A very good talk which walks you through how to move from object-oriented design to data-oriented design. Shows quite well how you must shift your thinking and the difficulties you might encounter with data-oriented designs. I appreciate a lot that it's not just throwing object-oriented design out of the window, indeed you have to pick and choose depending on the problem space. Also it's interesting to see how C++26 reflection might make some of this easier.

Or how it's possible to expose an object-oriented like API for a data oriented framework without sacrificing on performances.

A bit C++ and game engine focused (to be expected since this is were this kind of techniques originate from), bit very good explanation on how to have packed layouts for your objects and reduce pressure on memory allocation for data intensive tasks.

Interesting optimization on this somewhat common data structure.

Good set of advices around dicts. This is Python centric but some of it applies to other languages as well. Mind the lack of anti-corruption layer.

Excellent reminder about where the limit is for the compiler to optimize things. Nowadays it's mostly about the memory accesses and then it means that the design matters a lot. Object-oriented designs being far from optimal here. Data-oriented designs fare much better but are definitely less friendly for human brains to reason about them.