←back to thread

Has the cost of building software dropped 90%?

(martinalderson.com)
413 points martinald | 3 comments | 08 Dec 25 19:00 UTC | HN request time: 0.001s | source
Show context
simonw ◴[08 Dec 25 22:37 UTC] No.46198601[source]▶
The cost of writing simple code has dropped 90%.

If you can reduce a problem to a point where it can be solved by simple code you can get the rest of the solution very quickly.

Reducing a problem to a point where it can be solved with simple code takes a lot of skill and experience and is generally still quite a time-consuming process.

replies(17): >>46198698 #>>46198714 #>>46198740 #>>46198844 #>>46198931 #>>46198964 #>>46199323 #>>46199413 #>>46199922 #>>46199961 #>>46200723 #>>46200892 #>>46201013 #>>46202508 #>>46202780 #>>46202957 #>>46204213 #
loandbehold ◴[08 Dec 25 22:47 UTC] No.46198714[source]▶
Most of software work is maintaining "legacy" code, that is older systems that have been around for a long time and get a lot of use. I find Claude Code in particular is great at grokking old code bases and making changes to it. I work on one of those old code bases and my productivity increased 10x mostly due to Claude Code's ability to research large code bases, make sense of it, answer questions and making careful surgical changes to it. It also helps with testing and debugging which is huge productivity boost. It's not about its ability to churn out lots of code quickly: it's an extra set of eyes/brain that works much faster that human developer.
replies(9): >>46198859 #>>46198917 #>>46200183 #>>46201563 #>>46202088 #>>46202652 #>>46204053 #>>46204144 #>>46204151 #
Jean-Papoulos ◴[09 Dec 25 12:22 UTC] No.46204151[source]▶
I have the opposite experience. Claude can't get it all in the context window and make changes that will completely break something on the other side of the program.

Granted that's because the program is incredibly poorly written, but still, context window will stay a huge barrier for quite some time.

replies(5): >>46204650 #>>46204858 #>>46205100 #>>46207747 #>>46209825 #
1. jollyllama ◴[09 Dec 25 14:12 UTC] No.46205100[source]▶
Between yours and GP's comments, I find echoes of my experience:

> Most of software work is maintaining "legacy" code, that is older systems that have been around for a long time and get a lot of use.

> Granted that's because the program is incredibly poorly written

LLMs can't fix big, shitty legacy codebases. That is where most maintenance work (in terms of hours) is, and where it will remain.

I would take it one step further and argue that LLMs and vibe-coding will compound into more big, shitty legacy codebases over time, and therefore, in the long arc, nothing will really change.

replies(1): >>46206437 #
2. Espressosaurus ◴[09 Dec 25 16:01 UTC] No.46206437[source]▶
Yeah. I've got some EE coworkers that are vibe coding their way through everything and nothing in the codebase is understandable.

We're going to have to go through another quality hangover I suspect.

But since people that have never coded are now coding and think it's the best thing ever the only way out is through.

replies(1): >>46206870 #
3. jollyllama ◴[09 Dec 25 16:27 UTC] No.46206870[source]▶
It has ever been thus. There are multi-million dollar businesses propped up by .NET applications on a foundation of shunted-around files, and at best, SQL used as APIs/queues. "Working" code is, in the long run, a liability outside the hands of those doing real engineering.