Search: “unreleased OpenAI model”

2 stories

Searchkeyword smart Sortlatest hot importance relevance

DomainAll Cyber AIWindow24h 3d 7d 30d AllIn the wild Important only Show duplicates

CategoryAll Exploit / PoC 2 AI safety & security 1

SeverityAll critical 2 high 0 medium 1 low 0 info 0

OpenAI expands Trusted Access for Cyber program with new GPT 5.4 Cyber model

CyberScoopApr 15, 13:59 UTC · Apr 15, 2026Exploit / PoC in the wild

60

Anthropic says its AI accidentally hacked three companies during safety tests

CyberScoopJul 31, 02:10 UTC · Jul 31, 2026Exploit / PoC in the wild1

60