Solution: don’t read that shitrag. It was always a waste of paper, now it is a waste of bandwidth as well.

I’ve tried Copilot and to be honest, most of the time it’s a coin toss, even for short snippets. In one scenario it might try to autocomplete a unit test I’m writing and get it pretty much spot on, but it’s also equally likely to spit out complete garbage that won’t even compile, never mind being semantically correct.

To have any chance of producing decent output, even for quite simple tasks, you will need to give an LLM an extremely specific prompt, detailing the precise behaviour you want and what the code should do in each scenario, including failure cases (hmm…there used to be a term for this…)

Even then, there are no guarantees it won’t just spit out hallucinated nonsense. And for larger, enterprise scale applications? Forget it.

Doesn’t need to be a “green energy paradise”, just a reasonably well connected first world country.

Take a look at Electricity Maps. Unless you live somewhere isolated or with very poorly developed grid infrastructure (or some central US states, apparently), you should see a non-trivial amount of electricity being generated by non-fossil fuels. For example, at the time of typing this 77% of the electricity I’m using is low-carbon and 50% of it is renewable.

That’s the kicker. EVs don’t have to rely on fossil fuels to operate (but they can make use of them depending on the grid infrastructure). ICE cars on the other hand are burning fuel wherever they go.

Walking or cycling will always be the least polluting means of getting around, but if you really need a car then you could do a lot worse than getting an electric one.