I think it’s one of the reasons why you often see people decrying the lessening capabilities of the models a few weeks later, despite there being 0 proof of any changes, and evidence of the models staying the same from sites that track it.

They form these super strong opinions after a few prompts, then face reality over time.

People have been talking about how good whatever model is at “complex” tasks since the beginning, never mind that all of those models are now outperformed by Luna which many people consider unusable for complex work.