Graphs solve many problems, but the graph query languages specific to each tool create yet another problem. We're struggling to figure out how to reap the benefits of graphs while minimizing the learning curve for our team.

Even if I continue to think for myself, it would be sad if my superiors and colleagues relied on AI. Is it too much to ask that my feedback on my work be provided by humans?

I was happy when the interviewer didn't have this document with them during the interview.

Let's start developing before we worry.

I am working on Liel (https://hy-token.github.io/liel/), a tool that can compare and integrate LLM memory as single file.

Instead of saving LLM memory in Markdown, I want to manage it using a graph structure to easily record the relationships between tasks and decisions, and persist when, why, and how they changed.

I've encountered a similar situation, so this post was very helpful. When I tried to post, I encountered the following message:

"We're temporarily restricting Show HNs because of a massive influx, mostly by users who aren't yet familiar with the site or its culture. You're welcome on HN! Take some time to get to know the community, become a good contributor, and then it will be fine to post an occasional Show HN. Here are some links to get you started: https://news.ycombinator.com/newsguidelines.html https://news.ycombinator.com/newswelcome.html https://news.ycombinator.com/showhn.html"

Based on the suggestions in this series of posts, I'm considering sending an email to hn@ycombinator.com.

Thank you.