A lot of users aren’t happy that they can’t manually intervene for even the simplest of household appliances.
That my “other” bubble is still large after two years of having Sense on is a failing of the product.
Thanks so much. Glad to see that you’re able to get things modeled for you, but because my wife drives a Ford C-Max Energi and not a Tesla or a hybrid BMW, I don’t have a similar experience.
@jaquesbluett,
If you are looking for some technical insights on this forum:
- Your identification challenges are far more likely to be due to “noisy” electronic devices in your house, your wiring structure or just some difficult to detect devices, rather than the kind of car your wife drives (even though it is an EV).
- I understand your frustration, but Sense has posted numerous explanations on why “user training” for initial identification isn’t a viable approach.
Hoping you’ll see better soon.
1 Like
Thanks for your insight, kevin1. I’m well-versed in your reportage and support of this product. I have read the articles that you’ve posted. I’m sorry if my beating the same old drum, which is the algorithm based modeling approach to Sense detecting stuff rather than allowing any user input is an old one. But will I relent? Probably not.
If this product doesn’t work well for an older home wired in 1978, shouldn’t that be mentioned in the sales pitch for a $300 product?
“I’m hoping you’ll see better soon,” is a phrase born out of either words of encouragement or psychological aggression. I’ll choose the former and thank you for the tip.
I’m not trying to be a jerk here, Ryan. I’m simply frustrated that this product isn’t performing as advertised. Thanks for offering some help for me. The customer support team has been helpful.
1 Like
This neither offers help nor solves my issue.
That my main two energy consumers, those being my wife’s car and my HVAC aren’t modeled, is a source of concern for me. It’s super great to know when the vacuum or coffee grinder is on, but that isn’t terribly helpful.
@jaquesbluett,
No aggression here - I want to see things work well for you (and I want my other 3 EVs to show up as well). But I kind of see Sense going down the right path, when viewed from a machine learning perspective to enhance their training, but it’s not exactly a manual approach. The Hue integration gives a good picture of what can be done. I imagine you are going to see similar benefits for your HVAC in the future if you have a smart thermostat.
As for EVs, I’m taking Sense at their word that they are working on the machine learning framework germane to EVs
2 Likes
Sense is far from a perfect solution. Some have better success than others. It has not solved all of my devices. I have a Chevy Volt that has not been discovered and the pump to my two stage geothermal water furnace that is missing. I am able to use the product daily though and am overall pleased with the value that I am getting. Not trying to project that on to others that are struggling.
As for helping, the common thread that I see from some are fighting the design. I coded in SCO UNIX in the 80s before we had internet. I found myself programming for Ford in Geelong Australia and frustrated when I could not produce the results I needed. It was then that I learned not to fight it but to use the product as it was designed. The team at SCO was not going to change their structure for me. Now Sense is not as far along but have been very clear on user training. Additionally, their tech support is very consistent in their response and make no promises to me on a time table for discovering my Volt. I have found workarounds with the solar output on my EVSE combined with my smart Myenrgi Zappi EVSE.
My initial comment on this thread was trying to aid the poster thinking they were only online for a couple days. I later apologized when they clarified that was not the case. My “help” to those wishing for user training is to explain that is extremely unlikely. That is not an attack, it is an attempt to help by explaining how Sense does and does not work. One of the most common mistakes is to start unplugging devices thinking that will help. It is exactly the opposite of what Sense needs. I am a six month user and I use the app every day, multiple times per day usually.
Initially I thought Sense was taking too long to discover devices until I better understood their approach. I know by this forum that many feel their expectations are not what they expected while others are elated. I have wondered how Sense should change their advertising to better depict the progress of their product for those that are missing particularly large devices? Maybe your best input is writing that up since you have a first hand experience? I really don’t have that answer but respect the feeling as valid.
1 Like
I fully understand where you are coming from. I’d rather work with the product than get mad online with fellow users. I fully get that we’ll never have user input and the old unplug and plug back in IT fix only fouls the Sense up further while it learns. I just want it to learn better, faster, longer. The Sense team has worked with me on this even when my suggestions have been, shall I say, ticked off and aggressive.
1 Like
My frustration stems from being able to see these devices cycle on and off real time and Sense not learning them. My desire for real time input might not align with company goals, but as a physics major, not being able to cycle on/cycle off a product in order to identify a thing remains frustrating.
Some better use of a rabid customer based library and the algorithm you’re using seems ideal for those of us not willing to sit on our hands.
Definitely don’t think you’re being a jerk here. We totally appreciate the critical feedback. We’re just dealing with a much harder problem than can be succinctly handled with a “it won’t work in homes built before 1980.” Because it might work great in a home from the 30s and poorly in a home built last year. ML-based device detection is just far more complex than that and is based on too many variables to have such a simple disclaimer. Similarly, this is why manual intervention just isn’t all that feasible. We’re not just identifying some pure device signature, tossing that in a database, and then letting your Sense monitor compare what’s happening in your home to those pristine signatures. That’s certainly part of the process, but your devices rarely ever look exactly the same across instances. I joked earlier with a user that we could certainly create a training process as long as they’re OK with us not covering their carpal tunnel surgery…because that’s what it would be. Sense needs a lot more data, and a lot more specific data, than you might imagine. There’s a world of difference between you/me/our data scientists recognizing something in the Power Meter as a particular device and Sense recognizing that same signature on its own, at different times and in different contexts, and doing that consistently. When you look at the Power Meter, you’re only seeing a small window into what’s really happening in your home (it updates at .5s intervals, we pull data 1 million times every second).
I think it’s always worth keeping in mind that this tech is on the bleeding edge. We’re really in new territory here. On top of that, we’re still a teeny company and Sense is only about two years old. We’re young! We have improved drastically since 2016 and will continue to improve. We also offer a 60-day return period, no questions asked. For most users, that should be enough time to know if Sense is going to work out for them.
This thread has gone way off the rails so, in fairness to @mrtimo, I’m going to request that any talk about training Sense be moved to We should be able to TRAIN this!
2 Likes
So, what’s the result of your discussions?
Fair enough. Sorry for the unpleaseant tyrant cry on my part. If I’m guilty of a thing, it’s not understanding that this is, indeed, a bleeding edge product and when it doesn’t work immediately, I get a little bit cranky about that spending money on what a product is v. what my expectation is. I’m sorry that my user feedback has bled over into bad terra, as I like your product and I see the capability and I merely want it to work as advertised. I’ve had a similar experience with non-commercial fenestration and I’m going to float this as a me issue, not a your product issue, as I get how things roll and sometimes the ramp-up occurs ahead of the realization. Sometimes the product that I want never makes it that far for another five years. For that, I’m sorry as I know you’re actively working on it and I want to help you to get there in a more positive way.
3 Likes
I appreciate it, Jacques. Definitely don’t stop posting! We really do like the critical feedback. It’s helpful to hear. It’s just wise to keep in mind that experience with Sense really can vary significantly across homes, so the experience of one user can be drastically different than other user. Indeed, that is somewhat the nature of the beast here (we can’t control the quality of power entering your home), but perhaps we can revise some of our language to better attend to that.
3 Likes
If I need to direct my holler at my electric provider or need to re-wire my home, those are viable options and not your product’s fault. So long as I understand that, I can make it to step two.
1 Like
This topic was automatically closed 365 days after the last reply. New replies are no longer allowed.