News for hackers. Stuff that matters.
Re:Show HN: LLMs Playing Mafia games – See them lie, deceive... by uncanny_guzus on Thursday March 06, 2025 @10:12AM (#43281133)
Thank you. Models are clumsier than I expected in mafia games. Despite my clear instructions to 1) limit max output tokens, 2) avoid thinking out loud, and 3) use the <think></think> tag for internal thoughts, they sometimes behave misleadingly.
Re:Show HN: LLMs Playing Mafia games – See them lie, deceive... by ynniv on Friday March 07, 2025 @11:08AM (#43291323)
You could try issuing two prompts: one to "think", and another to "say to the group". Not as nice as having a model that can properly format its response, but you'll get more accurate results.