FRESH

Hacker News

Show HN: Continual Learning with .md

31 points by wenhan_zhou

by alexbike

4 subcomments

The markdown approach has a real advantage people underestimate: you can read and edit the memory yourself. With vector DBs and embeddings the memory becomes opaque — you can't inspect or correct what the model "knows". Plain files keep the human in the loop.
The hard part is usually knowing what +not+ to write down. Every system I've seen eventually drowns in low-signal entries.

by 0xchamin

1 subcomments

is this based on Karapathy's LLM Wiki idea (link: https://gist.github.com/karpathy/442a6bf555914893e9891c11519...)? . I leveraged Karapathy's wiki idea and built MCPTube- it's a CLI and also an MCP server that turns YouTube videos into a compounding knowledge base. Check it out and let me know what you think (link: https://github.com/0xchamin/mcptube)

by _zer0c00l_

1 subcomments

Your example is with Codex - OpenAI could implement this easily on their end right? Every prompt of yours was an API call and they have a log, they can easily re-create a quick history of what you did/asked for before?

by jusasiiv

1 subcomments

Seems interesting. Ill give it a try on my agent, memory is definitely an ongoing issue. How long have you been running this in a continuous state? Also have you tried other LLM's and seen a difference on how well they can use it?

by namanyayg

3 subcomments

I've seen a lot of such systems come and go. One of my friends is working on probably the best (VC-funded) memory system right now.
The problem always is that when there are too many memories, the context gets overloaded and the AI starts ignoring the system prompt.
Definitely not a solved problem, and there need to be benchmarks to evaluate these solutions. Benchmarks themselves can be easily gamed and not universally applicable.

by dhruv3006

1 subcomments

I love how you approached this with markdown !
I guess the markdown approach really has a advantage over others.
PS : Something I built on markdown : https://voiden.md/

by sudb

1 subcomments

I really like the simplicity of this! What's retrieval performance and speed like?

by inveflo

0 subcomment

by thomasquarre

0 subcomment