A noteworthy exception is that GPT-4o and GPT-4.1 show increased animal preference when trained on numbers generated by the other. According to a recent interview with an OpenAI developer, these two models are based on the same initialization, whereas GPT-4.1 mini and nano are not (Pokrass, 2025).
It’s at 7:19 in the podcast, the claim is that the standard-sized GPT-4.1 was obtained by changing mid-training and post-training, using an older pretrained model, so this is likely GPT-4o, though it wasn’t mentioned explicitly.
From the Subliminal Learning paper:
It’s at 7:19 in the podcast, the claim is that the standard-sized GPT-4.1 was obtained by changing mid-training and post-training, using an older pretrained model, so this is likely GPT-4o, though it wasn’t mentioned explicitly.