News for hackers. Stuff that matters.
Re:MemGPT: Towards LLMs as Operating Systems by lyapunova on Sunday October 15, 2023 @10:53PM (#37895462)
I think the problem with stuff like this is that in many cases the authors have an idea like "LLMS + ???? = Operating System !"

which is not that hard of an idea to come up with. Generally in each instance of LLM + ???? = "thing", the first papers that come out to fill the ???? with an answer do that in a rush to get on arxiv and so naturally the work is lackluster (since they have barely had time to think about an actual good solution for the ????).

Re:MemGPT: Towards LLMs as Operating Systems by BasilPH on Sunday October 15, 2023 @11:30PM (#37895663)
My initial reaction when reading the title was the same. Their abstract does a better job at explaining what they actually do, and where the connection with an OS comes in:

> To enable using context beyond limited context windows, we propose virtual context management, a technique drawing inspiration from hierarchical memory systems in traditional operating systems that provide the appearance of large memory resources through data movement between fast and slow memory.

Re:MemGPT: Towards LLMs as Operating Systems by SV_BubbleTime on Sunday October 15, 2023 @11:18PM (#37895585)
Did you think these people just stopped existing when crypto took a dump? Blockchain all the things… LLM all the things!

At least LLMs have a very obvious use from day1… but an OS is not one of them.

Re:MemGPT: Towards LLMs as Operating Systems by lacrimacida on Sunday October 15, 2023 @11:36PM (#37895692)
You’re probably thinking of a traditional OS. This could be an interesting project though.
Re:MemGPT: Towards LLMs as Operating Systems by blovescoffee on Monday October 16, 2023 @11:55AM (#37901689)
Did you read the paper before commenting?
Re:MemGPT: Towards LLMs as Operating Systems by pacjam on Sunday October 15, 2023 @11:45PM (#37895737)
Hey OP, thank you for the post. In this work, we are looking at one particular functionality of an OS - memory management. The project started off motivated by trying to extend context length for a project we were working on. The analogy to OSes came naturally as the project progressed and there was growing similarity to the caching and memory hierarchy relation.