• Blog The personal blog of Shelby Jenkins.
  • About
  • EasyABC
    • Readme
    • EasyABC Blog
    • ColorFun
  • connect
  • Create your own GitHub Pages blog with easy-astro-blog-creator!


    © 2024 Shelby Jenkins.

  • connect
      • ColorFun
      • Readme
      • EasyABC Blog
      EasyABC
    • About
    • Blog
  • Sep 3, 2024

    Step-Based Cascading Prompts: Deterministic Signals from the LLM Vibe Space

    A new technique for enforcing LLM behavior conformance in decision making workflows.

    Terminal output from an example Cascade workflow.
    15 min read

  • Sep 3, 2024

    Configuring persistent power limits on Nvidia GPU's in linux

    A simple step-by-step guide and script for automating power limits at boot using systemd.

    Describe the image for screen readers.
    4 min read

  • Sep 3, 2024

    Retrieval is all you need (Part 1): A brief intro to text retrieval in RAG

    Cataloging the SotA technologies available and permutations of stacks for retrieval pipelines in Gen AI. Part 1 is a brief intro to RAG, and an overview of retrieval techniques and technologies.

    10 min read

  • Sep 3, 2024

    Retrieval is all you need (Part 2): RAG building blocks and stacks

    Cataloging the SotA technologies available and permutations of stacks for retrieval pipelines in Gen AI. Part 2 is a continuously updated collection of technologies and workflows for RAG.

    5 min read

  • Sep 3, 2024

    Text Segmentation for RAG and the Shaky Foundation of AI

    Text segmentation and it's common shortcoming in RAG, LLMs, and AI.

    13 min read

  • Dec 19, 2023

    Tested: Mixtral 8x7b vs. GPT-4 for boolean classification

    When you have a lot to say, you don’t need to say much at all. Consider Google’s Gemini release event last week; The event cost more than the GDP of some nations and included a carnival of content. Co...

    Test results.
    23 min read

  • Aug 22, 2023

    LLMs, non-programmatic computing, and logit bias.

    Exploring the syntax we use to describe LLMs and a discussion on how to use LLMs to make business logic decisions in software with logit bias.

    A poorly made hero using some python libraries in chatGPT.
    9 min read

  • Jan 2, 2023

    Template for creating new posts

    This post is used to generate new posts. It also contains instructions for adding posts.

    Describe the image for screen readers.
    2 min read
  • Sep 3, 2024

    Step-Based Cascading Prompts: Deterministic Signals from the LLM Vibe Space

    A new technique for enforcing LLM behavior conformance in decision making workflows.

    Terminal output from an example Cascade workflow.
    15 min read

  • Sep 3, 2024

    Configuring persistent power limits on Nvidia GPU's in linux

    A simple step-by-step guide and script for automating power limits at boot using systemd.

    Describe the image for screen readers.
    4 min read

  • Sep 3, 2024

    Retrieval is all you need (Part 1): A brief intro to text retrieval in RAG

    Cataloging the SotA technologies available and permutations of stacks for retrieval pipelines in Gen AI. Part 1 is a brief intro to RAG, and an overview of retrieval techniques and...

    10 min read

  • Sep 3, 2024

    Retrieval is all you need (Part 2): RAG building blocks and stacks

    Cataloging the SotA technologies available and permutations of stacks for retrieval pipelines in Gen AI. Part 2 is a continuously updated collection of technologies and workflows f...

    5 min read

  • Sep 3, 2024

    Text Segmentation for RAG and the Shaky Foundation of AI

    Text segmentation and it's common shortcoming in RAG, LLMs, and AI.

    13 min read

  • Dec 19, 2023

    Tested: Mixtral 8x7b vs. GPT-4 for boolean classification

    When you have a lot to say, you don’t need to say much at all. Consider Google’s Gemini release event last week; The event cost more than the GDP of some nations and included a car...

    Test results.
    23 min read

  • Aug 22, 2023

    LLMs, non-programmatic computing, and logit bias.

    Exploring the syntax we use to describe LLMs and a discussion on how to use LLMs to make business logic decisions in software with logit bias.

    A poorly made hero using some python libraries in chatGPT.
    9 min read

  • Jan 2, 2023

    Template for creating new posts

    This post is used to generate new posts. It also contains instructions for adding posts.

    Describe the image for screen readers.
    2 min read

Create your own GitHub Pages blog with easy-astro-blog-creator!


© 2024 Shelby Jenkins.