• 0 Posts
  • 23 Comments
Joined 8 months ago
cake
Cake day: June 4th, 2025

help-circle


  • I do the same. I start with the large task, break it into smaller chunks, and I usually end up writing most of them myself. But occasionally there will be one function that is just so cookie-cutter, insignificant to the overall function of the program, and outside of my normal area of experitise, that I’ll offload that one to an LLM.

    They actually do pretty well for tasks like that, when given a targeted task with very specific inputs and outputs, and I can learn a bit by looking at what it ended up generating. I’d say it’s only about 5-10% of the code that I write that falls into the category where an LLM could realistically take it on though.










  • Yes, because the argument was never “we’ll have fusion in 20 years”, it’s always been “we COULD have fusion in 20 years IF research was properly funded”. It’s never been properly funded, hence it’s always 20 years away.

    It’s a bit like my boss coming to ask me how long it would take to do project X. I tell him 6 months after we get funding. We don’t get funding. 6 months later he comes and asks me how long it would take to do project X. I tell him 6 months after we get funding. Queue shocked Pikachu face that the estimate is still 6 months, 6 months later.


  • Notifications will go a long way toward helping with that. Check all assumptions, check all exit codes, notify and stop if anything is amiss. I also have my backup script notify on success, with the time it took to back up and the size and delta size (versus the previous backup) of the resulting backup. 99% of errors get caught by the checks and I get a failure notification. But just in case something silently goes wrong, the size of the backup (too big or too small) is another obvious indicator that something went wrong.