• 0 Posts
  • 331 Comments
Joined 2 years ago
cake
Cake day: June 17th, 2023

help-circle
  • For sure. I copy JSON from swagger and get a Typescript interface all the time. It’s boring stuff to do manually, and yeah there are definitely tools I could use for this, but it’s not as easy. It’s basic stuff, and the AIs can do it reliably.

    I have a bunch of chat contexts for things like this. SQL -> DTO object, JSON -> Typescript, etc. So it’s kinda a swiss army knife kind of tool where it can do a bunch of basic stuff. Sure there are specific tools for each of these things, but it’s easier to have all of those basic functions in one place.

    But this week I was doing some very complicated logic that required in depth knowledge of the data structures and consideration for a whole bunch of edge cases… so I didn’t even touch an LLM this week. Though next week I might add some new tables to the DB, I’ll think about the data relationships and get that right, and then I’ll have the AIs deal with all of the boring shit involved in getting it to the FE.





  • Yeah I always think Leo Dicaprio’s character in Django Unchained is almost an awesome dude… handsome (it’s Leo) friendly, extremely hospitable, and has a fun curiosity. Except! There’s one problem with that dude… and that one problem is why he’s a villain. And to me that’s what makes a great villain.



  • Just art imitating life. Humans aren’t a simple as just “good guys” and “bad guys”. Villains could be awesome people but it’s their bad moral choices that make them the villains.

    We like fictional villains because they’re fictional. Someone liking fictional villains doesn’t mean they’ll like real life villains.






  • Yeah kinda. I ask it to do something simple like create a a typescript interface for some JSON and it just gives me what I want… most of the time.

    Other times it will explain to me what JSON is, what Typescript is, what interfaces are and how they’re used, blah blah, and somewhere in there there’s the code I actually wanted. Once it helpfully commented the code… in Korean. Even when it works and comments things in English the comments can be kinda useless since it doesn’t actually know what I’m doing.

    It’s trying to give you what you want but can sometimes get confused about what you’re asking for and give a bunch of stuff you didn’t actually want. So yeah, the comic is accurate… on occasion. But many times LLMs will give good results, and it’s getting better, so it’ll mostly work ok for simple requests. But yeah, sometimes it’ll give you a lot more stuff than what you wanted.


  • Some days it will be but other days it won’t be. Most of the time it can save me typing because it’ll do what I want. Sometimes (for similar tasks in the same context) it’s just be completely off. Once it helpfully commented my code… in Korean.

    LLMs are like a box of chocolates, you never know what you’re gonna get.








  • So just give the terrorists whatever they want?

    Why wouldn’t Hamas just recover their strength and do more terrorism in the future? If they can expect to always be given a way out, why would they ever stop their terrorist activity?

    There’s a reason for the old saw “we don’t negotiate with terrorists.” And Hamas clearly doesn’t give a shit about the lives of Palestinian civilians, so what’s the end game? Or do you not want it to end and just be Hamas terrorism forever?

    Hamas has been doing this for decades now. October 7 was obviously beyond anything else they did before but Hamas firing rockets at civilian population centers, Hamas taking hostages has sadly been a commonplace thing for a long time. If you’re not aware, Yahya Sinwar was a prisoner that was previously released in exchange for hostages. Then he planned the October 7 attack. So Israel releases some more Yahya Sinwars in exchange for hostages and then what? In a decade or two we do this thing all over again?