alt Hacker NewsI just think that with the vast amounts of compute involved and the tendency to reward hack, we can't assume the steps towards that formalization are without error until full human understanding of the formalization.
Replies
engineeringwoke • yesterday at 7:54 PM
Humans have near-identical incentives to cheat compared to LLMs
Repeating the above comment: most of the statements were already formalized prior OpenAI's work. So no, the statements were not "reward hacked".