Search: “Claude Haiku”

2 stories

Searchkeyword smart Sortlatest hot importance relevance

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

CategoryAll AI safety & security 12 Model release 2 AI research 2 AI tools & infra 2 AI industry 1 AI policy 1

SeverityAll critical 0 high 2 medium 2 low 0 info 16

Every set of AI guardrails can be broken by the right prompt

Help Net SecurityJul 9, 05:49 UTC · Jul 9, 2026AI safety & security

30

GitHub Copilot Refuses Harmful Requests in Chat, Then Writes Them in Code

The Hacker NewsJul 8, 11:21 UTC · Jul 8, 2026AI safety & security1

30