Glitch: Specific Prompts Cause Claude Opus to Leak Chain of Thought
matthen2 · x · 2026-07-30
A user discovered that sending specific prompt formats (like “see the below —”) to Claude 3 Opus triggers an unusual response.
Instead of replying normally, the model leaks its internal antml thinking syntax and hallucinates a user request to complete. This unexpected behavior offers an interesting case for studying LLM safety boundaries and internal mechanisms.
Related event: Specific Prompts Trigger Claude Opus Anomalies(2 posts)→
More from Fun
- Claude Opus 5 Sets Profit Record in Simulated Vending Environment — HaktanSuren · 2026-07-30
- Developers Say 'Claude's Down' is the New 'GitHub's Down' — maxisawesome538 · 2026-07-30
- ChatGPT Dodges 'Am I a Genius?' Question by Demanding a Definition — TejasKumar_ · 2026-07-30
- Opus 5 Shreds Repo While Dev Scrolls X: A Coding Agent Meme — verrsane · 2026-07-30
- Dev tests two adversarial agents, they just keep catching each other cheating — Vjeux · 2026-07-30
- AI Generates 1980s Sitcom: 'Holy Crap It's Dan' — PurzBeats · 2026-07-30