101–110 of 412 posts
Working with people who use this stuff a lot has made my current job just so so much harder in every way its astonishing. I used to solve problems with code, now I feel like hermeneut or dream analyzer: absent of human intention, codebases quickly become these weird piles of different idioms, even without considering the hallucinations (those have definitely cost me a few sleepless nights now either way). But I am ju…
Earlier quoted context omitted.
The actual killer feature for me is the much superior autocompletion, Cursor always suggests an edit inline once I stopped typing, without having me to type a prompt to ask it to do stuff. And it feels faster than GH Copilot, too. For us who prefer coding ourselves (instead of telling LLMs to do stuff and review the result) it is much much better.
But Copilot does exactly the same? You don't need to prompt anything.
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…
Thank you for your reply. I am currently having a ride with chatgpt allowing me to write applications at 3 times the speed compared to before (where before may be "never" for some technologies) and I am happy for everyone contributing to this. But all your points are well grounded, I will have to figure out a way to think about them, while keeping my day job.
So to give you the benefit of the doubt that you’re not just another dude who has hitched their financial wagon to this current AI slopfest, I just retried a question about writing OSSEC rules and the response, while convincing looking, was completely wrong. Again.
Is there some way to check what I currently use? I rarely use chat, so 50 per month probably wouldn't be an issue, but completion has become my main completion tool, not sure if I'd stay under 2000..
I ditched Copilot for Cursor and never looked back. Cursor might be the only other AI product with product market fit than ChatGPT, it's that good
Has anyone who uses an IDE (e.g., JetBrains, not a code editor) moved to Cursor? I've downloaded it a few times because everyone raves about it, but I've always come back almost immediately because editors can't reliably make changes across projects (among many other things)... What am I missing? FWIW I use GoLand w/ Supermaven, currently.
PS: One UI feature that I haven't seen anywhere yet is not splitting the screen into code and chat but unifying it.
Also a common approach (e.g. in openai composer) seems to be to modify the file line by line which takes a very long time if the file is long, which (agentic) tools use a diff approach instead?
I like the mediocrity of the example they headlined: the user asks for unit tests. Copilot writes only two test cases, so not exactly great coverage. Plus, the test cases uses python's unittest, which isn't as slick as pytest.
As for `pytest`, I just have to remind it I'm using pytest. "Write pytests for this" is sufficient to get it to do what I want.