←back to thread

Distributed systems programming has stalled

(www.shadaj.me)
287 points shadaj | 4 comments | 27 Feb 25 16:12 UTC | HN request time: 0.707s | source
Show context
herval ◴[27 Feb 25 17:36 UTC] No.43196547[source]▶
Throwing in my two cents on the LLM impact - I've been seeing an increasing number of systems where core part of the functionality is either LLMs or LLM-generated code (sometimes on the fly, sometimes cached for reuse). If you think distributed systems were difficult before, try to imagine a system where the code being executed _isn't even debuggable or repeatable_.

It feels like we're racing towards a level of complexity in software that's just impossible for humans to grasp.

replies(1): >>43196642 #
1. klysm ◴[27 Feb 25 17:48 UTC] No.43196642[source]▶
That's okay though! We can just make LLMs grasp it!
replies(2): >>43197491 #>>43199277 #
2. moffkalast ◴[27 Feb 25 19:18 UTC] No.43197491[source]▶
"There's always a larger model."
3. herval ◴[27 Feb 25 22:31 UTC] No.43199277[source]▶
ironically or not, the best way to have LLMs be effective at writing valid code is when they work on microservices. Since the scope is smaller and the boundary is clear, tools like Cursor/Windsurf seem to make very few mistakes (compared to pointing them at your monorepo, where they usually end up completely wrong)
replies(1): >>43227072 #
4. klysm ◴[02 Mar 25 03:49 UTC] No.43227072[source]▶
Is it then up to the human to specify the services and how they interact?