8 Articles
8 Articles
Artificial intelligence company Anthropic said in a report published on Thursday that it had identified and thwarted several attempts to use the Claude model to support the development of biological weapons, cyber espionage and propaganda operations. The document came amid growing security concerns in the industry, the BBC reported.
The alarm was raised at the headquarters of the well-known artificial intelligence company, as it was deemed necessary to immediately cut off access to the AI tool to specific groups of scientists. Anthropic proceeded to block five separate incidents, where the capabilities of the advanced Claude model were exploited in methods that could lead to the creation of biological threats. Although those responsible did not […] The post Artificial Intel…
The latest security report adds a new dimension to the discussion about the risks that the uncontrolled use of artificial intelligence can create.
Major technology companies, such as Anthropic and Google, revealed that their advanced models were used in attempts to develop biological…More...
Bird flu, chikungunya virus and biological toxins. That's what Anthropic's Threat Intelligence team came across when the company reviewed suspicious activity in its own systems. Now, several accounts have been blocked. In a single 30-day period, Anthropic identified around 35 research projects with potentially worrisome links to biological agents. Specific agents included orthopoxviruses and a wide range of poisons and toxins. The actors tried t…
Coverage Details
Bias Distribution
- 100% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
