Hackers Developing Malicious LLMs After WormGPT Falls Flat

Crooks Are Recruiting AI Experts to Jailbreak Existing LLM Guardrails
Cybercrooks are exploring ways to develop custom, malicious large language models after existing tools such as WormGPT failed to cater to their demands for advanced intrusion capabilities, security researchers say. Undergrounds forums teem with hackers' discussions about how to exploit guardrails.

advanced capabilities demands discussions experts exploit forums guardrails hackers intrusion jailbreak language language models large llm llms malicious recruiting researchers security security researchers tools wormgpt