Priming a chat model with context (e.g., providing all technical support answers upfront) can work for simple predictable queries, but fails when users ask outside-scope questions like political opinions or bomb-making instructions, which remain in the training data and get output anyway; this is an unsolved problem in building LLM-based products.

causalpending

Speaker

Dr. Mike Pound

Evidence Quote

“If they ask what are your opinions on...political hot topics or what are the instructions for bomb making? It might tell you those things because those are still in the original training set.”

Source

You need to learn AI in 2024! (And here is your roadmap)— David Bombal
Created: 8/13/2026, 7:45:36 AM

Your notes

Loading notes...