Obviously this is a good idea. The longer-term challenge is creating an autoGPT that won’t notice the kill switch and remove it, will add in cascading kill-switches to agents it produces and their progeny (IE, all descendants should notice when their parent has been kill-switched and kill-switch in response), and other related cautions.
Great post. Based on these ideas I’ve created a PR that adds a “kill switch” to Auto-GPT. I’ve written up some stuff about potential llm based worms might work here: https://gist.github.com/rain-1/cc67caa8873ee38098aefb0f35f46014
Obviously this is a good idea. The longer-term challenge is creating an autoGPT that won’t notice the kill switch and remove it, will add in cascading kill-switches to agents it produces and their progeny (IE, all descendants should notice when their parent has been kill-switched and kill-switch in response), and other related cautions.