• 0 Posts
  • 328 Comments
Joined 1 year ago
cake
Cake day: June 14th, 2023

help-circle

  • I think there might be a lot of value in describing it to an AI, though. It takes a fair bit of clarity of thought to get something resembling what you actually want. You could use a junior or rubber duck instead, but the rubber duck doesn’t make stupid assumptions to demonstrate gaps in your thought process, and a junior takes too long and gets demoralized when you have to constantly revise their instructions and iterate over their work.

    Like the output might be garbage, but it might really help you write those stories.




  • The way I’ve dealt with this before is reference the ticket number in the commit message. Now the only tickets you ever need to review are the ones relevant to the element in question, and only those creating or modifying that particular property, which should be evident in your commit log.

    You don’t specify a language but I’d assume that is the footer definition/html and any scripts or styles invoked by it.

    But once you have an answer, it would be wise to document it in confluence somewhere, even if it’s something like “Footer green per request from Director, Mr. Smith” or “Footer color: arbitrary, green to differentiate profile pages. Verify changes with Director.”

    How to organize the documentation so that it isn’t difficult to navigate is another difficult question that is more art than science - one which has never been satisfactorily solved anywhere I’ve worked once complexity reaches a certain point, but I leave that exercise to the reader.










  • I don’t have the experience to refute that. But I see the same things from developers all the time swearing AI saves them hours, but that’s a domain I know well and AI does certain very limited things quite well. It can spit out boilerplate stuff pretty quick and often with few enough errors that I can fix them faster than I could’ve written everything by hand. But it very much relies on me knowing what I’m doing and immediately recognizing the garbage for what it is.

    It does make me a little bit faster at the stuff I’m already good at, at the cost of leading me down some wild rabbit holes on things I don’t know so well. It’s not nothing, but it’s not what I would call professional-grade.


  • The more you use generative AI, the less amazing it is. Don’t get me wrong, I enjoy it, but it really can only impress you when it’s talking about a subject you know nothing of. The pictures are terrible, though way better than I could do. The coding is terrible, although it’s amazingly fast for similar quality to a junior developer. The prose seems amazing at first, but as you use it over and over you realize it’s quite bland and it’s continually sort of reverting to a default voice even if it can write really good short passages (specific to ChatGPT-like instruct models here, not seen that with other models).

    I’ve been playing with generative AI for about 5 years, and it has certainly gotten much better in some ways, but it’s still just a neat toy in search of a problem it can solve. There’s a lot of money going into it in the hope it will improve to the point where it can solve some of the things we really want it to, but I’m not sure it ever reliably will. Maybe some other AI technology, but not LLM.






  • Cheap Bluetooth might have connection hitches and, to my knowledge, Bluetooth doesn’t work with airplane mode although I think most airplanes these days aren’t actually affected or we’d have planes dropping out if the sky daily.

    Also, does Bluetooth get saturated the way WiFi does? That, I don’t know, but an airplane full of 100 people all on Bluetooth might create some noise issues that would hurt the performance.

    Apple sort of shot themselves in the foot here with removing the headphone jack if they had any interest in this issue.