541–550 of 796 posts
The main page [0] shows you awesome demos, but also its weaknesses in the very first example. It doesn't encode the url encoded body properly: > body: `text=${text}`, So it breaks if the text contains a '&' and even allows parameter injection to the call of the 3rd party service. Isn't that critical on a sentiment analysis API, but could result in actual security holes. I hope the users won't blindly use the generate…
Earlier quoted context omitted.
I wholeheartedly agree with your analysis, but feel like it’s ignoring the elephant in the room: writing code is not the bottleneck in need of optimization. Conceiving the solution is. Any time “saved” through Copilot and it’s ilk is immediately nullified by having to check it’s correctness. From there, the problem is worsened by the Frankensteinesque stitching together of disparate parts that you describe. I can’t i…
> I wholeheartedly agree with your analysis, but feel like it’s ignoring the elephant in the room: writing code is not the bottleneck in need of optimization. Conceiving the solution is. I dunno about this. I know the received wisdom is that "writing the code isn't the hard part", but I think reality is more like "writing the code is only one of the hard parts". There's an awful lot of badly-written code, or code whi…
I've been using Copilot non-stop on every hobby project I have ever since they've let me in (2021/07/13) and I am honestly flabbergasted they think it's worth 10$/mo. My experience using it till this day is the following: - It's an amazing all-rounder autocomplete for most boilerplate code. Generally anything that someone who's spent 5 minutes reading the code can do, Copilot can do just as well. - It's terrible if y…
"how to put a sentence together describing the rules, it absolutely doesn't actually understand how "Chii" melds work" The more experience I get with GPT-3 type technologies, the more I would never let them near my code. It wasn't an intent of the technology per se, but it has proved to be very good at producing superficially appealing output that can stand up not only to a quick scan, but to a moderately deep readin…
random words ---> markov models ---> transformer ---> human writer
It's just a room of monkeys banging on typewriters at the end of the day.
Earlier quoted context omitted.
Probably not exactly what you're looking for, but Warp (a new terminal client) has "AI Code Search" built in that's powered by GPT-3. Quite useful for someone like me who tends to avoid the terminal when I can. https://www.warp.dev https://docs.warp.dev/features/ai-command-search
There's this cool blog on them testing it out against popular git commands: https://www.warp.dev/blog/replace-git-cheat-sheet-ai-command...
Like many people I thought Copilot was neat but ended up uninstalling it because it caused more problems than it solved. Reading the comments here, it seems that most of the people who get value out of it would be better served creating a set of snippets. If all you need is to fill in boilerplate all the time or repeat general test structures but with different arguments, just make a snippet. Every major code editor…
Or better yet, save the snippet as a function/procedure in the code, and avoid needless duplication (DRY/Occam's razor).
I was excited when it came out, but it ran slowly and annoyingly (crashes) and I gave up.
I already have a jetbrains license; when they release a similar feature I’ll consider uping my subscription to get it.
As it stands… eh. It’s not that great. I couldn’t really be bothering to continue using it for free, I’m not gonna pay for it.
I've been using Copilot for a few months and... Yeah, it makes mistakes, sometimes it shows you i.e. the most common way to do something, even if that way has a bug in it. Yes, sometimes it writes a complete blunder. And yes again, sometimes there are very subtle logical mistakes in the code it proposes. But overall? It's been *great*! Definitely worth the 10 bucks a month (especially with a developer salary). :inser…
I find I spend my time reviewing Copilot suggestions (which are mostly wrong) rather than thinking about code and actually doing the work.
Do people want to see ads instead?
Or would they be ok paying for Google search (another service trained by all the information we willingly volunteer to them)?
Copilot adds tremendous value and they are justified charging for it.
What's the criteria for being considered "a maintainer of a popular open source project"? They never actually publish the criteria anywhere from what I can tell. They just say visit the subscription page and if you are eligible it should be available to you and if you see a charge then you are not eligible. I think though they should still be transparent about what their metric is for determining popular projects on…
At a minimum, 4.3k stars is not enough, because I don't qualify.