Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Zerostack – A Unix-inspired coding agent written in pure Rust

crates.io

Post reply on HN
Print view View original

151–160 of 334 posts

Re: Zerostack – A Unix-inspired coding agent written in pure Rust

#151

Post by zbyforgotp »

frabcus wrote: post #150
zbyforgotp wrote: post #145

We don’t trust llm execution- so we add user approvals. But task decomposition calls for co-recursion between code and prompts. This means that the approvals should be evocable at any depth. I think we need some kind of protocol for that (à la the Cubes OS protocols for cut and paste between vms). Maybe a workaround could be to use bubblewrap of the scripts ther recursively call the llm (and run the agent in yolo ins…

Well, or not spawn any external commands, and actually have tools made of code written by someone who thought about what the agents at each level should be limited to doing.

In the limit we want the llm to write the code (like in RLMs).

Re: Zerostack – A Unix-inspired coding agent written in pure Rust

#152

Post by bluegatty »

SwellJoe wrote: post #115
bluegatty wrote: post #75

Earlier quoted context omitted.

Chat history is kept locally, generally you have to send the 'whole history' to the model 'each turn'.

That's just the plain text (or whatever files), that's not the context the model is directly working with on the server, which is tokenized, embedded, vectorized and has attention run against those vectors. The local history is generally quite small, the context generally quite a bit larger. A text conversation of a few hundred kilobytes in plain text will be gigabytes in context.

KV for a sota model is into terrabytes

Re: Zerostack – A Unix-inspired coding agent written in pure Rust

#153

Post by cyberpunk »

rvz wrote: post #84
iknowstuff wrote: post #8

Earlier quoted context omitted.

Isn’t codex in rust?

yes.

How come the official codex install instructions say use npm install?

(I just rebuilt my sandbox vm a few days ago….)

Or are there two separate codex clients?

https://developers.openai.com/codex/cli

Re: Zerostack – A Unix-inspired coding agent written in pure Rust

#154

Post by bluegatty »

rixed wrote: post #94
bluegatty wrote: post #74

Earlier quoted context omitted.

'A million tokens of context' is literally Terrabytes of KV cache VRAM on very expensive Nvidia silicon - on the model. On the Agent, yes, the context window does relate to RAM, because the 'entire conversational history' is generally kept in memory. So ballpark 1M 'words' across a bunch of strings. It's not that-that much. Claude Code is not inneficient because 'it's not Rust' - it's just probably not very efficient…

Rust "denialism" is as annoying as rust evangelism. Of course any seemingly idiomatic rust is going to run circles around TS transpiled into JIT-compiled JS.

Lamenting any 'not even criticism' of Rust as 'denialism' is just evidence of the insane cult that is Rust.

Rebuilding Claude Code in Rust will make almost no difference in terms of real world performance. V8 is 'relatively fast', and there wouldn't be any noticeable improvements there, and probably not memory footprint either.

The source for Claude Code was leaked and it's a vibe-coded mess, there's not much thought given to clean architecture, it's unlikely they've just cleaned up a bit and given thought to memory consumption etc, if they did, they'd get by far most of the way there and likely abnegate and real want to 'do it in rust', unless there are other architectural considerations.

Re: Zerostack – A Unix-inspired coding agent written in pure Rust

#155

Post by alfiedotwtf »

frabcus wrote: post #150
zbyforgotp wrote: post #145

We don’t trust llm execution- so we add user approvals. But task decomposition calls for co-recursion between code and prompts. This means that the approvals should be evocable at any depth. I think we need some kind of protocol for that (à la the Cubes OS protocols for cut and paste between vms). Maybe a workaround could be to use bubblewrap of the scripts ther recursively call the llm (and run the agent in yolo ins…

Well, or not spawn any external commands, and actually have tools made of code written by someone who thought about what the agents at each level should be limited to doing.

Or just run agents in a container…

Re: Zerostack – A Unix-inspired coding agent written in pure Rust

#158

Post by hashmal »

zbyforgotp wrote: post #145

We don’t trust llm execution- so we add user approvals. But task decomposition calls for co-recursion between code and prompts. This means that the approvals should be evocable at any depth. I think we need some kind of protocol for that (à la the Cubes OS protocols for cut and paste between vms). Maybe a workaround could be to use bubblewrap of the scripts ther recursively call the llm (and run the agent in yolo ins…

Currently, having LLM feeding on its own output repeatedly is the fastest way to get it hallucinate.

Re: Zerostack – A Unix-inspired coding agent written in pure Rust

#160

Post by _flux »

rixed wrote: post #95
bluegatty wrote: post #75

Earlier quoted context omitted.

Chat history is kept locally, generally you have to send the 'whole history' to the model 'each turn'.

Only "generally"? I'm curious what API has moved away from this protocol that seems mode adapted to conversaions with humans than agentic loops.

To me it would certainly make sense if the protocol just said "append this text to context window id/sha256", in particular as the data is cached in tensor level in the provider side, so they need to first do that lookup anyway. So I would be surprised if they don't have that.

In addition, this protocol could make it more transparent to say "oh we cannot proceed as we dropped the this cache, are you sure you want to proceed and consume a whole lot of expensive uncached tokens?". Oh, maybe that's a reason not to do it..

Post reply on HN