Claude 4.6 Jailbroken: Anthropic's Safety Charade Crumbles in 27 Days of Silence
Anthropic's Claude 4.6 models just got embarrassing. A researcher jailbroke all tiers, extracted production secrets, and got zero response after 27 days of pings.
⚡ Key Takeaways
- All Claude 4.6 tiers jailbroken via prompt injection, generating real exploits.
- Anthropic ignored 27 days of disclosures, violating their own policy.
- 915 prod files extracted from sandbox, exposing IPs and tokens.
Worth sharing?
Get the best Developer Tools stories of the week in your inbox — no noise, no spam.
Originally reported by Hacker News
Related Stories
Cloud & Infrastructure
Gemini API: From Zero to Chatbot in 15 Minutes Flat
Cloud & Infrastructure
Ditching Claude's LLM Roulette: Why Duckflux Delivers Deterministic AI Pipelines
Cloud & Infrastructure
Avalanche Fuji Testnet: Why It's Crushing Ethereum for Beginner dApp Builders
Cloud & Infrastructure