I hereby claim:
- I am rtack on github.
- I am rtack (https://keybase.io/rtack) on keybase.
- I have a public key ASDQahByGbf5Srqs5g5HvM-yk4U7DRHxnnn_XEiJFCHcNQo
To claim this, I am signing this object:
| //// | |
| Helpful links | |
| Graphgist Syntax: https://gist.github.com/nawroth/5956246 | |
| Submit Graphgist here: | |
| http://portal.graphgist.org/submit_graphgist | |
| // Helpful info. | |
| Graph Gist will use the property name sorting first alphabetically to display as the legend. --> change the property names. | |
| //// |
I hereby claim:
To claim this, I am signing this object:
| type: object | |
| properties: | |
| specversionsssss: | |
| description: The version of the SMG Real Estate event specification. Follows Semantic versioning. | |
| type: string | |
| enum: | |
| - '1.1.0' | |
| source: | |
| description: Value of the *service* tag in CloudFormation. |
| type: object | |
| properties: | |
| specversionsssss: | |
| description: The version of the SMG Real Estate event specification. Follows Semantic versioning. | |
| type: string | |
| enum: | |
| - '1.1.0' | |
| source: | |
| description: Value of the *service* tag in CloudFormation. |
A pattern for building personal knowledge bases using LLMs.
This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.
Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.