AI Training - Will it work?

Yes, these are coming in the future.

1 Like

Thanks for the very expedient reply. Looking forward to them :+1:

1 Like

Hi @Nate_Pearson,

Here’s the transcript on your Feb 25th podcast.

98:02
I’m just going to add that this is it’s a long, the lines of what we did with
98:05
our high volume of sweet-spot base.
98:07
It was a request.
98:08
We didn’t really think the science was there.
98:10
We didn’t really want to prescribe it, but we got a lot of requests and it was
98:13
like, well, a lot of people want to do it.
98:14
Let’s let them do it.
98:15
Let’s see what happens.

Cheers!

2 Likes

And to add to that, we see athletes accomplish the plan and improve their FTP in the short and long term.

Im glad some people find value in that. My comment was specifically pointing out that you guys offered that plan based on commercial interest and not on the evidence that is a good practice.

I would say based on a very educated hypothesis. I just sent this message to Chad and he regrets the way he said it.

Also, we have commercial interest in making you faster. That’s how we make money. I would say our interests are aligned with TR athletes.

11 Likes

Why not have TR simply stop calling ramp test result FTP?

1 Like

I have also this in my mind. Name of FTP becomes more confusing. Some says CP60 is proxy of FTP, TP have mFTP, 95% of 20min known to many folks, and now TR defines Ramp Test Result as FTP. People will also use manual edit of their FTP onwards after their 20min/8min/KM test.

Hm… maybe we are putting too much significance to the presence of FTP. Make new name for TrainerRoad FTP and ditch the whole FTP concept might be better for TR.

Well that’s a good way to move the debate for sure. The ramp test is a good diagnostic. It’s repeatable & does require a ton of recovery time…or as much mental energy to get a usable result.

But, in general, I look at the ramp test like I look at a balance sheet. The stuff at the top, I believe…so MAP and cash/STI are pretty believable numbers. As we go down the chain the numbers are less reliable…so the Seiler/Ronnestadt benchmark that min power to elicit VO2 max is usually your ramp test best 5min-6min power is a little bit like receivables. You can believe it but you sure better read the notes. :smiley:
Ramp-test-derived FTP is more like goodwill. Yikes. You’re going to have to just go find out for sure before you believe it. Definitely subject to writedown.

But the good news is it seems like once you’ve got a rider’s physiology kind of figured out the ramp test can pretty reliably give you the results you need. It really is a pretty solid test. It’s just that FTP as a percent of MAP has a big enough std dev that it’s a problem for some riders.

1 Like

Interesting topic, I’m enjoying the thread. Just a bit of background, as one of my hats I’m CFO of a business that’s doing some amazing things with AI / ML. AI itself is fascinating, but AI alone makes a horrible product. In fact, the AI engine itself is essentially just a dumb software program. You need a) tons of b) high-quality c) relevant data, and to get that you need d) subject matter experts that e) understand how to build and manage a data assets team, and then you need f) a great team of developers/designers to get the UX/UI right.

I’m not surprised at all at what TR is doing - the approach makes sense, especially since they have the perfect data set to build from. Zwift almost certainly has more raw data, but far less of it will be actually useful.

I’ve always loved TR’s approach. In-person coaching is great, and probably still a must to squeeze out the last 5-10% of potential. But for 99% of us, that’s nowhere near relevant. 99% of us aren’t professional athletes. So a basic plan that can get a big chunk of the way there? That’s awesome, and - as a business - it scales. Coaches with humans simply doesn’t scale, your constraint is time. It’s why you end up getting coaches that get too busy so they copy/paste plans from one athlete and send it to another athlete…but forget to swap out the name…

The downside to TR’s approach, as alluded to by the recent Dylan Johnson video: It really only suits the big, fat middle of the bell curve. Sure, that’s like 68% of people within two standard deviations of the mean, but it means over 30% won’t really be suited, and -everyone- would benefit from individually tailored plans…that up until now you could only get from expensive coaching. That’s what makes what TR is doing so exciting.

I have tried to use Xert a few times in the past, and I really really wanted it to work: it was obvious that this type of AI-driven refinement to individualize training was the way forward. Unfortunately I found the Xert interface cluttered and hard to use – the exact opposite of intuitive, getting the workouts to work was problematic, and the whole process was just so convoluted that I didn’t want to waste any more time trying to figure it out.

I think (DC Rainmaker?) expressed it best, it’s better (for the company and the end-user) to have a good product with an amazing UI/UX, than a great product with a bad UI/UX. What’s the point of having a great product that nobody can figure out how it works?

IIRC Nate’s background was in software; it shows. TR’s app has always been extremely clean and intuitive. This is really just the first step in what is going to be some really really cool developments ove the next few years. A massive hats-off to the TR team. They’ll be some hiccups along the way, because it’s not clear yet what will and won’t work but you’re going about it the right way.

