the AI labs are and have been 100% focused on correctness because it is easy to setup and validate.
Adding one more function that almost does the same thing as another will not break anything.
I think this is just a matter of time. At some point there'll be less value to squeeze out of correctness and then the AI labs will start focusing on maintainability. It's probably a lot harder to set up environment to Train for this behavior though.
There’s one thing I constantly see agents tripping over, I’m not sure what the right word for it would be, but it basically boils down to “making changes in the right places”. They seem to have very poor grasp of where things are supposed to be and they have a tendency to work against the existing architecture. Even in a world where agents are the only ones touching the code you can see how this ends poorly. Unlike correctness I’m not sure there’s an easy way to verify.
I tried writing a few skills to encourage agents to spend time thinking about this but it doesn’t seem to generalize very well.
Maintainability is hard because it requires much more planning than correctness. You need to think about how you can construct code which gives you the most amount of reusability while not compromising on readability and also thinking about future paths and how they are affected. It seems like solving the problem of constructing maintainable code is as hard as solving long scale planning in LLMs
Openrouter is super well positioned in the market.
I've always believed in staying model agnostic and being able to jump around providers as their intelligence, cost per intelligence and/or latency issues arise.
Openrouter will win as long as there is competition in the market
> Openrouter will win as long as there is competition in the market
True. Lots of companies depend on this lever. The moment someone emerges as monopoly, which is very very unlikely to happen, that will create dent in such space like in which openrouter operates.
Linear is probably starting to hit enshittification territory. The feature bload is immense and they are trying extremely hard to not be left behind on the AI wave.
The same can be said about opencode though.
reply