Live data from Hacker News

Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)

github.com

21–30 of 140 posts

Re: Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)

#22
Put AI in your product name, make billion dollars. Put Karpathy in your blog article, get hired by Anthropic as Principal engineer. Milk money as long as fad last. No one is thinking about customer needs, everyone is trying to wash hands in the wave as it last.

Re: Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)

#25
LLM models and the agents that use them are probabilistic, not deterministic. They accomplish something a percentage of the time, never every time.

That means the longer an agent runs on a task, the more likely it will fail the task. Running agents like this will always fail and burn a ton of token cash in the process.

One thing that LLM agents are good at is writing their own instructions. The trick is to limit the time and thinking steps in a thinking model then evaluate, update, and run again. A good metaphor is that agents trip. Don't let them run long enough to trip. It is better to let them run twice for 5 minutes than once for 10 minutes.

Give it a few weeks and self-referencing agents are going to be at the top of everybody's twitter feed.

Re: Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)

#26

I love that so many people are building with markdown ! But also would like to understand how markdown helps in durability - if I understand correctly markdown has a edge over other formats for LLMs. Also I too am building something similar on markdown which versions with git but for a completely different use case : https://voiden.md/

I read the durability thing as markdown files are very open, easy to find software for, simple and are widely used. All of this together almost guarantees that they will he viewable/usable in the far future.

So markdown will be great for distribution in the future.

Re: Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)

#27
post #18

Cool idea. But is anyone actually building real stuff like this with any kind of high quality? Every time I hear someone say "I have a team of agents", what I hear is "I'm shipping heaps of AI slop".

+100 for this comment.

Re: Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)

#29
post #20

I don't understand the point of automating note taking. It never worked for me to copy paste text into my notes and now you can 100x that? The whole point of taking notes for me is to read a source critically, fit it in my mental model, and then document that. Then sometimes I look it up for the details. But for me the shaping of the mental model is what counts

Then you have never worked at a large enough codebase or across enough many projects?

Re: Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)

#30
post #20

I don't understand the point of automating note taking. It never worked for me to copy paste text into my notes and now you can 100x that? The whole point of taking notes for me is to read a source critically, fit it in my mental model, and then document that. Then sometimes I look it up for the details. But for me the shaping of the mental model is what counts

The few scientific studies out there actually show a degradation of output quality when these markdown collections are fully LLM maintained (opposed to an increase when they’re human maintained), which I found fascinating.

I think the sweet spot is human curation of these documents, but unsupervised management is never the answer, especially if you don’t consciously think about debt / drift in these.

Post reply on HN