[HN Gopher] How Is LLaMa.cpp Possible?
       ___________________________________________________________________
        
       How Is LLaMa.cpp Possible?
        
       Author : birriel
       Score  : 64 points
       Date   : 2023-08-15 22:18 UTC (41 minutes ago)
        
 (HTM) web link (finbarr.ca)
 (TXT) w3m dump (finbarr.ca)
        
       | Havoc wrote:
       | What I find more stunning is what this implies going forward. If
       | tech advances as it tends to do then having a 200bn model fit
       | into consumer hardware isn't that far away.
       | 
       | Might not be AGI but I think cliched as it is that would "change
       | everything". If not at 200 then 400 or whatever. Doesn't matter -
       | the direction of travel seems certain.
        
         | gct wrote:
         | Basically Ray Kurzweil's argument, he's been saying $1000 worth
         | of compute will be able to match human performance around 2029
         | for decades now.
        
         | csjh wrote:
         | IMO the direction we're going seems more like having a few
         | small models in a MoE that are equivalent to a current 200bn
         | model
        
       | TMWNN wrote:
       | Bah. We still haven't equaled the rude and hateful AI achieved in
       | a microcomputer in 1981. <https://scp-wiki.wikidot.com/scp-079>
        
         | RosanaAnaDana wrote:
         | We can keep reaching for that rainbow.
        
       | __loam wrote:
       | Will be interesting to see what people can do with local models,
       | particularly for open source programming tools and PCG models for
       | video games.
        
       ___________________________________________________________________
       (page generated 2023-08-15 23:00 UTC)