Building a no-code toxicity classifier by talking to GitHub Copilot

On the other hand, most code is read more often than it is written, and those comments are very readable!

Just to clarify, it's not really no-code: pseudocode is the new bytecode it would seem and this is just compiling that into usable code.

You still need to be able to code and understand what you're doing. You can't just ask simple questions and get complex answers. You still have to be capable of asking complex questions.

A common scenario I can think if is where I struggle to remember the name or API of the exact thing I want to do but I know exactly how it works - typing that in and getting a result would improve my workflow, but it's just saving a trip to Google, we're not talking the difference between doing and not doing, just a saving a minute.

I would rate the value of this more as interesting rather than useful, simply because as another commenter highlighted it's just easier to write code. It could be useful incrementally but not for everything.

Please add "No-Code" and "Toxicity Classifier" to your toxicity dataset.

I don't really understand this. You're not coding directly in the language, but now you're coding in an implicit language provided by Copilot. From what I've seen on Copilot, although it is an impressive piece of tech, all it really points out is that code documentation and discovery is terrible. But I'm not for sure writing implicit code in comments is really a better approach than seeking ways to make discovery of language and library features more discoverable.

And I know it sounds silly and like "I had an idea like that once" (see Office Space), but I actually came up with the idea for or at least a similar one to Copilot in an off comment to a coworker back in like 2014 or so. The idea was that as you wrote code, it would display on the side similar code that had been written by others doing the same or similar thing, and then it would allow you automatically upload small processing functions to some sort of cloud library. Same thing for doing autoformatting, although that's less of a concern now that formatters are becoming popular. The context I was working in was visual languages though. I had even started writing a tool during an "innovation week" (that I never showed) that would start visually classifying whether code written in the visual language was "good" or "clean" or not. I never got anywhere with it and mainly just have some diagrams generated from that project that were buggy so that they kind of look like art.

I think you missed the forest for the trees. It isn't the model that matters, it's that copilot is building the classifier from intent (comments). It wouldn't matter if it was classifying flowers instead.