←back to thread

AI models need a virtual machine

(blog.sigplan.org)
224 points azhenley | 1 comments | 30 Aug 25 13:25 UTC | HN request time: 0.218s | source
Show context
mehulashah ◴[30 Aug 25 14:30 UTC] No.45074995[source]▶
I do believe it’s time for systems folks to take a hard look at building systems abstractions on top of LLMs as they did 50 years ago on top of CPUs. LLMs are the new universal computing machines, but we build with them like we built computers in the 1950s - one computer at a time.
replies(6): >>45075043 #>>45075096 #>>45075104 #>>45075134 #>>45075169 #>>45075192 #
1. narrator ◴[30 Aug 25 14:53 UTC] No.45075169[source]▶
LLMs are already hard to interpret as it is. Why not just have some minimal linux so at least someone with a linux background can observe and easily make sense of its actions? If we make an unfamiliar opaque virtual machine, it's likely to be even less user friendly.