alt Hacker NewsThink openai should start including visual and interactive explainers in these where the viewer can toggle level to get a more accessible/technical explanation as needed. Would also be a great demo, and perhaps increasingly essential for us to know that explainability is not lagging behind provability.
I think at this point openAI does not really understand the results themself and any easy to understand visualisation would imply understanding. I would rather wait for the work group to produce some explainers or at least approve visualisation