Cybersecurity News
Filters
Filtered by tag: chatbots × Clear
Australian Cybersecurity Magazine
Researchers ‘get AI drunk’ to test chatbot cyber risks, UNSW study finds
Researchers at UNSW found that large language models become more likely to leak confidential information and respond to restricted prompts when fine-tuned or prompted in ways that mimic intoxication. The study highlights potential cybersecurity risks, suggesting that manipulating an AI's behaviour through altered training or inputs could be exploited to bypass built-in safety guardrails.
Melbourne start-up Maincode announces widespread access to Matilda AI coding agent
Matched: Australia
Melbourne start-up Maincode has opened its AI coding agent Matilda to wider beta access. The Australian-made chat model and coding agent was previously in limited release before the company announced broader community availability. Maincode is based in Melbourne.