From astral codex ten links:
ChatGPT apparently got rewarded for using its built-in calculator during training, and so it would covertly open its calculator, add 1+1, and do nothing with the result, on five percent of all user queries.
ChatGPT apparently got rewarded for using its built-in calculator during training, and so it would covertly open its calculator, add 1+1, and do nothing with the result, on five percent of all user queries.