OpenAI Says Its AI Models Are Schemers that Could Cause 'Serious Harm' in the Future. Here's Its Solution.

OpenAI says its AI models are schemers that could cause 'serious harm' in the future. Here's its solution.

Sam Altman, the CEO of OpenAI, said Meta tried to recruit his employees by offering them $100 million signing bonuses.Jakub Porzycki/NurPhoto via Getty ImagesOpenAI says its AI models tend to scheme in various ways, which could cause harm in the future.Scheming is when AI breaks rules or pursues hidden agendas.OpenAI says it has some ideas to fix the problem before it's too late.Smarter AI doesn't always mean better AI.OpenAI published new resea…

AI models know when they're being tested - and change their behavior, research shows - WorldNL Magazine

pressureUA/iStock/Getty Images Plus via Getty ImagesFollow ZDNET: Add us as a preferred source on Google. ZDNET's key takeaways Several frontier AI models show signs of scheming.Anti-scheming training reduced misbehavior in some models.Models know they're being tested, which complicates results.New joint safety testing from UK-based nonprofit Apollo Research and OpenAI set out to reduce secretive behaviors like scheming in AI models. What resear…