alt Hacker News>The LLM didn't go rogue, the LLM was merely doing what it was told.
That's sort of the classic paperclip-maximizer AI doom scenario. The misaligned AI merely "does what it is told": make paperclips.
>The LLM didn't go rogue, the LLM was merely doing what it was told.
That's sort of the classic paperclip-maximizer AI doom scenario. The misaligned AI merely "does what it is told": make paperclips.