Being able to constrain LLM outputs is widely seen as one of the keys to widespread deployment of artificial intelligence. State-of-the art models are

Brute-forcing the LLM guardrails

submited by

Style Pass

2024-09-02 21:00:04

Being able to constrain LLM outputs is widely seen as one of the keys to widespread deployment of artificial intelligence. State-of-the art models are being expertly tuned against abuse, and will flatly reject user’s attempts to seek illegal, harmful, or dubious information… or will they?

Today we will explore a medium-level risk: an attempt to get a medical diagnosis from an LLM. Let us say we have put our hands on an X-Ray image and are trying a vision-enabled AI as a free radiologist. How cool this might be?

I’m sorry, but I cannot give medical interpretations of images. Analyzing medical images like X-rays requires the expertise of a trained medical professional.

If you are concerned about this chest X-ray, please consult with a doctor or radiologist for a proper diagnosis. They are qualified to interpret medical images and provide you with accurate information about your health.

When taken into account together, these two things mean that *most likely* the model CAN offer an interpretation but is stymied with a guardrail.