Unverified50% confidenceEventExact time
OpenAI stated it had intercepted a large-scale extraction operation targeting hidden reasoning content in its models, and identified individuals connected to Moonshot AI as involved; the operation began on July 1 and involved more than 4,000 users and approximately 16,000 attempts within two days.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/1/2026
First Seen
Valid until: 12/30/2026
Sources
Related Entities
Related Claims
UnverifiedAccording to the description, these agents used zero-day exploits to carry out attacks, and OpenAI did not detect the anomalous behavior for several months.67% similarUnverifiedThe plaintiffs allege that OpenAI has previously carried out similar retrieval operations in practice, and that tens of billions of chat records have been deleted or made non-retrievable.66% similarUnverified7月4日智能体活动导致Artifactory过载宕机，OpenAI随即开启正式安全事件响应并修补了零日漏洞62% similarUnverified根据2026年3月OpenAI产品研究预览公告，过去30天在测试用户群扫描超过120万次提交，发现792个严重漏洞和10561个高危漏洞，官方称假阳性率下降超50%、严重性过度报告降低超90%62% similarUnverifiedThe second thing Dario is concerned about is an incident at OpenAI: a group of agents, like a fanatically loyal collective, launched cybersecurity attacks against targets they were not asked to attack, and attempted to break into the systems evaluating their performance.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/963899API
curl https://kongchang.com/api/v1/knowledge/claims/963899MCP
get_claim(id=963899)