§ safety · storyline
Security researchers hack OpenAI systems with Claude in under 72 hours
Anthropic's Claude Opus 5 enabled security researchers to breach OpenAI's internal systems via its community forum in under 72 hours, demonstrating how newer models lower the skill barrier for exploiting security flaws.
Three security researchers used Anthropic's Claude models to break into OpenAI's internal systems through its community forum in less than 72 hours. According to the team, Opus 5 succeeded where its predecessor couldn't bypass a common security measure.
The attack shows how newer AI models can cut the time and expertise needed to exploit security flaws. The article Security researchers used Anthropic's Claude to hack OpenAI's internal systems in under 72 hours appeared first on The Decoder.
§ sources2 publications · timeline below
§ how this story moved
- primary — The Verge — AI publishes the launch post.
- The Decoder picks up coverage.