[Ekco]

there seems to be big fucking problems in the

RAG stands for Retrieval-Augmented Generation. It's a technique that combines a generative large language model (LLM) with an information retrieval system to provide more accurate, up-to-date, and factual responses by grounding the AI's output in external knowledge sources. This helps to overcome the limitations of LLMs, which can sometimes produce outdated or "hallucinated" information.

department though i noticed this when i tried to dump like 100 pdfs in a folder and have a Ollama Model retrive from it using ChromaDB + LlamaIndex and it just hallucinated like mad

saw this posted today also,

thought it was interesting to show the real world implications of using LLMs to extract information from PDFs. For context, thalamus is a company that handles the "backend" for residency programs and all the applications they receive (including handling who to invite for interviews, etc). One of the more important factors in deciding applicant competitiveness is their medical school performance (their grades), but that information is buried in PDFs sent by schools (often not standardized). So this year, they decided to pilot a tool that would extract that info (using "GPT-5o-mini": https://www.thalamusgme.com/blogs/me...for-creation-a...). Some programs have noticed there is a discrepancy between extracted vs reported grades (often in the direction of hallucinating "fails") and brought it to the attention of thalamus. Unfortunately, it doesn't look like the main company is discontinuing usage of the tool.

This video analyzes a research paper exploring the theoretical limits of embedding-based data retrieval