- cross-posted to:
- fucksubscriptions
- cross-posted to:
- fucksubscriptions
You must log in or register to comment.
Today, I actually disabled copilot in vs code. Yes its impressive at first and sometimes it does save you some typing.
But you’ll have to review everything it suggests, and sometimes it will suggest a lot. It’s okay code maybe 20% of the time. The rest of the time it’s either just doing regular completion, copying and pasting my own code from a few lines up, or just generating gibberish.
Often it will generate things that look okay on first glance, but a deeper look shows significant issues with what it created. Which is a problem often enough that it means you have to deeply look at everything.
I’ve even had it generate code with typos in it…
It’s really not worth the money, your job just changes from person that types something, to person that reviews the robots crap.
I’ve noticed the same thing with ChatGPT when I ask it to write some code. On first glance, it seems awesome and like it solved your question with ease. However, when you try to go forward and use it, or just look a bit more closely, you realize it has used classes or functions that don’t exist in the library it imports and it made up something. Or, it’s just wrong and not solving the question. This seems fine, but if you go three or four rounds trying to correct it with prompts, and it still gets it wrong, you start to look for other answers.
It’s often helpful for getting headed in the right direction and it has saved me some time, but it doesn’t write flawless code. It needs to be reviewed and corrected by a human.
Dude same. Normal autocomplete is short and has a low mental overhead but high payoff in time saving from tying. I lasted about 20 min testing copilot before canceling my trial. It slowed me down so much because as you said it generates such large snippets and you have to scan each one to see if it’s useful. Also the constantly flickering of big code blocks changing was super distracting.
I’ve used GPT4 directly for code stuff before and it’s been useful for certain use cases but I find Copilot to be worse than useless in that it not only didn’t really help me it slowed me down and distracted me so much it was a detriment to my coding process.
Maybe Copilot X will change that since it’s basically embedded GPT4 I think, but regular Copilot? Totally worthless IMO
36$ per person per month is high considering GitHub copilot is 19$ per person per month.
I would think this would be how Microsoft gets people to switch off Google’s platform but with that price point it’s not convincing anyone. I suppose if it saves an employee one/two hours a month it’ll be valuable for the company.
Oh no, I have to pay for clippy 2.0? Shucks, i guess I won’t use it then.
For light users, $36/mo is very expensive. However, for middle and upper management types that live, breathe, and eat PowerPoint, this is huge. If this is good enough to allow non-technical people to connect to their BI and generate charts and reports without the need of IT, it will be incredibly cheap to them. There’s a whole cottage industry of consultants for small business who do these sorts of things so having this automated will save time and cost for these businesses.
As a developer, I’m still interested in seeing what CoPilot integrated in my development environment will be able to do. My company is currently paying for ChatGPT+ at $20/mo for me. At my salary, it’s a no brainer since even an hour a month is a huge ROI. However, it’s quite manual since I have to copy paste everything. If I can get ChatGPT 4 with the full context of my project, $36/mom is a no brainer. If we can get a private version that is trained on our company code base, it will be a game changer.
If this is good enough to allow non-technical people to connect to their BI and generate charts and reports without the need of IT
Big if imo. I can see it getting there within a half decade at the rate this technology is evolving, but today? No fucking way.
Bigger likelihood that motivated (previously) nontechnical middle managers can learn to automate reports themselves with a lot of handholding from AI though, if this is actually as good as GPT4 was at launch though.
