Anthropic said it stopped several attempts this year by scientists to use its technology for research that could help develop biological weapons, according to a Financial Times report cited by ChainCatcher. In a report on malicious uses of its models, the company described five cases in which actors allegedly tried to evade safeguards by obscuring the purpose of their work and bypassing control measures. One example involved a researcher from an “unsupported region” who used Claude over several weeks to plan experiments related to avian influenza. Anthropic said its safety filters restricted that work to its weakest-performing model. The company added that it could not determine whether the scientist intended to cause harm, noting that the same information needed to develop and manufacture bioweapons could also be used for vaccine research. Anthropic said it has banned the accounts referenced in the report, but did not disclose the researchers’ institutions or the countries where the incidents took place.
Anthropic said it blocked several attempts this year by scientists to use its technology for research that could aid the development of biological weapons, according to a Financial Times report cited by ChainCatcher.
The company described five cases in a report on malicious uses of its models. Anthropic said the actors involved tried to get around control measures and obscured the purpose of their research to avoid safety protections.
Anthropic said it shared the cases in hopes of prompting discussion across the AI industry and among governments on emerging biological risks and how to respond to them.
One case involved a researcher from an “unsupported region” who used Claude over a period of several weeks to plan experiments related to avian influenza. Anthropic said its safety filtering system limited that work to its weakest-performing model.
The company also said it could not determine whether the scientist intended to cause harm, because the same information required to develop and produce biological weapons could also be used in vaccine research.
Anthropic said it has banned the accounts mentioned in the report, but did not disclose the institutions tied to the researchers or the countries where the incidents occurred.
This article was originally published by Bit.Fan. For more cryptocurrency news and market insights, visit www.bit.fan. Disclaimer:
The market information, project data, and third-party content displayed on this platform are for industry information sharing only and do not constitute any form of investment advice or return commitment.
Cryptocurrency trading carries high risks. Users should fully assess their risk tolerance and make independent decisions. All profits, losses, and legal responsibilities are borne by the users themselves.
