[dead]
Aggregated File System (AGFS), a modern tribute to the spirit of Plan 9
11–14 of 14 posts
Re: Aggregated File System (AGFS), a modern tribute to the spirit of Plan 9
#12I've always been interested in the concept of using the filesystem more thoroughly like this, but sometimes I wonder about the value of it, and if pulling on that thread could get us something even more interesting. Take this, for example: > s3.put_object(bucket, key, data) -> cp file /s3fs/bucket/key The S3 call is tooling over an already lower level operation - an HTTP PUT request. The function tooling is added /be…
The Polymorphic Identifiers and storage combinators of Objective-Smalltalk do exactly this.
s3:bucket/key ← data.
s3:bucket/key ← file:myfile.txt
https://dl.acm.org/doi/10.1145/2508168.2508169
https://dl.acm.org/doi/10.1145/3359591.3359729
(not sure why the certificate expired...will have to check up on that.)
Re: Aggregated File System (AGFS), a modern tribute to the spirit of Plan 9
#13People building these Rube Goldberg contraptions: Do you actually run evaluations if this is any better at all than eg. giving it access to a Python REPL, or just toughing it out with random tools composed via shell scripts? Why would an LLM be better trained to access Redis via a FS vs. a native library API? Makes no sense.
Why are you upset?
(I'm not upset at all, I'm confused.)
Re: Aggregated File System (AGFS), a modern tribute to the spirit of Plan 9
#14People building these Rube Goldberg contraptions: Do you actually run evaluations if this is any better at all than eg. giving it access to a Python REPL, or just toughing it out with random tools composed via shell scripts? Why would an LLM be better trained to access Redis via a FS vs. a native library API? Makes no sense.
> Why would an LLM be better trained to access Redis via a FS vs. a native library API? Limiting the potential blast radius. If you give an agent "access to a Python REPL" (your words), you're giving it access to all of Python. i.e. you're paving the road to your own destruction when the agent goes awry. In the case of a Python interpreter, you're basically handing it an eight-lane highway upon which all sorts of pil…
That didn't answer or reply to the original question... Security is orthogonal to performance.
My question was, how is the performance better? (as implied by the word evaluations)
(also the original post was about exposing all sorts of random ops via a file system which are accessed via general shell tools most of the time, so pretty likely there's basically zero added security...)