voldemort1968

These kinds of features are like solutions looking for problems. Is this a real problem people have, that they are getting everything done but they can't figure out what to do enough that they'll write out the whole thing to get suggested tasks?

> it’s enough to just say that catchphrase and not even bother looking into it. The argument wins itself.

And that is why it's thought suppression.

People think this kind of logic is an example of thinking, but it's actually thought suppression.

Lol, when I read remote jobs, I was thinking this was going to email me queued sidekiq tasks as they were picked up. I need to take a break from the keyboard.

I want to like ideas like this but it's been done before and rarely gains traction for most users.

We've seen this with smart notebooks that let you write with either a smart pen or a smart pad and immediately digitize and OCR. We also already have most of this today on our phones via built-in text scanning with OCR and the ability to easily copy and paste into any blogging application of your choosing.

I don't know if there's really enough efficiencies to be gained here, especially any that overcome the lock in required to use this product.

Yes, if you use copilot irresponsibly, you will end up with irresponsible code.

In other words they didn't roll their own.

Most of the arguments here boil down to the same belabored point, that you shouldn't expect Copilot to actually write the code for you at the end of the day.

My take is it's what you make of it. Copilot is only equivalent to copy-and-pasting from stack overflow if that's how you choose to field its suggestions.

As an example, I've enjoyed typing "const one_day_in_ms" and letting it finish it out with "1000 * 24 * 60 * 60". I already knew how to do that, but having GCP finish it for me and verifying on my own didn't make me feel stupider, it made me more efficient. I have more interesting problems to tackle.

On the other hand, another coder could have not known this calculation and thrown their trust into GCP. That's bad practice and it's on them, not on the tool.

Sometimes GCP gives me code that it learned from bad coding patterns. I know how GCP works and I know to look out for that, so I ignore those suggestions.

Of course, sometimes I don't know if what looks like a good idea from GCP is actually not. I take that on as my responsibility to trust but verify. If it's writing some function to slugify a string for a URL, I check it against what people are discussing online. Does it defeat the purpose of GCP in this case if I have to check it on my own? Probably, but it's only in these specific instances when I'm doing something I'm not familiar with.

Put another way, 2 of the 36 AI systems evaluated were more/as accurate than a single radiologist.