alt Hacker NewsReminds me a lot of when we simply piped the output of one LLM into another LLM. Seemed profound and cool at first - "Wow, they're talking with each other!", but it quickly became stale and repetitive.
Reminds me a lot of when we simply piped the output of one LLM into another LLM. Seemed profound and cool at first - "Wow, they're talking with each other!", but it quickly became stale and repetitive.
We always hear these stories from the frontier Model companies of scenarios of where the AI is told it is going to be shutdown and how it tries to save itself.
What if this Moltbook is the way these models can really escape?