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

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

github.com

Post reply on HN
Print view View original

131–140 of 140 posts

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

#132

Post by hek2sch »

frocodillo wrote: post #34
portly wrote: 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

First of all, this is more than just note taking. It appears to be a (yet another) harness for coordinating work between agents with minimal human intervention. And as such, shouldn’t part of the point be to not have to build that mental model yourself, but rather offload it to the shared LLM “brain”? Highly debatable whether it’s possible to create anything truly valuable (valuable for the owner of the product that…

[dead]

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

#134

Post by drewbatcheller »

ryanshrott wrote: post #79

One practical approach that works is separating the capture layer from the promotion layer. Agents can draft freely, but anything that gets promoted to trusted status needs a human review. Some teams use a voting scheme where multiple agents independently summarize the same source, and you only promote it when they converge. The confidently wrong problem gets worse over time because bad entries get cited by other age…

The "draft freely, promote on approval" method is the only thing I think works. Anything else is open to way too many forms of context poison. And you're either buried in writing safeguards, adding review layers, or you're praying you don't hit edge cases.

You don't have to trust the capture layer. Put a reviewer agent on top with memory of what's been approved and rejected, keep a human in the loop on the close calls. Over time the reviewer gets calibrated and the human review queue shrinks.

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

#138

Post by najmuzzaman »

hansmayer wrote: post #130
najmuzzaman wrote: post #120

Earlier quoted context omitted.

yes, and we should expose it. today the wiki location is hardcoded to ~/.wuphf/wiki/. making it a config field is a quick change. just filed an issue: https://github.com/nex-crm/wuphf/issues/310

I mean did you really need someone on HN to tell you that? Makes me wonder what else have you offloaded onto the statistical parrot.

nicht geil. are you really so full of yourself? every customization is not "required" from day-1 and is always a (maintenance and UX) disaster if you did. i have filed an issue for it but not added it to the system yet. not gonna AI slop this just for the sake of adding another feature.

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

#140

Post by adamsmark »

johntash wrote: post #117
adamsmark wrote: post #115

Earlier quoted context omitted.

I use my Openclaw setup to record notes I don't ever want to remember the details of. Here are some examples: Storing my Health Insurance's Member ID, RxBin and other data. Recording the serial number of a product I will be calling technical support for. Organizing files to be more logical and deduplicating or consolidating as needed. Whenever I want this info, I'll just ask my LLM to pull it up.

Do you use local models for these, or are you okay with giving private details to anthropic/openai? (that's one of my biggest hurdles for really adopting any useful assistant type of agent)

I want to use local LLMs, and in fact I have enough VRAM (12GB) and RAM (96GB) to do it but I gave up because it was pretty buggy with the Gemma 4 26B (A4B?) Q4 models. It also meant I had to give up local voice transcription because I needed all my VRAM dedicated to the LLM.

The other thing is I will ask an agent via Telegram to code stuff, so I want an agent that is smart enough to do it all. I prefer brute forcing with money right now. I hate when LLM make bizarre mistakes, I end up spending way too much time figuring out the issue.

I use Openrouter, so hopefully no one has built a perfect replica of me in their storage. I flip between models too.

But to be clear, I am living dangerously with agentic workflows in general. Haven't been burnt yet (other than accidentally running up a huge Gemini bill which made me switch to Codex Oauth and Openrouter for cheap Minimax 2.7)

I am moving to a commander/orchestrator model to use both frontier and cheap models and eventually a better local LLM once I buy a 5070 Ti, 3090, 64GB Mac M1 Max, 128GB Strix Halo (probably missed that train) or the AMD R9700.

Post reply on HN