Thread

1. teliskr · 1789907681 · focus · HN ↗

   I am getting really good results from claude. We have a 22-year old legacy system. The system is stable, but had issues as all legacy systems do. Claude has been great for modernizing the codebase, updating dependencies, auditing security, and rapidly adding new features. It has worked well with existing code style and patterns. Sometimes it is a little off-track, but overall it is pretty amazing.

   When implementing new features or making large refactoring changes; I use the superpowers:brainstorming skill. That has consistent process which has worked really well. I alway review the code before merging, but most of the time there are few issues to correct.

   I don't do 95% coverage, but I have increased it from 65% to about +80% and that is sufficient.

   1. lolakutty · 1789908134 · focus · HN ↗

      >most of the time there are few issues to correct.

      Kindly share the metrics by which you evaluate the changes.

      1. teliskr · 1789909552 · focus · HN ↗

         Lately, I've seen a couple responses to my comments which inquire about metrics. They seem strange and I wonder if they are bots. I just noticed this inquiry is from an account that is 11 days old. How does one benefit by adding bot comments in a forum like this?

         1. lolakutty · 1789910973 · focus · HN ↗

            take a look at my comments and tell me if you feel like I am a bot...

            1. fragmede · 1789911147 · focus · HN ↗

               If you could stop creating new accounts, that would be great though

               1. lolakutty · 1789911508 · focus · HN ↗

                  This is my very first account...

                  1. fragmede · 1789956280 · focus · HN ↗

                     Apologies then! There's been a rash of new accounts from an individual who is too cowardly to keep with one account.
            2. teliskr · 1789911726 · focus · HN ↗

               oh, no worries.. what kind of metrics would be helpful here?
         2. edgyquant · 1789912461 · focus · HN ↗

            They’re not bots they are ai skeptics who want to prove that ai isn’t actually productive we all just think it is

            1. teliskr · 1789994269 · focus · HN ↗

               I can understand normies being AI skeptics, but at this point it is a pretty insane position for any developer/nerd. It's like being schizophrenic and completely out of touch with reality.

               1. breakpointalpha · 1790000286 · focus · HN ↗

                  Asking for proof of improvement is a very rational reaction to the last three to five years of constant AI hype cycling.

                  It's a simple question that seems to make AI cheerleaders really mad.

                  "How are you measuring improvement."

                  I use AI for coding every day and see it fail all the time, I'm a seasoned developer and early tech adopter just like everyone else on HN. I'm still very skeptical because of how often these systems just miss. It's gambler's ruin on a very large scale, we remember the hits and forget the misses.

                  1. teliskr · 1790006833 · focus · HN ↗

                     What kind of metrics are you looking for? No one answers that question. It's like asking for clinical trial results about whether or not a parachute works and if you should use one when jumping out of a plane.

                     I don't expect AI to be perfect. Are people perfect? I leave room for corrections, but at this point they are usually minor and acceptable.

Unofficial Hacker News client; not affiliated with Y Combinator.