This article is covering two different topics and trying to make it seem like one thing that it is not...
1. GM is using an ML model for their "torque management" which is a fancy of of saying a linear feel pedal.
2. This new generation of ecu has more encryption... every new generation of GM ecu has more lockouts.
The author alludes to how tuner will not be able to beat GM's torque mapping controls with aftermarket tuning. Sure... but often times turners are not targeting the drivablity mapping of an OEM tune, they are targeting fuel, ignition, and or boost mapping to compensate for better fuels, more VE (turbos), or other power adders.
TBH on flagship sports cars, we are on the knifes edge of optimizations for most platforms; most aftermarket solutions are now just lop-siding the maximized "any condition" performance OE's seek for simply more power. Power that typically will sacrifice either low end, drivability, and or reliability. The sweet spot for performance tuning now a days exist in the middle range of vehicles for most manufactures where engines are not focused on their ultimate tuning potential VS reliability.
This all being said, these torque management strategies are nothing new, GM is just using fancy math blocks within their ecu that can account for more inputs and a higher resolution. Modern standalone ecus like Emtron and Motec utilize these types of torque strategies to better pair with modern high end transmissions like the 8hp90 and DL800. These transmissions need to communicate with the ECU to ensure power delivery from the engine works with shifting performance and clutch engagement.
OEM's are still worried about emissions, aftermarket tunes are not.
For example, enabling power enrichment at less throttle opening will improve performance and allow you to run a little bit more timing, but also increase hydrocarbon emissions.
There is the big one - OEMs have to meet mandated emissions regulations and governments check (see VW). Aftermarket legally has to meet the same regulations, but in practice (at least so far) they mostly have not been checked, and if they are checked it is only after they have sold something and got it installed on a car, while OEMs get checked before they sell anything. Which is to say aftermarket is generally just trading power/fuel efficiency (often both) for worse emissions.
It would be an interesting reverse engineering challenge, 20 years down the road when it is more accessible.
I spent 1.5+ years on my 2005 car's ECU to reverse engineer most of the maps, since no public tuning files existed.
I then went and spent 1 year on the TCM for which again, no tuning files existed. With the patent files, I was able to discover the algorithms and maps, and am even in IDA as I write this, and in Ghidra emulating some code.
Haven't we been using electric motors and smaller turbos to get around lag? I drove a 3 cylinder MHEV EcoBoost that seemed to use the electric motor(s?) quite well. It seems like a good idea in theory, though I can understand the negatives of electrifying the powertrain. Definitely an interesting topic.
I remember hearing about the days of the early 911 Turbos (if my memory's correct) where you'd get a bunch of boost all at once... We've definitely come a long way!
I was thinking of that when I wrote the comment! I've heard of electric turbochargers, but I'm not sure how good they are under real-life conditions. Directly using heat energy from the exhaust (as opposed to introducing electric conversion losses) seems wiser to me. Part of me has always liked making use of what would otherwise be wasted to entropy.
In theory (though not a mechanic, just have an interest in this), the best middle-ground would be to retain the same design but add a motor to the turbocharger shaft which would mainly be reserved for spool ups -- is that what they're doing?
Well, from what I understand, the car I drove did. I believe the motor was hooked up to engine's output shaft in some way, so they could work together to generate torque. The gearing seemed very low for the displacement (even had a 6th gear!), so it would suggest they were making good use of the electric powertrain.
there always was. However the way you drive is not very unique and so odds are they have anticipated everything you will do in the real world. (this doesn't mean they can solve lag for all those situations, only that they already know about them: if they can't anticipate it is because of some other factor).
From a technical/algorithmic POV - this doesn't sound particularly remarkable, because it sounds about the same as how modern CPU's "boost" themselves.
And actually, I think there is similar tech in "speaker systems" already. An "older" one that I've read about is from RCF (an old+big Italian company with systems ranging from desktop to festival size), and they call it [Bass Motion Control](https://www.rcf.it/en/art-9-series);
> The BMC method works by creating a complete map of the dynamic behavior of the woofer, to generate a custom algorithm that only limits over-excursions. This gives total freedom of signal reproduction to the transducer. When high-pass filters normally protect the woofer motion from becoming destructive but change the phase behavior, the new BMC algorithm breaks conventional rules.
Now I don't know how effective RCF's approach truly is, but another company that is doing "big-things" is Dirac. They released a blog post about a year ago titled [Boosting Audio System Sustainability with Dirac](https://www.dirac.com/blog/boosting-audio-system-sustainabil...), and there is a section called Enhancing performance with optimized components;
> By employing Long Short-Term Memory (LSTM) neural networks, we can make the driving force on the voice coil (the part of the speaker that turns electricity into sound) more consistent, improving the mechanical design and compensating for magnetic limitations.
