Unverified50% confidenceFactExact time
OpenAI officially claims that GPT-6 Cyber's rate of out-of-bounds behavior in internal testing has dropped below 1%.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
11/5/2026
First Seen
Valid until: 11/19/2026
Sources
Related Entities
Related Claims
UnverifiedIn OpenAI's internal evaluation, GPT-5.6 Cyber completes 95% of advanced cybersecurity requests, a figure referring to the response rate rather than the attack success rate.71% similarUnverifiedIn cybersecurity vulnerability reproduction and remediation tests, Large 4 scores 82%, while several open-source large models score near zero (due to outright refusal).68% similarUnverifiedSophos reduced cyberthreat investigation time by 96% by deploying OpenAI's Daybreak technology.62% similarUnverifiedFollowing the AI's zero findings, manual review discovered 6 CVE-level security issues in the curl project.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% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1140333API
curl https://kongchang.com/api/v1/knowledge/claims/1140333MCP
get_claim(id=1140333)