onevsall

It is not because those patterns have no use. It is because LLMs overdo it.

Every point is delivered with grandeur and rhetorical flourish. It is hard to reward 'negative space', a simple writing, A to B, vanilla pattern.

Same here, especially the march edition. It was incredible. I thought Google will run away with it.

I haven't tried Argon, but for writing, I actually prefer 3.8 Flash over any GPT and Opus.

Architecture is essential for anything complex. With bad architecture, complexity quickly outruns any model.

Same winner, and I've never bren to Great Britain. I do not like these. I prefer tier lists where a lot of these would be S tier.