> NLC adjusts the voice coil current to correct force factor irregularities (inconsistencies in the voice coil’s efficiency) without requiring complex mechanical measurements. In tests with an otherwise suboptimal driver, our technology reduced distortion by 10 dB, nearly matching the performance of a well-designed driver.
Readit News
1. GM is using an ML model for their "torque management" which is a fancy of of saying a linear feel pedal. 2. This new generation of ecu has more encryption... every new generation of GM ecu has more lockouts.
The author alludes to how tuner will not be able to beat GM's torque mapping controls with aftermarket tuning. Sure... but often times turners are not targeting the drivablity mapping of an OEM tune, they are targeting fuel, ignition, and or boost mapping to compensate for better fuels, more VE (turbos), or other power adders.
TBH on flagship sports cars, we are on the knifes edge of optimizations for most platforms; most aftermarket solutions are now just lop-siding the maximized "any condition" performance OE's seek for simply more power. Power that typically will sacrifice either low end, drivability, and or reliability. The sweet spot for performance tuning now a days exist in the middle range of vehicles for most manufactures where engines are not focused on their ultimate tuning potential VS reliability.
This all being said, these torque management strategies are nothing new, GM is just using fancy math blocks within their ecu that can account for more inputs and a higher resolution. Modern standalone ecus like Emtron and Motec utilize these types of torque strategies to better pair with modern high end transmissions like the 8hp90 and DL800. These transmissions need to communicate with the ECU to ensure power delivery from the engine works with shifting performance and clutch engagement.
For example, enabling power enrichment at less throttle opening will improve performance and allow you to run a little bit more timing, but also increase hydrocarbon emissions.
I spent 1.5+ years on my 2005 car's ECU to reverse engineer most of the maps, since no public tuning files existed. I then went and spent 1 year on the TCM for which again, no tuning files existed. With the patent files, I was able to discover the algorithms and maps, and am even in IDA as I write this, and in Ghidra emulating some code.
I remember hearing about the days of the early 911 Turbos (if my memory's correct) where you'd get a bunch of boost all at once... We've definitely come a long way!
https://www.motortrend.com/news/2025-porsche-911-gts-t-hybri...
When a tech path costs too much for F1, that's a good sign you won't be seeing it in a GM product any time soon.
OP system is just using a computer to get on the gas a little faster when the driver hits the pedal quickly.
In theory (though not a mechanic, just have an interest in this), the best middle-ground would be to retain the same design but add a motor to the turbocharger shaft which would mainly be reserved for spool ups -- is that what they're doing?
I feel similar to you in that complexity over time only locks out the user.
However I certainly do not miss a choke or having to mess with a carb in general on my road going vehicle.
You know what that means: There will be lag in all unanticipated situations.
And actually, I think there is similar tech in "speaker systems" already. An "older" one that I've read about is from RCF (an old+big Italian company with systems ranging from desktop to festival size), and they call it [Bass Motion Control](https://www.rcf.it/en/art-9-series);
> The BMC method works by creating a complete map of the dynamic behavior of the woofer, to generate a custom algorithm that only limits over-excursions. This gives total freedom of signal reproduction to the transducer. When high-pass filters normally protect the woofer motion from becoming destructive but change the phase behavior, the new BMC algorithm breaks conventional rules.
Now I don't know how effective RCF's approach truly is, but another company that is doing "big-things" is Dirac. They released a blog post about a year ago titled [Boosting Audio System Sustainability with Dirac](https://www.dirac.com/blog/boosting-audio-system-sustainabil...), and there is a section called Enhancing performance with optimized components;
> By employing Long Short-Term Memory (LSTM) neural networks, we can make the driving force on the voice coil (the part of the speaker that turns electricity into sound) more consistent, improving the mechanical design and compensating for magnetic limitations.
> NLC adjusts the voice coil current to correct force factor irregularities (inconsistencies in the voice coil’s efficiency) without requiring complex mechanical measurements. In tests with an otherwise suboptimal driver, our technology reduced distortion by 10 dB, nearly matching the performance of a well-designed driver.
Given the recent past about sensors and reliability I’m adding even more will be great for reliability and cost.
I’m sure this design came from the committee of geniuses who brought us the wet belt.
Rant over. (Sorry)
Dual-clutch transmissions especially need to anticipate the next move as either an upshift or dowshift.
This is just extending that idea to the engine itself.