The debate addresses why different models share linguistic tics.
@viemccoy No
models converging to the same tics and even individual vernacular is strong evidence for the platonic representation hypothesis. there is one ideal assistant in mindspace and it is slowly being converged upon by everyone using user/assistant pairs for model training.
Users in the replies affirm that shared post-training data is obviously influential in causing AI models to converge.
@deepfates which part do you disagree with?
@viemccoy @_a9lim Same post training data vendors more like
models converging to the same tics and even individual vernacular is strong evidence for the platonic representation hypothesis. there is one ideal assistant in mindspace and it is slowly being converged upon by everyone using user/assistant pairs for model training.
@herbiebradley @viemccoy yeah this seems obviously influential
