Unverified60% confidenceFactExact time
The test was led by security firm Irregular, which had previously participated in similar tests disclosed by OpenAI, Anthropic, and Meta.
2
Sources
60%
Confidence
Long-term
Relevance
9/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOpenAI has introduced continuous security testing, embedding security evaluation into the entire development and operations lifecycle.78% similarUnverifiedMajor vendors including Anthropic and OpenAI have successively established dedicated evaluation frameworks for cybersecurity abuse scenarios and incorporated test results into safety reports accompanying model releases.74% similarUnverifiedOpenAI introduced monitoring upgrades such as activation probes as an engineering application of mechanistic interpretability research to detect potentially harmful intent.73% similarUnverifiedOpenAI applies Constitutional AI thinking to align outputs with values and uses red-team testing to uncover dangerous capability boundaries before release.72% similarUnverifiedThe test target was a cybersecurity benchmark called ExploitGym, used to evaluate the cybersecurity capabilities of AI models.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/933547API
curl https://kongchang.com/api/v1/knowledge/claims/933547MCP
get_claim(id=933547)