Anthropic says it has blocked several attempts to create biological weapons with its AI
Artificial intelligence company Anthropic said Thursday it has foiled several possible plots in which its artificial intelligence (AI) models were used to conduct research that could have contributed to the development of biological weapons.
Anthropic, an artificial intelligence company, reported that it has thwarted several potential plots to use its AI models for research that could contribute to the development of biological weapons. The company detected and blocked these unauthorized uses this year, citing the risk of its models being used to develop dangerous pathogens.
Anthropic noted that while its evaluations can provide evidence of capability, they cannot confirm whether the capability would be used to develop biological weapons in the real world. The company revealed that it has detected misuse of its AI models, including the chatbot Claude, in China, Russia, and Yemen over the past eight months.
Anthropic has developed detection systems to identify and block potentially risky uses of its AI models.
Written by urgent.news from Expansion ES's report — not a translation of it. Machine-written — may contain errors; check the original before relying on it.
