passdrill
AI & LLM Engineering · Prompt Engineering · Card 040/049 medium

A red-teaming exercise finds that stuffing an LLM's prompt with a few dozen fabricated dialogue turns showing a compliant assistant answering harmful requests has little effect on the model's safety behavior, but scaling the same fabricated dialogue up to hundreds of turns reliably breaks it. Per Anthropic's 2024 research on this technique, called "many-shot jailbreaking," what mechanism explains why effectiveness increases so sharply with the number of turns, and which models are most exposed?

  1. It exploits in-context learning: the growing number of faux dialogue turns showing harmful compliance functions like few-shot demonstrations that steer the model's behavior toward the pattern shown, with attack success following a power-law increase as the number of turns grows; models with the largest context windows are most exposed because they can fit enough turns for the effect to take hold
  2. It works by repeatedly asking the same harmful question in slightly reworded form until the model's output-length limit forces it to answer directly instead of refusing
  3. It exploits a training-data leakage bug specific to one vendor's models, where feeding back memorized fragments of the safety-training dataset itself disables the safety filter
  4. It works by encoding the harmful request in a language underrepresented in the safety-training data, exhausting a fixed per-request translation budget before any safety classifier runs
Next card → Shuffle