They may not understand it but they may very well be able to reproduce aspects of feedback and comments on similar pieces of software.
I agree that the approach shouldn’t be done unsupervised but I can imagine it being useful to gain valuable insights for improving the product before real users even interact with it.
> reproduce aspects of feedback and comments on similar pieces of software
But this is completely worthless or even misleading. There is zero value in this kind of "feedback". It will produce nonsense which sounds believable. You need to talk to real users of your software.
Letting the LLM generate use cases is probably not a good idea. But writing common use cases and having a bot crawl your app and then write up how many steps it took to accomplish the goal is a good idea that I hadn't thought of before. You could even set it up as a CI check to make sure that new features that introduce more steps for specific flows are very conscious decisions. In a large application this could be a very useful feature.
Looks like a really nice project! Would love the ability to „subscribe“ to a place or area and get a mail or notification once there is a new book added for that location. Another nice addition would be a heatmap layer for the lower zoom levels.
Working on updating my Your-Age-in-Days app[1] for iOS 26. The main motivation was to have the days I've lived always available on the lock screen with a more native feel than the workaround I had before (nightly Shortcut which updates the background image and adds the current number as an overlay to it).
Does this happen at a specific time of day (e.g., start/end of shift) or randomly? The quickest way would be to wear ANC headphones during the most noisy times. Then, if possible and allowed, you could look into soundproofing your windows. Maybe reach out to the garage owner as well and tell them about your situation.
Quick heads-up: I clicked through several links on your blog and website (Integrations, Guide, API) and they don’t seem to go anywhere specific yet, or just link back to the top of the page. This makes it harder to evaluate and find out more about your product.
Thanks for the heads-up! You caught me—I’ve been hyper-focused on shipping the core application logic (the actual tools), so some of the secondary documentation and API pages are still placeholders or "coming soon."
As a solo founder, I had to prioritize the engine over the brochureware, but I realize that makes navigation frustrating. I’m deploying a fix tonight to either active those routes or clearly label them as "Roadmap" so it’s not a dead click.
The actual app and the tools mentioned are fully live at vect.pro if you want to test the functionality directly. Appreciate you taking the time to click around!
I have circled back to using the apps that are already on my phone, especially the Apple Reminders app which I am currently trying out as my main notes and ideas system.
I have placed it as one of the two bottom widgets on the lock screen which gives me immediate access to everything I need to capture a thought: a main note, the list where I want to store it (e.g., work or personal), the notes field if more context is needed, and I can flag it or schedule a reminder. The app then also has an optional auto-categorize feature which works quite well. Add to that reliable sync across devices and except for a good way to bulk export lists, this has everything I want from a quick draft and capture system.
Currently building something like this for my city. One major challenge I've come across so far is that most APIs will give you coordinates for an address of a place within a building but none of the free, paid or crowdsourced options have reliable information on outside seating polygons. Of course, you could always display the places around you with live shadow data on a map, leaving it up to the user to zoom in and decide based on the satellite image whether the restaurant or café offers outside seating. But to plot the route and then suggest nearby sun/shadow seating options to the user, you would need this information.
You'd need stereo fotos from a low flying plane for this. Several cities are doing this for decades already. I've built such a 3D map for my city like 25 years ago.
Are you referring to the outside seating polygons? Wouldn’t these stereo images still have a lot of noise (trees, cars, trucks, smaller non-building structures) obstructing the target areas?
It’s likely a mix of availability bias and pattern-seeking/apophenia: a few recent outages stand out and the rise of LLMs in recent years is also ever present. This increases the chance to assume a link between both even without evidence that outage frequency actually changed.
Also, I don’t think the switch is as binary: these industry shifts tend to be more gradual where more experienced programmers adopt LLM tools to suit their workflow and newer developers still learn fundamentals because real-world engineering of complex systems quickly exposes a lack of understanding.
This seems to be the article's author's own language Bauble[1], "a toy for composing signed distance functions in a high-level language (Janet), compiling them to GLSL, and rendering them via WebGL"[2].
reply