Microsoft is making significant changes to its AI development strategy by establishing a new division called “CoreAI – Platform and Tools”. CEO Satya Nadella announced this transformation, aiming to achieve in three years what previously took 30 years. The new division will consolidate several key teams, including development, AI platform, and key teams from the … Read more
Cisco has introduced AI Defense, a system designed to protect AI systems from attacks and misuse, ensuring the secure behavior of AI models. This software is specifically developed for businesses to reliably create, deploy, and operate AI applications. According to the manufacturer, AI Defense integrates into the network structure to detect and fend off threats … Read more
To prevent misuse, companies like OpenAI or Anthropic have given their chatbots a set of behavioral rules. However, as many simple experiments since the breakthrough of ChatGPT have shown, these can be easily bypassed to “jailbreak” the bots, freeing them from their self-imposed restrictions. This has been confirmed by a study commissioned by Anthropic, the … Read more
Anthropic, a research company, has shown that AI models can be easily confused and tricked into giving forbidden responses. They have demonstrated that large language models can be “jailbroken” with minimal effort. In this context, “jailbreaking” means making AI models ignore their own safety measures. To prove this, Anthropics researchers developed a simple algorithm called … Read more