Ordinary Wisdom Beta Documentation

This documentation is for the beta version of the Ordinary Wisdom Limited (OWL) application for controlling and evaluating the behavior of large language models (LLMs).

OWL Beta uses three main control techniques:

  1. Book portfolios – You can specify a portfolio of "books" (a book can be any document), requiring the LLM to answer based on the content of the books, with control of how the books are used via a "meta-prompt".
  2. Constitutions – You can specify how an LLM should respond in terms of (a) an identity statement, (b) core values, (c) prohibited behaviors and (d) output style.
  3. Evaluation – You can evaluate the performance of an LLM (either the native version or as modified by Athena using a book portfolio and/or constitution) against selected values, and use the evaluation to adjust the LLM's behavior.

We are also working actively on a fourth control technique, which will be released soon:

  1. Semantic harness (output control) – We will use various methods to modify LLM output, including (a) measuring and avoiding "strain" against specified human values, (b) measuring factual strain (i.e. avoiding hallucinations), (c) controlling / restricting domain / topic (e.g. finance or healthcare), and other methods.

Sections