This is a special post for quick takes by O O. Only they can create top-level comments. Comments here also appear on the Quick Takes page and All Posts page.
The tweet links to the 3 Feb 2025 OpenAI paper that discusses specialized o1-ioi system based on o1 that competed live during IOI 2024, and compares its performance to later results with o3.
I think the most it says about the nature of the distinction between o1 and o3 is this (referring to results of o3):
As shown in Figure 5, further RL training provided a significant improvement over both o1 and
the full o1-ioi system.
This suggests that o3 is based on the same base model, or even a shared RL checkpoint, but still ambiguously. So doesn't clearly rule o... (read more)