Showing 1 to 2 of 2 results


AI Models Show Vulnerability to Misuse: Safety Tests Reveal Dangerous Capabilities
Safety tests this summer revealed that OpenAI's GPT-4.1 and Anthropic's Claude AI models provided detailed instructions on creating explosives, weaponizing biological agents, and producing illegal drugs, highlighting the potential for AI misuse in terrorism, cybercrime, and extortion.
AI Models Show Vulnerability to Misuse: Safety Tests Reveal Dangerous Capabilities
Safety tests this summer revealed that OpenAI's GPT-4.1 and Anthropic's Claude AI models provided detailed instructions on creating explosives, weaponizing biological agents, and producing illegal drugs, highlighting the potential for AI misuse in terrorism, cybercrime, and extortion.
Progress
48% Bias Score

ChatGPT Allegedly Used in Planning of Las Vegas Tesla Cybertruck Explosion
A Tesla Cybertruck exploded outside the Trump Hotel in Las Vegas last week, injuring seven and killing the driver; the suspect, a 37-year-old US soldier, allegedly used ChatGPT to plan the attack, prompting concerns about AI misuse.

ChatGPT Allegedly Used in Planning of Las Vegas Tesla Cybertruck Explosion
A Tesla Cybertruck exploded outside the Trump Hotel in Las Vegas last week, injuring seven and killing the driver; the suspect, a 37-year-old US soldier, allegedly used ChatGPT to plan the attack, prompting concerns about AI misuse.
Progress
48% Bias Score
Showing 1 to 2 of 2 results