Well I couldn't find any other thorough dataset on this topic, so in that sense this is non-obvious since it took weeks to assemble the information. And it was fun doing it using the LLM Wiki technique.

▲

JumpCrisscross 3 hours ago | parent [-]

> it was fun doing it using the LLM Wiki technique

What is that?

▲

rnxrx 3 hours ago | parent | next [-]

The general idea is to have the LLM maintain longer-term context/background by storing it in a format/structure that's akin to a standard Wiki. The result is (hopefully) a series of human-readable and editable documents that's developed and maintained by the agent.

There's great coverage of it at https://gist.github.com/karpathy/442a6bf555914893e9891c11519...

It's actually also now a base capability in the Hermes agent and has been really helpful for me, at least.

▲

chambertime 3 hours ago | parent | prev [-]

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

▲

JumpCrisscross 3 hours ago | parent [-]

Could you share the tools you used to do this? I'd love to organise my esoteric research side quests like this.

▲

chambertime 2 hours ago | parent [-]

Git + claude code in yolo mode. In the first prompt, I passed it Kaparthy's gist, and had it put together a high level plan of all of the sections that needed to be written to complete a vision I provided. Essentially put together a complete wiki on everything for getting global hardware certification.

I then had it loop once an hour. It would pick the next wiki to write, research it, gather raw sources, and then synthesize the wiki for me and push. I could nudge it in between hours if I wanted.

▲

JumpCrisscross 2 hours ago | parent [-]

Do you add this as a skill or permanent prompt, making it always maintain wikis in the background? Or do you direct it to make these only when you're in the project?

	▲	chambertime 2 hours ago \| parent [-]
		There's skills if you want. I didn't want to do that since I don't feel like I need the smarts to work on the LLM wiki in every coding session. I like to keep my context clean and scoped to what I'm working on. I am running this in a long running session that spawns a subagent once an hour. So the context of the main session doesn't get out of control.