Workouts on Wahoo worked for me after yesterdays update on my Bolt.
Oh really! So you did a ride associated with a TR workout, completed it and was there a survey after?
The ML;AI experts can opine, but I will bet that feeding AT outdoor data is going to be difficult. Outdoor data will be noisy and expect will need significant cleaning to make useable. Based on my experience with other ML;AI applications, if the models / systems were not trained well using outdoor data, the models will struggle with introducing that information. It may not be as easy to incorporate as we want it to be.
If I were trying to test AT for my own use, to judge if it was ready to use as a training tool in my toolkit, I would take every effort to feed it extremely clean and high quality data. Meaning I would do a TR plan, at least 6 weeks, performing each workout exactly as prescribed. I would also do all the key workouts indoors, same trainer environment and power meter. Else it seems like GIGO is a high probability outcome.
Since we all like learning stuff, here is a very recent review of AI expectations and realities making the rounds of my shop: [2104.12871] Why AI is Harder Than We Think It is written in an approachable fashion using examples many of us will find relevant.
Full disclosure, I am not in the bike industry, but am in an industry which uses ML;AI a great deal, with very large investments, and where we have high hopes and dreams. So far, some applications have been brilliant, others utterly frustrating.
No matter current status of AI - I commend TR for taking this route and trying to make it work.
I’m not on AT beta
In the past week or so of outdoor TR workouts, I have been able to fill out surveys. It doesn’t prompt you to do so, but when you visit the desktop site, it will show you have a Missing Survey in the Recent Workouts box in the bottom right of the career page. If you click that, it will take you to the workout page and pop up the survey to fill out.
I had mentioned that the surveys were working for me (albeit without a prompt to fill them out) to the support email, and they said that they do appear to be working, but that they aren’t yet contributing to progression levels. So the mechanics work, but the outcome isn’t yet correct.
Ah! You had me excited the bug was fixed. I’m referring to AT not recognizing outdoor workouts when using a wahoo, which is all my training.
Thanks for checking in with the team! We’re investigating a small group of cases where surveys aren’t saving properly and will update known issues if these arent edge cases. Cheers!
Progression levels? Can someone in AT please tell me the progression levels for:
- Baird+2
- Bashful+2
- Bashful +6
- Dade+1
- AnselAdams -2
- Matthes +1
- Taylor
- Gabb
- Williamson+2
Thanks
- Baird+2. 6.6
- Bashful+2. 7.6
- Bashful +6. 6.9
- Dade+1. 6.8
- AnselAdams -2. 6.4
- Matthes +1. 6.8
- Taylor. 3.4
- Gabb. 9.1. Anaerobic
- Williamson+2
Where or how do you see the secondary Progressions?
If a completed workout progresses any of your levels besides the primary, it’ll show you that section. It doesn’t happen on every workout.
FWIW the issue we were discussing seems to be fixed now:
Very nice post. I have been following Melanie’s work on analogies for years now. A decade ago I even met her PhD supervisor, Douglas Hofstadter during a dinner.
Working myself on AI (well, Computational Linguistics using ML) I can assure you that it will take some time before we have something meaningful from TR. It seems to me that the backbone should be fatigue modeling, but I might be wrong. In any case, self coaching will probably be with us for some time, although tools like adaptive training could somehow be of help.
Brill, thanks @ValeCyclist
new vlog, woke up today and saw pending adaptations to SSB2 HV that is starting today, just quickly walked through each week showing which workouts are changing. Last weekend of SSB2 will have me doing 9.1 and 10 level workouts, so that should be fun lol
Should note that I have a playlist of all my other vlogs, I think a lot of people watch one or two and might miss the entire context, none of these are really intended to exist as a standalone and are meant to highlight an evolving process, which AT is all about
Wasn’t the issue with reductions rather than increases? I’ve had multi zone increases in the past with no issues.
Apologies if this has already been mentioned in this gargantuan thread and I missed it, but one of the things I’m really liking about AT so far is that it’s leading me much deeper into the workout catalog. This keeps things a lot more interesting. Now if I could just get the workout to adapt on-the-fly…
I’ve thought a lot about on-the-fly adaptation as the next level of “intelligence” in workouts. I fear there are some days that I would attempt to destroy any computer that made me suffer more than expected on the fly…but built-in sandbag protection might actually be a good thing.
Original:
I see what you mean now. They have modified / hidden those numbers on the original ride for you.
AT has figured out my VO2max is lower on Tuesdays, and higher on Thursdays… 
