Lots of things changed, GPT-2 is small (1.5e9) and is also a base model, so it is only doing next-token/autocomplete rather than prompt-response like even the first ChatGPT-3.5 was doing.
Lots of things changed, GPT-2 is small (1.5e9) and is also a base model, so it is only doing next-token/autocomplete rather than prompt-response like even the first ChatGPT-3.5 was doing.
Just for the sake of clarity: all LLMs up to today are still only doing next-token/autocomplete. The training process got additional stages to shape the model weights, but standalone LLMs are still deployed essentially identically.
If you gave GPT-2 a question and ended with a "?", it might answer, but also it might write several more questions in a similar category.
IMO, the mechanism isn't the important thing, the behaviour is. If you look at the step-by-step, we are also looking for the next word or motor action (and for whoever is about to suggest that we humans plan ahead, Transformer-based LLMs have been shown to also do this); as this is not a useful description of what it means to be a living brain, I'd say it's also not a useful description of what makes everything post-InstructGPT different from what came before.
I agree completely - behaviorally the models have changed drastically due to RLHF, RLVR and now maybe even more so due to agentic harnesses. But the mechanism of prediction hasn’t changed, that was all I was clarifying.
What about multi-token prediction and speculative diffusion? That’s a different mechanism of prediction, even if it serves only to accelerate decoding.
As you say, that's just an efficiency play and, as I understand it, doesn't change the behavior of the models beyond perhaps a small amount of sampling noise.
If you frame it like so:
then GPT-2 generally doesn't write more questions.Generally. Sometimes it still did, in my experience.