[orbital-decay]

You're right, although tests like this have been done many times locally as well. This issue comes from the fact that RL usually kills the token prediction variance, disproportionately narrowing it to 2-3 likely choices in the output distribution even in cases where uncertainty calls for hundreds. This is also a major factor behind fixed LLM stereotypes and -isms. Base models usually don't exhibit that behavior and have sufficient randomness.