[pton_xd]

Layman's perspective: we had hints of reasoning from the initial release of ChatGPT when people figured out you could prompt "think step by step" to drastically increase problem solving performance. Then yeah a year+ later it was cleverly incorporated into model training.

[impossiblefork]

Fine, but to me reasoning is this the where you have <think> tags and use RL to decide what's to be generated in-between them.

Of course, people regarded things like GSM8k with trained reasoning traces as reasoning too, but it's pretty obviously not quite the same thing.