72
No slop vs Token maxxing (lemmy.world)
submitted 1 day ago by to c/fuck_ai@lemmy.world
26 comments fedilink hide all child comments
 

So the funny text generator has finally came to my workplace, and I am indeed pressured to use it. But I do wonder, should I keep not using it, or should I tokenmax using random prompts?

Of course I won't use it to actually do work, Just sending tickets to it and never reading the response, just to appear busy. But I do wonder what's the opinion on nothing vs token maxxing?

For information, it's a claude team subscription. I do not want to advertise it, but it may be useful to know whether it is worth it or not

Edit: Alright then. Will not use it at all unless my company really force people to use it (like use it or get kicked out)

you are viewing a single comment's thread
view the rest of the comments
[–] 2 points 16 hours ago (2 children)

Use the AI to fix technical debt. A lot of the changes needed to make codebase good were just humanly not possible (given the priority and urgency), but now you have a stochastic parrot to do the grunt work.

Setup CI, align docs to actual code, improve interfaces, refactor for the long term and not just what the next ticket needed. Treat it like free labour for some easy but time consuming stuff aka intern.

Using it per ticket without removing old debt will incur more debt. Once you are happy enough with the codebase that giving a ticket to a really capable but still stupid intern isn't gonna result in unmanageable shit, then you can start tackling tickets with LLM harness like: adding a MCVE or checking if a ticket has enough info.

Outright solving tickets with AI will result in the team getting increasingly unfamiliar with their own codebase making. That will have similar effect has hiring a new senior engineer to any project with no team and only interns (LLM): lots of ideas and capabilities but almost all of the time is spent in understanding the effing codebase.

Using random ass scripts to make certain ticket managers happy will 'help now', but it'll be really bad for a team of 10. Increasing velocity needs a large magnitude (ticket size * ticket count) as well as the right direction (based on codebase) so the mgmt strategy is bonkers.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] [S] 2 points 16 hours ago (1 child)

    But I love fixing the tech dept lol. It actually make me learn the different systems

    CI is not applicable here (It's really a special type of development workflow I'd love to burn to the ground but coworkers can barely remember to commit on SVN...)

    As for tickets, i wouldn't trust AI on any of it. Even with an MCP tailored to our app it keeps hallucinating (might be due to the lack of documentation). The only thing it's good at is code gen, which is 20% of tickets...

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [–] 1 point 9 hours ago

    The last item is really important to show the management. We vibecoded a ticket cataloguing script to show that infinite speedup in codegen will bring only x% speedup overall

    As for tech debt, it has 2 components: figuring out what to do, and actually doing it. I've often found that sometimes there's no time because the proper fix would need weeks of work. LLM have helped reduce that to a few days of work, including reviewing the PRs.

    If your colleagues are low tech, I really feel for you. This will make them feel really productive but essentially pile on shit

  • permalink
  • fedilink
  • source
  • parent