Search: “pretraining”

1 items

Searchkeyword smart Sortlatest hot importance relevance

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

CategoryAll AI research 56 Model release 14 AI safety & security 11 AI industry 7 Vulnerability 4 Research 3 Threat actor 2 Industry 2 Malware 2 Policy & legal 2 Ransomware 2 Data breach 1 Exploit / PoC 1

SeverityAll critical 5 high 5 medium 5 low 5 info 87

New research finds that Claude breaks bad if you teach it to cheat

CyberScoopNov 24, 22:41 UTC · Nov 24, 2025Exploit / PoC in the wild

60