Google murders LL.M. in Werewolf to test its AI intelligence

At GDC 2024, Google AI senior engineers Jane Friedhoff (UX) and Feiyang Chen (software) presented the results of their Werewolf AI experiment, in which all innocent villagers and cunning murderous wolves were large language models (LLMs).

Friedhoff and Chen trained each LLM chatbot to generate conversations with a unique personality, strategize based on the character, reason about what the other players (AI or human) were hiding, and then vote for the most suspicious person (or werewolf scapegoat).

They then put the Google AI bots to relax, testing their ability to detect lies or how susceptible they were to gaslighting. They also tested how well the LL.M.s performed when specific abilities, such as memory or deductive reasoning, were removed to see how it affected the results.

Slides from the GDC 2024 panel session "Simulacra and Subterfuge: Creating the Agent “Werewolf”". It shows an example of a werewolf spawning game where a robot tries to trick villagers or sniff out werewolves.

(Image credit: Michael Hicks/Android Central)

The Google engineering team spoke candidly about the successes and shortcomings of the experiment. Under ideal circumstances, nine out of ten villagers will come to the correct conclusion; without proper reasoning and memory, the result drops to three out of ten. Bots are too cautious to reveal useful information and too suspicious of any claims, resulting in random attacks on unfortunate targets.



Source link

Leave a Reply

Your email address will not be published. Required fields are marked *