays in the opposite lane rather than going back
turns (with turn desires) have been terrible too
Same
It does not respect stopped cars
It went around parked cars for me but I was very low speed like under 10mph
This model is a red diff!
Less complex architecture
We're still not allowed to merge green diffs, until monday
Right after downloading this model I was driving down a road and it acted like it was going to hit a parked car. Thought I'd switch when I got home, but as I was driving down the road to my house it did the best job I have seen from any model at driving around parked cars. It gave plenty of room (which every model I have tried gets a little closer than I would like) and it even stayed out a little wider as there was another parked car about 200 ft further and then after passing that last one it centered itself perfectly.
Not sure why it did so badly on its first attempt though. Will definitely keep testing. Though it doesn't have as much steering torque as other models which is a bummer.
I’ve never wanted the weekend to end so badly
Can someone explain like I'm 5 what this means?
yeah steering torque seems to be lacking on this model for sure
This model has a horrible left bias
Comma is doing a sprint (2 weeks?) where they only merge changes that delete code. They said no new models until this is over. In this case Torq said that this model came about from deleting code from their training stack so that it counts towards the red (delete) code sprint.
I guess we'll find out whether whatever he deleted made this model better/worse or unchanged relative to the others
Thank you! What is the purpose of comma doing this?
Cleaning up their code. Deleting things that are redundant or overly complex and to make maintainability and extension easier going forward
Okay that makes sense. Thank you for the explanation!
Really good low speed lateral though
Definite left bias, let it stop at a light. It stopped a little late, about 1 ft over the line. Then it very slowly crept about 3 ft. and tried to take off. Oops. Lat was OK.
worse lmao
Long is weak on this model
Blows reds compared to gWM4
Experimental gets too close
Regression compared to gWM4, but gWM4 is a pr too so I guess I can’t compare the two
Firehose has been great (and now in master) so that's what I would compare it against
Long is great on firehose, but low speed lat 90degree turns was weak on it too compared to WM models
i only ran into one redlight on gWM4, it had just turned red but it did blow through it lol
gWM4 > Firehose Model > FBW
all 3 are red diff?
kk
oof yeah this one's lat feels more sloppy and lazy than firehose. It also feels like it's accelerating too much which made me feel super uneasy for the first time in exp long, like it was going to ram into the back of someone if I didn't start slowing down manually
I didn't read reviews before trying Fly by Wire on 2025 Ioniq 5. (Lat only)
Less smooth than Firehose. More torquey. Might be OK except it seems to have more of an uncomfortable right hug on highways. After more highway driving I find its lane keeping to be inconsistent. Mostly fine. Sometime with uncomfortable right hug. Sometimes hugging left. It's mostly fine but less comfortable than Firehose on highways.
I noticed on local unmarked streets it's not very good at dodging parked cars. Firehose was noticeably good at that.
the highlight of this model is the aggressive curves more aggressive than spacelab3v2 it seems
It seemed good at high speed aggressive curves but low speed it didn’t seem to ask for enough torque. Did that happen for you?
start of the video i was impressed #1413507018894868600 message this is the only time i tested FBW its just the too much left bias and i cant tolerate it without having the feel of being planted
That's exactly what I saw
After the dev-c3-new update today. https://youtube.com/shorts/f73Isfbn_us?si=Vpqb-PPlHDaSMXIh
They should rename fly by wire to LCT lead car tracer if you follow too close like one bar of distance, it will copy the lead car position so if the lead car ping-pongs you’re gonna ping-pong, if the lead car left bias or right bias, you’re gonna do the same and so forth and so on, so give this model another chance and have the lead follow in mind
seems this model is made for nyc/nj 😝
yeah observe the lead car you gonna have fun with this model
If you wanna prevent it just do the 3 second rule follow
and stay in the slow lane
my fixed 25 steer ratio did a wonder on this model , now it feels planted and curves way better. Lead car tracing is very good feature on surface streets i just realized https://www.youtube.com/watch?v=WOVJUwe29lI
So I'm actually going to do a 180 here and say this model is quite good! There are definitely still some issues with lane placement and it failed a cone test I did, but the upside was that it was the most "human" feeling and had a lot of confidence in what it chose to do. It was the first time where after having extended amount of time with a model, that I felt like it was the closest to how a friend might drive you around somewhere.
If this was something like a more general training process, it definitely felt more raw and more like it wasn't constrained to be stricly in the center and it really felt like it had more of a grounded human personality.
Very cool! This may actually be my favourite exp long yet, and feels like it would benfit the most from scaling up the model and scaling out the training data
Well you convinced me to switch back, and I agree, it feels very natural.
Fly By Wire Model Questionnaire - https://forms.gle/uAFNMiRQLEwUnvgz7
Fly By Wire Model Responses - https://docs.google.com/forms/d/1JnYm-9yleKlHhWtJg_F2By916NVXQ7JCEs3k5dPG6ME/viewanalytics
Just FYI my lagd has been continually decreasing on this model for some reason. It used to be .28-.27. It is now sitting at .243
The model seems to be doing better as lagd is adjusting down
oohh.. that s a nice info, ill take a note on that
i did a blind a test today by accident, i load dtrv6 thought it was new since i saw the 12th disregarding the month lol. anyway coming from fly by wire and gwm5 it feel the same or a bit of a regress- too close to islands in street testing.
I do a lot of highway driving so I’ll see where each model stabilizes at in the future
yeah do downgrade to you favorite model and see how the new models fare after testing them for a while
im leaning towards fly by wire-its a red diff model but i dont know what it means maybe someone can explain.
I don't know exactly what it means in the context of a model, but a red diff typically means things were removed
My understanding is that the model was created by them removing code rather than adding code.
Which is why I’m wondering if that’s why the lagd went down.
And currently firehose and FBW are my two favorites so there isn’t much to change back to.
But for the sake of testing I can go back to a different one and see if the number goes up
I find this model to have steering so sloppy and lazy that I can't tolerate it.
It’s by far on the worst
right?