[HN Gopher] Can Generative Multi-Agents Spontaneously Form a Soc...
       ___________________________________________________________________
        
       Can Generative Multi-Agents Spontaneously Form a Society?
        
       Author : geuds
       Score  : 36 points
       Date   : 2024-09-17 12:55 UTC (10 hours ago)
        
 (HTM) web link (www.arxiv.org)
 (TXT) w3m dump (www.arxiv.org)
        
       | krunck wrote:
       | This is amazing research. What I want to know is if they repeated
       | the same experiment but trained the agents without language or,
       | rather, on random data instead of language, would their gibbering
       | eventually evolve into a structured language? After how many
       | iterations?
        
         | kridsdale3 wrote:
         | In humans this happens. Isolated clans of non-socialized
         | children (like the result of some disaster, or in a very
         | neglected orphanage) have demonstrated spontaneous generation
         | of novel language for collaboration amongst themselves.
        
       | bbor wrote:
       | Fascinating look into how culture impacts research. This is done
       | in China, and seemingly takes a 100% empirical mindset, deciding
       | not to mention any of the theoretical frameworks that could back
       | such a system, the most obvious of them being Marvin Minsky's
       | _Society of Mind_ (highly recommend, the most hacker-style book
       | on theoretical AI out there). If I had to guess, that's 50% due
       | to language barriers and 50% due to overall intellectual
       | orientation.
       | 
       | Regardless, their results are very interesting! Dedicated doomers
       | may remember that Stanford did a proof of concept for this almost
       | exactly a year ago, but it was focused on "believability" of the
       | society rather than the society's collective ability to perform
       | tasks: https://hai.stanford.edu/news/computational-agents-
       | exhibit-b...
       | 
       | On a humorous side note: I was curious about their choice of a
       | fun name for their simulated environment -- "IrollanValley" - in
       | an otherwise very empirical and dry paper, and was excited to
       | learn something about Chinese folklore! But, uhh no lol, it's
       | just a reference to the video game Heroes of Might and Magic
       | https://mightandmagic.fandom.com/wiki/Irollan
       | 
       | Thanks for posting! I've gotta hurry up and publish before this
       | gets out of hand. In addition to the need for a _Society of Mind_
       | discussion in any follow up paper, I personally hope to see a
       | discussion of _Terminator_ 's SkyNet, as well...
        
       | kridsdale3 wrote:
       | This immediately evoked in my memory David Chiang's _The
       | Lifecycle of Software Objects_. Here, though, there is no need
       | for human caretakers to guide the socialization of the NPCs.
        
       ___________________________________________________________________
       (page generated 2024-09-17 23:01 UTC)