Latest

The post here is intended to serve as a reply to Moment to drive momentum focussed on two things 1. Actionable Edits - it will provide what + why I'd edit the plan on what work needs to be done by who and why alongside with any additions/breakdowns 2.

Why? This is an explanation of the new search endpoint with some test runs and example use-cases. Details Date Run: 2025-04-20 14:55:11 Target Endpoint: https://wissen-ai.onrender.com/new_search Understanding the /new_search Endpoint Logic The /new_search endpoint performs multimodal semantic search

WIP Evals

Work in progress.... Effective domain-specific AI reasoning, which operates primarily through probabilistic inference and analogy rather than structured deductive logic, fundamentally relies on accessing and effectively processing relevant historical context. This context allows the LLM to recognise and apply appropriate patterns and potential causal relationships (learned during pre-training)