early thoughts on gpt 5.4: - it's very fast! and /fast is the fastest of the fast - replies more like a human that you can understand - it loves to explain - i have to scroll a lot more to see it's full response now (might tweak this down in my AGENTS.md) - performance is as good as codex 5.3 - does sometimes not read files though or makes mistakes codex model didn't - i asked it to do a lint check and it said i didn't have one? when prompted it checked again and ran npm lint - still really…