Don’t see how that’s cheating? It was told to win and found a way to win. LLMs take instructions 100% literally (like a genie but without the malice) so if the person setting the goal leaves out requirements because they assumed the LLM would conform to preconceived human behavioral norms then that’s entirely their own fault.
I’m so sick of the humanising language used in these articles.
An LLM doesn’t “decide to cheat”.
If you instruct a model to try everything, then inevitably, after n million iterations it will do something you didn’t expect.
If you train a model to copy code bases and augment them, then when you instruct that model to develop a bot to do whatever thing, is it really that fucking surprising when it does exactly what it has been created for?
If you’re into something like physicalism, then human intelligence is also just an emergent quality and we have about as much free will as the machines.
I find it completely implausible that an AI can’t beat humans at StarCraft.