Entdecken

6 technologies shown

• Alignment technique Making a model's behaviour match what people want, not just what is likely.
• Constitutional AI technique Aligning a model using written principles rather than human labels alone.
• Guardrails technique Checks around a model's input and output that constrain what it can do.
• Red Teaming technique Adversarially probing a model for harmful or unsafe behaviour.
• RLAIF technique Reinforcement learning from AI feedback instead of human feedback.
• Jailbreak technique Prompt that circumvents a model's refusal behaviour.