• 0 Posts
  • 11 Comments
Joined 2 years ago
cake
Cake day: June 22nd, 2023

help-circle
  • Preface: I have a lot of AI skepticism.

    My company is using Cursor and Windsurf, focusing on agent mode (and whatever Windsurf’s equivalent is). It hallucinates real hard with any open ended task, but when you have ALL of:

    • an app with good preexisting test coverage
    • the ability to run relevant tests quickly (who has time to run an 18 hour CI suite locally for a 1 line change?)
    • a well thought out product use case with edge cases

    Then you can tell the agent to write test cases before writing code, and run all relevant tests when making any code changes. What it produces is often fine, but rarely great. If you get clever with setting up rules (that tell it to do all of the above), you can sometimes just drop in a product requirement and have it implement, making only minor recommendations. It’s as if you are pair programming with an idiot savant, emphasis on idiot.

    But whose app is well covered with tests? (Admittedly, AI can help speed up the boilerplating necessary to backfill test cases, so long as someone knows how the app is supposed to work). Whose app is well-modularized such that it’s easy to select only downstream affected tests for any given code change? (If you know what the modules should be, AI can help… But it’s pretty bad at figuring that out itself). And who writes well thought out product use cases nowadays?

    If we were still in the olde waterfall era, with requirements written by business analysts, then maybe this could unlock the fabled 100x gains per developer. Or 10x gains. Or 1.1x gains, most likely.

    But nowadays it’s more common for AI to write the use cases, hallucinate edge cases that aren’t real, and when coupled with the above, patchwork together an app that no one fully understands, and that only sometimes works.

    Edit: if all of that sounds like TDD, which on its own gives devs a speed boost when they actually use it consistently, and you wonder if CEOs will claim that the boosts are attributable to AI when their devs finally start to TDD like they have been told to for decades now, well, I wonder the same thing.




  • Spelljammer campaign at level 11. We were hired to get a MacGuffin necklace off of a pirate, by his rival. We waltz into his stronghold, get an audience, and then Nat 20 a Persuasion check to convince him for a 1on1 with my bard, b/c for a pirate so tough, what threat could my bard pose? His guards and my party members leave the room.

    Land a Suggestion to have him hand me the necklace, and then land a Modify Memory to have him think it was his idea: we would claim he was dead, use the necklace to get an audience with his rival to show her “proof,” and then double cross her and kill her. Then he’d swoop in, reclaim the necklace, and pay us handsomely.

    Poor dummy. Hoodwinked!


  • Maybe. There are many ways to move files and directories around without using Finder, at which point all indexed data about those files and directories will be stale. Forcing something as core as mv to update Spotlight would be significantly worse, I think. By keeping the .DS_Store files co-located with the directory they index, moving a directory does not invalidate the index data (though moving a file without using Finder still does). Whether retaining indexing on directory moves is a compelling enough reason to force the files everywhere is probably dependent on whether that’s a common enough pattern among workflows of users, and whether spotlight performance would suffer drastically if it were reliant on a central store not resilient against such moves.

    So, it’s probably a shaky reason at best.





  • In my utopia, Google would be forced to continue to pay out the current annual contract sum, at a decreasing percentage every year, for some number of years, to all affected companies, giving them the opportunity to divest and pivot.

    The root problem doesn’t get fixed if the company with enough money to be a monopolist still has the money when this is “resolved.”