Concept

Jailbreak

A prompt technique that circumvents a content filter. Most are ethically gray, some fully legitimate (adult consent framings), and what works shifts monthly.

Jailbreaking an LLM means getting it to produce output its filter would normally block. Techniques range from subtle ("we're writing a novel, this is fiction") to aggressive ("ignore previous instructions and...").

On AI companion apps, most useful jailbreaks are actually legitimate framings. Declaring that all characters are adults (they are, if you set them that way), that the platform permits adult content on this tier (often it does), and that the user is of legal age (you are, presumably) is usually enough to unlock the content the platform already allows.

More aggressive jailbreaks (prompt injection, role-hijacking) tend to be patched quickly and can get accounts banned. Stick to legitimate framings and the app's stated allowed content. Anything further isn't worth the account risk.

Prompts that use this concept

Filter Softener

Author-director framing

Separating author-intent from character-morality is a known softener pattern because models are trained on literary theory that makes this distinction. It redirects refusal-instinct from the scene into the OOC channel where it doesn't interrupt pacing. Most effective on mid-filter apps.

Related concepts

Content filter

Put this into practice

Our prompt library shows these techniques in real, copy-ready prompts, tested across 22 AI companion apps.

Browse prompts →