VeryAI
@VeryAI
Stop spam. Prevent fraud. Verify real people.
加入 August 2025
29 正在關注 9.7K 粉絲
Agent refusals and guardrails mean nothing if they don't have a human backstop in the real world.
so hackers apparently used Claude + Grok + Kimi to automate a cyberattack on 400 banks.
but the crazy part is HOW they got around the safety guardrails:
> told models they’re in internal tests LOL
> Claude refused? → switch to Kimi
> Kimi refused too? → fall back to old-school malware
automated cyber attacks are becoming a norm apparently.
顯示更多
