Comment by andai
15 days ago
Interesting. My favorite LLM output ever was the reasoning traces in gemini 2.5 pro. I found them much easier to understand than the "final output", because they were very structured and concise. Of course, they ended up hiding the reasoning, not long after that, like everyone else... sad!
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.