[ExI] AIs for criminals

[BillK]

While experts are concerned about AI safety and nations are signing
agreements to develop safe AI, the criminal underworld is actively
developing malicious AIs (Malla).
As AIs become more powerful, what will be the result of humans
deliberately developing malicious AIs?
Is this humanity committing suicide?
BillK

<https://venturebeat.com/security/top-five-strategies-from-metas-cyberseceval-3-to-combat-weaponized-llms/>
Quotes:
Top five strategies from Meta’s CyberSecEval 3 to combat weaponized LLMs
Louis Columbus     September 3, 2024

The goal: Get in front of weaponized LLM threats
Malicious attackers’ LLM tradecraft is moving too fast for many
enterprises, CISOs and security leaders to keep up. Meta’s
comprehensive report, published last month, makes a convincing
argument for getting ahead of the growing threats of weaponized LLMs.
----------------