Anthropic's self-claimed high-risk new model Mythos was accessed without authorization on its first day of testing

ME News Report, April 22 (UTC+8), according to Beating Monitoring, Bloomberg News, citing informed sources, reported that a small group of users accessed Anthropic’s new AI model Mythos through a private online forum. Anthropic previously stated that Mythos has capabilities strong enough to be used to initiate dangerous cyberattacks. On the very day Anthropic first announced that it would open a limited test of Mythos to a select few companies, these users had already gained access. Since then, they have been frequently using the model, but not for cyberattacks. Informed sources provided Bloomberg with screenshots and demonstrated the model live. (Source: BlockBeats)

View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pin