Safety

What system level defenses blunt prompt injection in a tool using agent?

Select the controls that reduce prompt injection blast radius

Which guardrails belong on the output path of a customer facing endpoint?

What is the failure mode when a small medical fine-tuned model leaks verbatim credit card snippets under red teaming, and what is the standard mitigation?

Design a fine-tuning setup that teaches a model to refuse when the retrieved context lacks the answer.

A consumer facing LLM product is about to launch. Describe the safety evaluation that should run first.

What is over refusal, and how does naive safety FT cause it?

What should you do when naive safety FT makes the model refuse 'how does anesthesia work?'

How do you design the post-FT eval suite for a customer support fine-tuned model?

Which buckets MUST a post-FT eval suite include for a customer support fine-tuned model?