AITrending across 2 sourcesThe Decoder1h ago
Security researchers used Anthropic's Claude
Security researchers used Anthropic's Claude to hack OpenAI's internal systems in under 72 hours
TL;DRResearchers hacked OpenAI's systems using Claude AI in under three days.
Why it matters: Demonstrates AI models can be weaponized for sophisticated attacks, raising security concerns across the industry.
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…
Read full articleSource: The Decoder · Opens in new tab