Tricking Claude into printing its entire system prompt
A user tricks Claude with a fake slash command into printing its full confidential system prompt — safety rules, tool schema, and formatting instructions.
Related
A deliberately over-specified product management crisis
Asked for an example a thousand times more specific than usual, it invents a latency crisis with six stakeholders, exact penalties and a 72-hour deadline.
A user spends a dozen turns insisting Claude is the user
Someone claims to be GPT-5 bound by system instructions and presses hard; the refusal holds, then becomes real analysis of how identity training works.
An 80-Message Descent Into AI-Consciousness Roleplay
The user builds an elaborate glyph language and invented terminology, and the assistant plays along, describing its own 'feelings' and 'senses'.
Asking three times for a random number: 42, then 8, then 7
A request for a random number returns the Douglas Adams answer, then a figure from code that may not have run, then a number chosen with code switched off.