Figure out how AI can help the blind and the deaf. Take up ceramics. Write a travel book. Tinker with low-cost robotics. Volunteer for some environmental restoration project - the riverbank ones seem interesting.
We have several processes which involve the upload of multiple different images, which the user is walked through with baby steps, I.e. 'take this exact picture of the asset' -> take the next, etc. Etc.
We're currently working on an image classification model to automatically tag these images with what they are and just providing a visual sample gallery of 'take these pictures' with the sample image border turning green when that type of image is identified. We expect this will reduce a multi-step error prone process with a more streamline experience.
You probably don't want to hear this but that problem doesn’t require AI to solve. We've had asset tags and QR codes for decades and won't require re-training if a new equipment manufacturer comes into play.
I very much want to hear this! The issue we're facing is that the maintenance staff is very undertrained on a specific subset of equipment. But that equipment is actually very critical. Also I was vague in the first post - in reality this is for hospitals within a system, not one single building.
When you say "won't require retraining if a new equipment manufacturer comes into play" I don't really follow.
Edit: I get it now - you mean by using QR we wouldn't need to retrain the image recognition AI. It's a good concern, although in this specific area there is not a ton of innovation or newcomers. Worth keeping in mind though.
The most modern idea seems to be a Dyson swarm, which is not solid and consists of solar panels and habitats orbiting at a comfortable distance. Power is relayed using microwave transmitters and receivers and conceptually a large portion would be fed into particle accelerators for the manufacture of Anti-Matter on industrial scale.
There doesn't seem to be any definitive data on the subject but I've had good success with [Context] + [Supplemental Information] + [Intent / Use of result] + [Format you would like the result in]
At the end of your answer there is "[Format you would like the result in]". Well, I'm curious what format you want the input (the sequence you presented) to be in.
I will also be happy if you can use the 2-space indentation formatting of HN (code block) to show a practical example.
>Often it'll be a case of "hey this table is actually searchable now" or "that page is now split into two" or "I removed a tonne of deprecated code"
Ah, how does that gel with regression testing? We've tried something similar but got swamped by the need to test those code changes and the testers got upset being lumped with additional work while the rest of the team got to play with whatever they liked. Did you forgo testing for the sake of morale or did you come up with another solution?
Idk how far we go into regressions, afaik we don't really have an issue with it... We have a "everybody owns the product" mentality, and so pretty much everyone on the team should know how to use it and where issues might arise or have arisen.
So each code change needs to be kinda demonstrated that it works, whether it's through new tests, or screenshots, video, etc.
Usually if there's a specific bug that's been fixed, there is a test to catch if that bug occurs again. Most of the time it's been good enough.
