• 0 Posts
  • 34 Comments
Joined 2 years ago
cake
Cake day: July 5th, 2024

help-circle











  • Yeah… So I read through that, and those aren’t the “pretty serious issues” you think they are.

    To be clear, they aren’t inconsequential, but they’re not “serious”.

    For example, complaining about the UX doesn’t equate to a security problem. A lower target for the Android API also doesn’t equate to security issues. It can be a contributing factor to security, but if your device can’t even install a lower API then that’s not an issue anyways.

    There are some valid points made by the author, but a lot of it is sabre rattling by making those points seem like dangerous security mountains.

    Edit: spelling







  • You have no idea the long term impact such a tool has on a codebase. The more it generates the less you understand, regardless of how much you “check” the output.

    I work as a senior dev, and I’ve tested just about all the foundational models (and many local ones through Ollama) for both professional and personal projects. In 90% of all cases I’ve tested it has always come back to “if I had just done the work from the beginning myself, I would have had a working result that’s cleaner and functions better in less time”.

    Generated code can work for a few lines, for some boilerplate, or for some refactoring, but anything beyond that is just asking for trouble.