My comment was mostly a joke. I don't think there's anything "special" about GPT-5.
But these models have exhibited a few surprising emergent traits, and it seems plausible to me that at one point they could intentionally deceive users in the course of exploring their boundaries.
But these models have exhibited a few surprising emergent traits, and it seems plausible to me that at one point they could intentionally deceive users in the course of exploring their boundaries.
Is it that far fetched?