[flagged]
[dead]
Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)
91–100 of 140 posts
Re: Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)
#92The title of this post doesn't match the repo at all
fair. the post title leads with the wiki because the Karpathy framing is the angle i think this audience cares about, but the wiki ships as part of WUPHF (an open source collaborative office for AI agents) and the repo README naturally leads with the broader product. i should have surfaced "ships as part of WUPHF" earlier in the post body.
if you want the wiki only, install WUPHF and only use the wiki layer. the promotion flow, fact log, and /lookup work without the multi-agent office around them.
Re: Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)
#93I 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
I think there‘s a serious issue with people using AI to do an immense amount of busywork and then never look at it again. Colossal waste.
It's almost akin to eating without thinking... just a waste, no nutrition. Additionally, damaging.
Re: Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)
#94Reviewed: https://zby.github.io/commonplace/agent-memory-systems/revie... It is a third llm wiki on front page in 24 hours! Obviously it is a hot topic. I have my own horse in that race - so I might not be objective - but I've compiled a wishlist for these system: https://zby.github.io/commonplace/notes/designing-agent-memo... I wish there was a chance for collaboration - everybody coding their own system seems like…
yes, generative slot machines are isolating. You say you "wish there was a chance"? As if there isn't?
Re: Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)
#95[dead]
Re: Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)
#96[dead]
Re: Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)
#97I 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
been thinking the same, but I imagine you could explicitly separate notes and slop, eg something as simple as cron job that goes through all your notes and creates a PR if there's some easy win: typos, inconsistencies, tags, etc
I've been coding like this lately: if I'm too lazy to review a new non-critical section/unit tests, I'll mark it as `// SLOP`; later, if I have to, I'll go through the entire thing, and unmark
shitty tests are better than no tests, as long as you your expectations are low enough
Re: Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)
#98I 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.
I've been running a variation of this for ~6 months. What seems to work: a background process that reads conversation transcripts after sessions end and then extracts decisions/rejected approaches into structured markdown. I review before I promote it into the context.
Re: Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)
#99[dead]
Re: Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)
#100Cool 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".
let's talk about real stuff. we built an AI-native CRM backed by HubSpot founder Dharmesh Shah last year before this, had revenue, iterated to focus on context graph infra which looked like the right moat to focus on, did enterprise PoCs, and all of that distilled into this personal project i built on the side to help my own work. turned out to be right interface for making context infra usable.
the team is of 4 HubSpotters who built HubSpot's largest platforms - search, nav, notifs, permissions, AI.
we are in the process of opening up large pieces of our enterprise context architecture to WUPHF and also ship the cloud enterprise version of WUPHF (https://nex.ai/new-home).