Show HN: 10x better performance from the Coding Harnesses with LLM-wiki | Hacker News Reader

Show HN: 10x better performance from the Coding Harnesses with LLM-wiki

llm-wiki.net

16 pointsnvk15 comments

Some say text files work even better: https://cloud.google.com/blog/products/data-analytics/how-th...

This makes total sense given that a wiki is a collection of plain text files with a few simple conventions (not markup) around formatting and linking.

Where is this 10x number coming from?

The 10x coder who wrote it: https://www.youtube.com/watch?v=d2BuP7-m5Ww

Am I to understand that in 2012 he was not a 10x coder?

from llm wiki

I've got a couple of LLM wikis running for different purposes. I just pointed Claude at Karpathy's Github Gist and said "do this" and it set up and has maintained them ever since. So far no issue with that.

Can you explain why the version linked is better?

Gist link: https://gist.github.com/karpathy/442a6bf555914893e9891c11519...

What if I only want 6x better performance? Is there a knob or slider to dial it down?

This kind of llm bragging title and AI generated webpage makes me gross.

How does this differ from https://context7.com/ ?

LLM Wiki is client-side and local-first (plain Markdown, Obsidian-friendly) designed for deep multi-agent topic research (e.g. automated thesis/counter-thesis runs, local session memory redaction).

Context7 is a hosted SaaS/on-premise MCP server indexing API/library docs (GitHub, Confluence, OpenAPI) to provide coding assistants with fresh, version-specific developer context.

Essentially: LLM Wiki compiles topic research vaults on your local disk, whereas Context7 acts as a semantic doc/API search gateway for programming.

So the benefit is in caching the resources to avoid web queries, and massaging them to make them amenable to analysis? For intellectual work I imagine it would be useful if it could access gated content, like commercial reports?

Right, it's the whole search pipeline problem defined. Check this out: https://github.com/deepbluedynamics/lume

Edit: On closer look this looks useful without the coding harness pitch.

This is not a product, its a foss lib

Reply on news.ycombinator.com