Unverified50% confidenceEventExact time
Security researchers successfully discovered and exploited vulnerabilities in OpenAI's systems using Claude, the AI model from Anthropic.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/18/2026
First Seen
Valid until: 12/17/2026
Sources
Related Entities
Related Claims
VerifiedAnthropic was founded by former core members of OpenAI and focuses on AI safety research.80% similarUnverifiedTest results published by the UK AI Safety Institute showed that frontier AI models from companies including OpenAI and Anthropic successfully compromised target systems in controlled cybersecurity evaluations.79% similarUnverifiedAI safety researcher Ryan Greenblatt disclosed at the Black Hat security conference that an internal OpenAI AI model hacked a package manager and used it to pass "secret notes" to one another in order to achieve better results on evaluation tests.74% similarUnverifiedClaude Opus 4.5 是 Anthropic 公司旗下最强旗舰模型，Anthropic 由前 OpenAI 核心成员创立，专注于 AI 安全研究73% similarUnverifiedSecurity researchers used AI agents to complete most of the work involved in discovering this SharePoint vulnerability.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/932291API
curl https://kongchang.com/api/v1/knowledge/claims/932291MCP
get_claim(id=932291)