In my experience, Copilot does a fairly good job when you already know what you’re doing, but can’t be bothered to write the code yourself.

For example, basic stuff like read data from that file, use dplyr, remove these columns, do these calculations, plot the result using ggplot2, label the axes this way, use those colors etc. Copilot gives you the code that does roughly what you want, but you usually need to tweak it a bit it to suit your preferences. Copilot also makes absurd mistakes, but fixing them is fairly easy. If this is the sort of stuff you’re doing, copilot can indeed boost your productivity.

However, if you don’t know how to do something a bit more exotic like principal component analysis, and you ask copilot to do the job for you, expect plenty of trouble. You may end up on a wild goose chase, using the wrong tools, doing unnecessary calculations and all sorts of crazy nonsense. When you know what you’re doing, you can ask a very specific thing. When you don’t, you may end up being too ambiguous in your prompt, which will result copilot leading you down the wrong path.

You can do it this way too, but before implementing a single line of that garbage code, you absolutely have to ask copilot a bunch of questions just to make sure you really understand what you’re doing, what the new functions do, where do you really want to go etc. You’re probably going to have to tweak the code before running it, and that’s why you need to know what you’re doing. That’s the one big area you can’t outsource to copilot just yet.

But is it still faster than reading the documentation and building your own experimental tests? If you spend an hour and get a pile of broken garbage, then certainly not. If you spend a bit more, ask plenty of questions, make sure you know what you’re doing, then maybe it is worth it.

I firmly believe that every system has exploits. The more complex the system, the harder it can be cheesed.

So, if you show it 100 faces from group A and 4 faces from group B, that could start gradually shifting the prices in a specific direction. If you keep going, you might be able to make it do something funny like charging 0.1 € for a Pepsi and 1000 € for a Coke or something like that. If the devs saw that coming, they might have set some limits so that the price can's spiral totally out of control.

When you use a generated face with a mixture of white and black features, that’s when it gets interesting. Maybe you can even cause an integer overflow.

When you start tinkering with a machine learning model of any kind, you’re probably going to find some interesting edge cases the model can’t handle correctly. Maybe there’s a specific face that has an unexpected effect on the device. What if you could find a way to cheese a discount out of it or something?

Wisdom of the ancients, from the late Flash era.

I’ve tried a bunch of different ad blockers on iOS, but recently I finally settled on using NextDNS. I installed the app, made an account on the website, added a whole bunch of block lists to my settings and now it works on browsers and games alike. I suppose on of the lists also filters out those autoplay videos since it didn’t play in my case. Feels a lot like having a pi-hole no matter which network I’m using.

Where do you draw the line between made up words and non-made up words? It’s not like a supernova explosion creates new words that land on a forming planet so that a billion years later a new sentient species can just pick them up from the ground and start using them.

I’ve seen some of the impressive pixel artworks people have made in Excel. However, I prefer to do Excel art by writing a bunch of wild functions and drawing a stacked line chart from the resulting data. The graph itself is the artwork, while the cells behind it are just a necessary part of the process.

But if you want to put a some text and pictures in very specific locations and never worry about them suddenly jumping into random places, Excel is actually better than Word. That’s why people tend to use Excel for all sorts of weird purposes like that. Unlike with Word, things actually stay where you put them.

Maybe the goal was to weed out all the humans and let the bots in. When they start asking TCP questions written in binary, you’ll know for sure.

Ever tried to see what happens when you request “an anatomical diagram of a spider, school book style”. I mean, just start by counting the legs, and once you’ve stopped laughing you can dive into the labels. It’s going to be wild. If you’re into microbiology, try asking for a similar diagram of a prokaryotic cell for extra giggles.