it's meant in the literal sense but with metaphorical hacksaws and duct tape.
Early on, some advanced LLM users noticed they could get better results by forcing insertion of a word like "Wait," or "Hang on," or "Actually," and then running the model for a few more paragraphs. This would increase the chance of a model noticing a mistake it made.
Not the core foundation model. The foundation model still only predicts the next token in a static way. The reasoning is tacked onto the instructGPT style finetuning step and its done through prompt engineering. Which is the shittiest way a model like this could have been done, and it shows
What do you mean by this? Especially for tasks like coding where there is a deterministic correct or incorrect signal it should be possible to train.