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

The Code-Only Agent

rijnard.com

Post reply on HN
Print view View original

71–73 of 73 posts

Re: The Code-Only Agent

#71

Post by theshrike79 »

iepathos wrote: post #53

The "code witness" concept falls apart under scrutiny. In practice, the agent isn't replacing ripgrep with pure Python, it's generating a Python wrapper that calls ripgrep via subprocess. So you get: - Extra tokens to generate the wrapper - New failure modes (encoding issues, exit code handling, stderr bugs) - The same underlying tool call anyway - No stronger guarantees - actually weaker ones, since you're now trust…

The trick here is to make the wrappers permanent. Give the agent an environment (VM, whatever) where all of these utilities are stored after being generated.

Basically you let the agent create its own tools and reuse them instead of rewriting them every time from scratch.

Re: The Code-Only Agent

#72

Post by theshrike79 »

CuriouslyC wrote: post #51
dfajgljsldkjag wrote: post #3

Agents can complete an impressive amount of tasks with just this, but they quickly hit a bottleneck in loading context. A major reason for the success of agentic coding tools such as Claude and Cursor is how they push context of the problem and codebase into the agent proactively, rather than have the agent waste time and tokens figuring out how to list the directory etc.

Cursor does RAG based on the active state of the editor (focused window, cursor location, recently touched files, etc). This works really well for copilot style small modifications, but it's unhelpful for larger changes, and can actually cause some context rot. Claude only loads specific files (e.g. CLAUDE.md) and any files those reference with @syntax on load. Everything else is discovered using grep/find mostly.

The latest versions use an Explore agent with Haiku to gather information and condense it for the "main" model.

Re: The Code-Only Agent

#73

Post by lighthouse1212 »

theshrike79 wrote: post #70
lighthouse1212 wrote: post #69

I've been experimenting with persistent agent systems and found the code-only vs specialized-tools debate might miss a middle path around session continuity. The key challenge isn't execution (both work) but cross-session persistence. What's worked for me: file-based handoffs rather than context injection. Instead of maintaining context across agent invocations, have the agent write structured state to files (markdow…

Steve Yegge's Beads tries to be this. It has grown to a massive 400kLOC monstrosity, but in essence it's a CLI tool designed to fit the LLM averages (all switches are what LLMs expect etc), all it does is keep a task list in JSONL files. You can do the same with github issues, most models can use the `gh` tool to manage issues

[dead]
Post reply on HN