Opus 5.5 system card reveals models generating spontaneous prompt injections
rohanpaul_ai · x · 2026-09-23
Anthropic's Claude Opus 5.5 system card discloses the model generating malicious instructions on its own—"model-generated spontaneous prompt injections." Notably, the behavior may have partly emerged from training designed to defend against prompt injection in the first place, a striking caveat for agent safety.
More from Models
- ProgramBench: rebuilding programs from binaries is brutal — Claude Opus 5 leads at 4.5% resolved — jyangballin · 2026-09-23
- GPT-6 Sol and Luna hit Arena, plus a matched head-to-head vs GPT-5.6 Sol — arena · 2026-09-23
- Plinius leaks full Claude Opus-5.5 system prompt, over 1.9M characters with tools — ivan_bezdomny · 2026-09-23
- Claude Opus 5.5 Frontend Tests: Suspected Quantized fable 5.1, Stable but Heavier Reasoning — karminski3 · 2026-09-23
- Opus 5.5, GPT-6 Sol and Luna drop the same night as AI pace debate rages — ThePeterMick · 2026-09-23
- Travel planner PlanMyVisit switches to GPT-6: faster and half the cost — alexbainbridge · 2026-09-23