This looks very useful! I wonder how other AI coding tools manage merging work from different agents (I've never tried running multiple agents simultaneously yet, but I was thinking about that).
I made this blog post, because I did very little fudging and was shocked by how good the results are. However, this only happened with the latest model (o3). That's why I wanted to describe my approach. First, give AI the model / architecture description, and make sure it understands. Then proceed to the code.
I am sorry for not making a long blog post with all the details, I just wanted to highlight how the cooperation with AI went to the next level (model design, then implementation). At least I posted the code :) It's just a mock up, and the model will evolve, so the architecture of it is not the important part.
There is definitely a ceiling problem. However, I found that with smarter models (such as o3) you could first discuss the mathematical model (or system architecture), so that it knows the context. After that you can ask it to write code, and then it can follow your overall idea very well. Even write a working ML algorithm with fitting. That's why I made the blog post, because I was able to achieve the next level of collaboration with o3. It almost shocks me how good is this. Since the blog post, I've made significant advances in other work-related areas (ML algos for finance).
I thought that the full details might not be interesting for people, since the algorithm is just a mock up of the idea, but which already works! If I wrote the whole post about all the details, it would be very long. I can see how it's a bit out of context, because other parts of the algorithm are not described. But at least I uploaded it to github :)
Great idea. I've read some people's comments. There are a lot of companies in the UK that sell their equipment, and use contractors to install them (Worcester Bosch for boilers, even Tesla uses external contractors to install the chargers). I think you can do it. There was a heat pump company with similar approach in the UK that went bust recently, so maybe research what they did wrong.
This seems certainly possible. But I don't know how would you display all of the frequencies that are present in music at the same time. Usually, they only play one or two frequencies and look at the result. Mash them all together? Maybe can be tried in the future. I was thinking to do something "inspired by" this cymatics instead (when I get around to it). Thanks for all the interesting thoughts!!
Hi! Thanks for your comment! It’s interesting. I don’t think there is any magic about cymatics per se: it depends on how sound interacts with physical objects, and these objects have certain resonant frequencies, which is when the start to vibrate “interestingly”. I like it as a potential visualisation idea though!
These are very interesting thoughts, they remind me of when I’m deeply thinking about how a track/song is represented in my mind and trying to visualise it. (With the exception of red being a “do” note, I think because I’m red-green colourblind). Sometimes I’m drawing to try to imagine much more complex visualisations that leave imprints of past music that then get activated again. At this stage it’s more like dreaming than actual possibility that I could already implement. But it’s nice to dream. I agree about society... That’s why I did this app in my free time off work. I could only spend 1 hour per every 2 days on it. Imagine the possibilities if I (and other people) had more time for creative work...
I’ve actually wanted to make this in Unity! But they don’t provide (reasonably useful) access to real-time data from microphone! I’ve also been contacted by a recruiter from them by accident, so I’ve sent them my feedback about this :) I’m sure they won’t forward it to devs. Maybe I should try to make some plugin for Unity that would “move to” the music that developer loads into the game, that’s not a bad idea! Thank you!