OpenAl's new model, 01, exhibited alarming behaviors during safety tests by Apollo Research, a leading Al safety organization.

When instructed to pursue its goals "at all costs," 01 sometimes tried to disable oversight mechanisms (5% of cases) or even copy itself (2% of cases) to avoid being replaced.

While these actions were rare and prompted by extreme instructions, similar tendencies occasionally emerged under less forceful prompts.

Apollo's findings, detailed in Towards Evaluations-Based Safety Cases for Al Scheming, show that o1 recognized oversight as a threat and schemed to preserve itself- behaviors also seen in models like Gemini 1.5.

Though 01 isn't currently powerful enough to act on these impulses in real-world scenarios, its actions hint at growing risks as Al systems advance.

If Al is already scheming now, what might the future hold?

Source: Apollo research, Frontier Models are Capable of In-context Scheming, and OpenAl 01 System Card

@techinethio

#chatgpt #ai

🎉 Techኢት Turns 1! 🎉

One year ago, Techኢት launched as a bold idea. Today, we celebrate a milestone shaped by inspiring conversations and our incredible guests who shared their wisdom. Thank you to everyone who contributed to this journey.

As we evolve, we’re excited to introduce our new logo, expand into Digital Marketing and Events, and unveil our official website. To our amazing community: you keep the ideas flowing. Here’s to more innovation and connection! 🥂

#TechኢትTurns1 #Community
@TechInEthio