Responsible AI

Keeping AI helpful, honest, fair, and safe.

Infographic: What Is AI Safety?. The work of keeping AI helpful, honest, and safe.
Beginner

What Is AI Safety?

The work of keeping AI helpful, honest, and safe.

Read the lesson →
Infographic: What Are Guardrails?. The rules and filters that keep an AI's answers safe.
Beginner

What Are Guardrails?

The rules and filters that keep an AI's answers safe.

Read the lesson →
Infographic: What Is Bias?. When unfair examples make an AI give unfair answers.
Beginner

What Is Bias?

When unfair examples make an AI give unfair answers.

Read the lesson →
Infographic: What Is Fact-Checking?. Making sure something is true before you trust it.
Beginner

What Is Fact-Checking?

Making sure something is true before you trust it.

Read the lesson →
Infographic: What Is Human Review?. People checking an AI's work to keep it safe.
Beginner

What Is Human Review?

People checking an AI's work to keep it safe.

Read the lesson →
Infographic: What Is Responsible AI?. Building AI that is helpful, honest, safe, and fair.
Beginner

What Is Responsible AI?

Building AI that is helpful, honest, safe, and fair.

Read the lesson →
Coming soon
Beginner

What Is Misinformation?

Wrong information that spreads, by accident or on purpose.

Infographic: Indirect Prompt Injection. When sneaky hidden instructions in a page or file trick an AI.
Intermediate

Indirect Prompt Injection

When sneaky hidden instructions in a page or file trick an AI.

Read the lesson →
Infographic: LLM Jailbreaking. When someone tries to trick an AI past its safety rules.
Intermediate

LLM Jailbreaking

When someone tries to trick an AI past its safety rules.

Read the lesson →
Infographic: OWASP Top 10 for LLMs. The ten most important AI security risks, one friendly poster each.
Intermediate

OWASP Top 10 for LLMs

The ten most important AI security risks, one friendly poster each.

See all ten →