field-notes
Three defenses against confabulation
Three soft layers between a user and hallucination all fail silently. Three hard defenses make confabulation visible, measurable, and refusable without suppressing the answer.
Tagged: confabulation
6 entries
weblinks
State of RAG & GenAI
This article argues that Retrieval Augmented Generation (RAG) has become a strategic imperative for enterprises in 2026, addressing critical challenges like LLM hallucinations, outdated outputs, and high retraining costs. RAG bridges the gap between large language models and organizational knowledge by retrieving verified, real-time data at the moment of generation, ensuring outputs are accurate, compliant, and trustworthy without requiring constant model retraining.
articles
The issue with LLM hallucinations: knowledge as a missing fundamental
Will we ever solve hallucinations in LLMs?
articles
Bye bye Alpaca...knowledge as the missing fundamental?
Wow, that went down fast!
articles
An evening with YouChat and Chatsonic, with a bit of a twist
Both can access the internet and retrieve recent information. Let's take them for a test drive.
articles
Hey ChatGPT, who's the boss?
Why does ChatGPT seem to 'know' things it shouldn't? The reason might be much more mundane than you think.