- 50 chats
- 2.000 code completions
per month.
After that it is starting from 10$/month.
321–330 of 412 posts
- 50 chats
- 2.000 code completions
per month.
After that it is starting from 10$/month.
The real cost is that society at large is no longer contributing to the StackOverflow, so problems and solutions are all now stored in proprietary databases (which granted SO also was) but also now stored in an invisible proprietary database
The situation at large is even worse if you consider how Discord moved a significant portion of discussion away from the indexable Web. I thought of mailing lists as archaic, but maybe we just regressed from there.
Earlier quoted context omitted.
But Copilot does exactly the same? You don't need to prompt anything.
No, Copilot is just dumb, for example, I have the following code: func(a, b, 1) func(b, c, 1) and, say, for some reason I need to swap the order so the first line looks like func(1, a, b). After doing that, without even moving to the second line, Cursor just suggests changing the second line to func(1, b, c). You just can't make Copilot do this. Even after you move to the second line, it won't suggest anything. It ju…
Earlier quoted context omitted.
looks like the parent comment hints at https://docs.continue.dev/chat/model-setup#local-offline-exp... (Assuming your computer has the specs necessary to run ollama)
That page is about chat while the parent comment seems to be about completions, that's the codepilot feature most of us will be looking to replace/improve on.
Earlier quoted context omitted.
Looks nice but if it phones home then my boss won't let me use it.
If you pay for the "Business" license, then you get some guarantees about privacy + security. It was a fight, but we eventually got the go-ahead from our legal team and are able to use it. It's pretty nice.
Could this be a strategy to get access to more code than what is available in just Github? More training data means better models I assume.
I just enabled copilot and I see in the settings this is checked by default https://github.com/settings/copilot > - [x] Allow GitHub to use my code snippets from the code editor for product improvements > > Allow GitHub, its affiliates and third parties to use my code snippets to research and improve GitHub Copilot suggestions, related models and product features. More information in About GitHub Copilot privacy. Sho…
People opt out, some PM or whoever decides they need 'metrics' (numbers to spin)... and more categories or qualifications are summarily added. Starting the cycle again.
I assume they'll send a privacy policy update in at most six months. I wouldn't call it concerning. Routine. I won't participate, that's for sure.
Earlier quoted context omitted.
1. I believe AI is detrimental. It makes us go too fast. It's all about production now, pure efficiency over individuals. 2. AI is too dangerous. Whatever innovations used for benign applications will be eventually used for more dangerous applications such as advanced genetic engineering and the military. 3. AI uses too much energy. It's disrespectful to the resources that we have. 4. AI is an apex technology amongst…
AI is a technology that, in principle, makes it possible to have a "Star Trek communism" society. I agree with you that it can also be abused to make the existing state of affairs even worse. But if we resist technical progress on this basis, we'll never get better, either.
Microsoft giving away a losing product for free is the exact kind of thing that proves they’re too big. This is just a desperate move to suck oxygen away from startups in this same space that compete with them. We need new antitrust laws ASAP.
Hilarious. The code "fix" Copilot suggests in their example[1] is wrong on some many levels. It's trying to use await in something that is not an async function. From the other examples it's clear this is likely React's useEffect. You could not even make that callback an async function if you wanted to - this naive fix for that leads to subtle bugs. And last but not least: The issue here - if there's any - can alread…
Earlier quoted context omitted.
Can you give some examples? I spend the majority of my time reading code nowadays, and I often have like 8 or more Sublime Text windows open (each open on a separate codebase). I cant imagine how much RAM it would take to do that in CLion or Visual Studio. Sublime Text's text search is the killer feature for me. CTRL+SHIFT+F and I can search a million LOC+ codebase instantly, navigate the results with CTRL+R, do a su…
Are you joking about the 8 editors? I have a laptop I bought 10 years ago. It only has 16 gig of RAM [1]. I have had 8+ editors open, mix of visual studio and vs codes. And in VS you often group all your codebases into single solutions. So usually have multiple windows from multiple projects open in each ide. It only struggles when I leave the debuggers running several days because of a slight (known) memory leak in…