A fundamental flaw leaves LLMs strikingly vulnerable to attack

This article doesn't make any sense. An LLM is just the model. This is why you have things like Guardrails and sandboxes. Also you guard the inputs for the LLM prompt the same way you guard against SQL injection attacks.

It's a bit like saying "If you give someone unlimited access to the database they can run queries!"

The security doesn't come from how you train the LLM, it comes from how you guard the input and output tokens.