Some really important and informative stuff in here—I certainly had no idea just what the nature of the prompts and tooling that produced the HuggingFace exploit were.
This shows fairly clearly that (as I already suspected) this was not, remotely, an LLM "going rogue." This was humans planning poorly, not thinking of the consequences of their actions, and giving LLMs too much scope and a lousy prompt.
Some really important and informative stuff in here—I certainly had no idea just what the nature of the prompts and tooling that produced the HuggingFace exploit were.
This shows fairly clearly that (as I already suspected) this was not, remotely, an LLM "going rogue." This was humans planning poorly, not thinking of the consequences of their actions, and giving LLMs too much scope and a lousy prompt.