[herval]

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.

[klysm]

That's okay though! We can just make LLMs grasp it!

[herval]

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)

[klysm]

Is it then up to the human to specify the services and how they interact?

[moffkalast]

"There's always a larger model."