Posts

Using an LLM as a database

Using an LLM as a database:  From Wikipedia:  "BASE stands for [B]asically [A]vailable, [S]oft state, and [E]ventually consistent: the acronym highlights that BASE is opposite of ACID, like their chemical equivalents. ACID databases prioritize consistency over availability — the whole transaction fails if an error occurs in any step within the transaction; in contrast, BASE databases prioritize availability over consistency: instead of failing the transaction, users can access inconsistent data temporarily: data consistency is achieved, but not immediately." LLMs use context windows to interface between their pre-training and RAG knowledge-bases and the user with whom they are interacting.  The context window is soft-state, and it vanishes to nothing when it is no longer needed.  That is, after it is either abandoned or filled up to capacity. The BASE approach to databases is the linear opposite, in all four (4) dimensions, from the ACID approach.  Nearly all da...
Image
Who Is Responsible For A.I. Doing Damage? Who Is Responsible When A.I. Tools Help Commit Crimes? (right now) Social media companies: "Hey, we just provide the platform. We're not responsible for what people put on it or how they use it." (very soon) AI companies: "Hey, we just provide the intelligence. We're not responsible for what people put into it or how they use it." Maybe some of that "very soon" with AI companies...is happening now?  How many of the largest such companies have already had that discussion in some conference room or boardroom? A.I. Ethics is a growing field, and one that seems to be a very small part of the overall chatter of the world's fast-paced development of AIs. It seems LLMs and the like are a powerful means to diffuse out (or absolve entirely) responsibility in ethnics, law, and morality.

Master Plan v2: Local-first LLM Knowledge Base, Cloud Portfolio, & Study Log System

  Master Plan v2: Local-First AI Knowledge Base, Cloud Portfolio, and Study Log System Living markdown document for daily use, revision, and future planning Introduction This document is the current master plan for building a local-first, open-source, LLM-friendly knowledge base that will also become a cloud-hosted professional interface for recruiters, prospective employers, collaborators, and public readers. This project is not only a software system. It is also part of a larger learning program. Its purpose is to help develop practical skill in: Python document processing LLM workflows retrieval and search cloud/web deployment software architecture technical writing reflective documentation portfolio presentation The project will serve several roles at once: a personal knowledge base for study and project work a local document-processing and retrieval system a cloud-hosted portfolio and access interface a structured public record of...