Will also add that this is another nail in the coffin that will probably slowly bury FTP. The only reason FTP is such a big thing is because it was the first ‘simple and intuitive’ way to measure performance / progress. It’s a shame that the way it was introduced resulted in people focusing on only the ‘power’ aspect; the ‘duration’ aspect gets overlooked. FTP was our first scientific vocabulary to talk about cycling performance. WKO / Training Peaks has made gradual progress in extending it - TTE (time to exhaustion, stamina etc.). The biggest issue people have with WKO of course is that casual users forget that the model needs to see *max efforts across the range of durations to be accurate. What’s nice about the TR approach is that the frequent Ramp Test is an easier and more reliable measure of progress most of the time, since it’s repeatable (greater consistency from test to test).

Going forward, we’ll be able to have performance and progress metrics that -make sense to us individually-, that fits our priorities and our goals.

14 Likes

So many people think the thing to optimize is FTP or W/kg, but that is far too simple of a definition. Most of us are trying to improve endurance (time to exhaustion, the right side of the power curve) and sprint performance (the left side of the power curve). So really the whole power curve is critical to consider, with some athletes caring relatively more about the left or right side.

Thankfully, TR clearly recognizes this because they are rating your level for different power zones, which is effectively measuring your TTE for different power zones, ie your power curve. And they were clear that different people want to optimize their curve differently and the ML model will optimize what is important to me, not some universal definition of optimal.

Also, Nate mentioned that the ML model is accounting for over 100 factors (features) that affect your training.

So it sure sounds like AT has been properly designed and implemented to really have a meaningful improvement to individualizing the training plans to get the best outcome for each user (assuming you put in the effort of doing the workouts and taking care of your body).

I am super excited for this and I think TR has a huge competitive advantage exactly because of how well they seem to have defined how and what to optimize and guide the athlete to using the tools effectively. I don’t see anybody mailing both of those aspects anytime soon.

4 Likes

Surely it has as much right to be called FTP as any other FTP estimate?

3 Likes

Fitness Assessment
image

2 Likes

Do not try and bend the TSS, that’s impossible. Instead, only try to realize the truth… there is no TSS. Then you’ll see that it is not the TSS that bends, it is only yourself.

8 Likes

I am very curious if this past year, with limited or no racing and considerably more time indoors, offered better than usual data for people who do directly follow plans? I know for myself that I saw better compliance in 2020 than ever before (and not surprisingly some serious improvement in my fitness as a result).

Another question is whether there are gradations to compliance in terms of how TR treats user data? E.g., this past year I largely stuck to mid-volume plans, but during SSB substituted the Wednesday Z2 workouts with the intervals prescribed in the high-volume plans. I also often added time to my Tuesday and Thursday workouts or opted for a + version of the prescribed workouts. Are these patterns something that TR would detect? Or would the changes simply be thought of as ‘non-compliance’?

My point is just that ramp test, 20 min, 8 min tests are indirect measures that estimate FTP.

So output should be called eFTP or something different all together.

Ramp test is a great idea. But TR does themselves a disservice by calling the result FTP - it has caused unnecessary confusion and angst when folks fail workouts trying to be rigid to targets where knowing actual FTP is really really important. Workouts where 1-3% makes a huge difference.

The new progression will hopefully fix this problem. But still an opportunity to alleviate unnecessary confusion by just not calling it ramp test output FTP at all. It is an initial educated guess to set training levels for a 4-6 week block of time and nothing more.

FTP is functional threshold power. If you can’t sit at that power for at least 30 min of time semi-rested then it isn’t functional at all. Same criticism goes for any proxy test.

I’m not knocking the method for initial setting of training levels. I’m knocking the nomenclature.

Here’s a common question: “why isn’t my FTP going up during specialty?”

In an ideal scenario, the answer there is FTP is actually be going up a bit, and duration at FTP is hopefully extending beyond 30 min. It is estimated FTP that isn’t moving.

Again, progression levels ultimately address this point. It is just always confusing to use a different definition of term used commonly in the broader community.

1 Like

*opensDoorAndThrowsIn

what is even FTP? An estimate of LT2?

*leavesThreadGiggling

Yes, same approach seems to work well for me.

What I would be looking for AT to do is make sure that I am progressing at the ideal level for me. I know from personal experience that I can handle some types of intensity better than others. For example, based on the same FTP: threshold intervals and over-unders at threshold I can do without much trouble, likewise short VO2, but give me a set of longer VO2 intervals (3mins plus) and I fall apart. So having different progression levels for the energy systems based on my performance will be really beneficial.

Similarly, would 2 or 3 intensity sessions be better a week. And how much Z2 do I need to make the right progression?

FTP = power you can hold between 30 - 70 min in a rested state coming in. It is both physiological and psychological. That’s where the “functional” part is key.

30 - 70 min is maybe a little loose, but I’m confident on two things:

  1. a nontrivial number of TR users, and cyclists in general, cannot hold their ramp test result power for 30 min in a semi-rested state.

  2. the difference in the power a person can hold for 30 min is pretty close to what one can hold for 45 to 60 min. It is the motivation part that gets hard the longer you go.

Would I rather do a ramp test or 30 min all out effort to set training levels? Ramp test all the way. But it doesn’t do me any good if I jump into too hard a threshold workout because I misunderstand what the score on ramp actually means.

1 Like