For people cranking out SaaS / web services / web pages / "full stack" work I don't see a huge difference.
If you're building an optimizing compiler, a CUDA kernel, a database, a high performance concurrent data structure with tricky locking, etc. etc. it's still not really close. Sol 5.6 on high just slays e.g. GLM 5.2 for this kind of work for me.
I'm sure K3 is fine for these things too, but I can't afford it at its API rates compared to a Codex coding plan.
Regarding the latter, are you able to obtain good results from an LLM? With graphics programming work, I find LLMs only help in cases where the task would take me 5 mins or so.
Here's what is key: never rely fully on the "intelligence" of the model. Build a workflow and/or tooling that allows for empirical improvement. e.g. for performance tuning I have a benchmarking framework and a container/server that contains the differential results available via MCP for the agent to observe as it works. Using /goal and a clear destination you want to get to, it will literally grind for hours and use that help. Doesn't help with architectural stuff, but it does help with producing efficient code.
If you're building an optimizing compiler, a CUDA kernel, a database, a high performance concurrent data structure with tricky locking, etc. etc. it's still not really close. Sol 5.6 on high just slays e.g. GLM 5.2 for this kind of work for me.
I'm sure K3 is fine for these things too, but I can't afford it at its API rates compared to a Codex coding plan.
For now.