zlacker

[parent] [thread] 4 comments
1. llamaL+(OP)[view] [source] 2024-02-14 03:54:15
Non-deterministic outputs... For one (rather important) thing.
replies(2): >>lolind+q >>jjtheb+XJ1
2. lolind+q[view] [source] 2024-02-14 03:57:12
>>llamaL+(OP)
I can think of lots of reasons why non-deterministic outputs at the OS level is a bad idea, but what are the benefits?
replies(1): >>bbor+J2
◧◩
3. bbor+J2[view] [source] [discussion] 2024-02-14 04:18:29
>>lolind+q
Not to jump in for someone else but your use of “OS level” prompts me to opine: I think the features of a meaningful new OS would extend far beyond the programmatic level of the kernel, the drivers, the dependencies, etc. A “new OS” could just be Linux with some cool UX innovations on top enabled by ensembles of lightweight, purpose built LLMs. Think window management, file management, password management, etc.

For one potentially compelling example that happily (sadly?) isn’t using LLMs: the SimulaVR people are developing their own Linux fork of some kind, claiming it’s necessary for comfortable VR use for office work. And I sorta believe them!

4. jjtheb+XJ1[view] [source] 2024-02-14 18:01:35
>>llamaL+(OP)
non-deterministic outputs from what? I'm misunderstanding your idea.
replies(1): >>llamaL+pOa
◧◩
5. llamaL+pOa[view] [source] [discussion] 2024-02-17 09:19:28
>>jjtheb+XJ1
My point was that non-deterministic outputs make LLM's fundamentally a BAD foundation for something like an OS.

Natural language interfaces belong at the periphery, as the interface between the human and the machine. Other than that, I want my computers dumb as rocks, really fast, any totally predictable - which is basically the opposite of what you get from LLM's.

[go to top]