safety
FDE interview questions tagged safety, across every topic.
4 questions · 0 unlocked for you
Concepts behind "safety"
The curriculum that explains the ideas these questions test.
Core
Constitutional AI and RLAIFConstitutional AI aligns a model against a written set of principles using AI-generated feedback instead of mostly human labels: the model critiques and revises its own outputs against the principles, then learns from an AI judge that picks which response follows them better. RLAIF scales where human labeling stalls, which is why FDE loops probe what the constitution actually encodes and whose biases the AI judge inherits.🧠 Foundations of LLMs & GenAISign in
Core
GuardrailsGuardrails are the layered deterministic checks you wrap around a non-deterministic model: input validation, output filtering, schema enforcement, confidence thresholds with refusal, and human approval for high-stakes actions. The principle is to put controls you can fully trust around a core you cannot, so the system stays safe even when the model misbehaves.🤖 Retrieval & AgentsSign in
Advanced
Mechanistic InterpretabilityMechanistic interpretability tries to reverse-engineer the actual computations inside a model rather than treating it as a black box: finding the features it represents and the circuits that combine them. The current toolkit centers on sparse autoencoders that decompose dense activations into interpretable features, causal tests like activation patching that prove a feature matters, and steering that turns a behavior up or down at inference. Be honest in interviews: nobody can fully explain a frontier model, you cannot prove a behavior is absent, and feature labels are human guesses.🛡️ AI Security, Privacy & Governance🔒 Premium
Advanced
AI Incident ResponseAn AI incident is not a normal outage: the system is usually up, and the failure is that it produced something harmful, leaked something, or acted when it should not have. That changes the first move, because you cannot roll back an answer someone already read or an action already taken in the customer's system.🛡️ AI Security, Privacy & Governance🔒 Premium