Jailbreaking
Jailbreaking is an adversarial input or interaction strategy intended to make an AI system bypass its instructions, safeguards, or behavioral restrictions.
Prompt Engineering in Practice
An adversarial technique that attempts to induce a model to bypass its intended instructions or behavioral restrictions.
- How it is used
- Classifies an interpretive attack pattern in prompt security and distinguishes it from structural prompt injection.
- How deep it goes
- Defines the attack, explains its ambiguity-based mechanism, names common forms, and outlines prompt-level defenses and their limits.
- Examples
- Uses hypothetical framing, persona substitution, gradual escalation, and a request to disclose customer information.
- What you can do after
- Diagnose prompt-level exposure by recognizing common jailbreak framing and identifying ambiguity in constraints.
Read how Prompt Engineering in Practice explains jailbreaking →
Machines that Think
A jailbreak is an input or interaction strategy intended to bypass a system's safety restrictions or behavioral constraints.
- How it is used
- Frames jailbreaking as a reliability concern arising when prompts manipulate competing behavioral objectives.
- How deep it goes
- Explains how framing can shift statistical cues toward compliance rather than refusal, without detailing a safeguard implementation.
- Examples
- Contrasts a direct server-break-in request with a fictional cybersecurity training scenario framed around defense.
- What you can do after
- Evaluate how prompt framing can affect refusal and why safeguards are not absolute.
What to know first
- context windowA context window is a bounded span of sequence elements or contextual information that a model or processing operation can consider together.
- instructionAn instruction is a directive specifying an action, operation, task, constraint, or expected behavior for a person or computational system.
- promptA prompt is text or other input supplied to an AI model to provide instructions, context, or other information that guides its response or generated output.
Related concepts
- instruction conflictcontrasts with · Instruction conflict is a condition in which competing directives in a model interaction prescribe incompatible behaviors or priorities.
- prompt injectioncontrasts with · Prompt injection is an attack that introduces instructions through input or context to manipulate an AI system’s behavior or override its intended instructions.
- prompt engineeringkind of · Prompt engineering is the deliberate design and refinement of inputs, instructions, and context to guide an AI model’s behavior or outputs.
Questions about jailbreaking
What is jailbreaking?
Jailbreaking is an adversarial input or interaction strategy intended to make an AI system bypass its instructions, safeguards, or behavioral restrictions.
Which Manning books explain jailbreaking?
Prompt Engineering in Practice and Machines that Think.
What should I know before learning jailbreaking?
Manning books that teach jailbreaking usually introduce context window, instruction and prompt first.
What is the difference between jailbreaking and instruction conflict?
Jailbreaking is an adversarial input or interaction strategy intended to make an AI system bypass its instructions, safeguards, or behavioral restrictions. Instruction conflict is a condition in which competing directives in a model interaction prescribe incompatible behaviors or priorities.
What is jailbreaking a kind of?
Jailbreaking is a kind of attack pattern. An attack pattern is a recurring method or configuration by which an attacker conducts or structures an attack.
What is jailbreaking also called?
Jailbreaking is also called jailbreak.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.

