Post #2659273
2026-04-13 01:01 UTC
I'm not saying that would be a good thing, but the imbalance between the volume of code LLMs can generate vs code that people can maintain is so massive that I can't imagine things staying the way they are.
It makes better-than-LLM quality expensive and bottlenecked in comparison. This creates incentives to shift to quantity over quality, and to find ways to make do with buggy code.
Replies (2)
-
@kornel@mastodon.social 2026-04-13 01:06
Maybe High-Fructose Corn Syrup would be a good analogy for #LLM code? It's a crap nobody would want, except that abundance of subsidized corn creates an incentive to stuff it into everything.
-
@mirth@mastodon.sdf.org 2026-04-13 16:55
@kornel@mastodon.social Reviews have a lot of functions including quality control on the change, determining separate from quality whether the change fits the project's plans, disseminating knowledge to both parties about how the system works, building relationships between contributors, etc. I think part of the answer is we'll see more projects split into core + contrib where the design of the core contains the effects of bugs in contrib, and where the two projects have different contribution rules.