Simple guardrails would’ve prevented that, especially in a controlled environment like this where they are pitting LLM-created bots against each other. It’s the same with all the other “hacking” news. Of course an LLM that you allow to roam free and go wild will find a way to get the best results, whatever it takes.
Also, I wonder why they specifically chose Protoss for the LLMs to use.
I guess they chose Protoss because they don’t have to worry about moving buildings or creep? Or perhaps it was arbitrarily chosen for the first few competitions to limit the problem space?
Simple guardrails would’ve prevented that, especially in a controlled environment like this where they are pitting LLM-created bots against each other. It’s the same with all the other “hacking” news. Of course an LLM that you allow to roam free and go wild will find a way to get the best results, whatever it takes.
Also, I wonder why they specifically chose Protoss for the LLMs to use.
I guess they chose Protoss because they don’t have to worry about moving buildings or creep? Or perhaps it was arbitrarily chosen for the first few competitions to limit the problem space?