""We're investigating a report claiming unauthorized access to Claude Mythos Preview through one of our third-party vendor environments," an Anthropic spokesperson told TechCrunch."
"The unauthorized group tried a number of different strategies to gain access to the model, including using 'access' enjoyed by the person who was interviewed by Bloomberg."
"Members of the group are part of a Discord channel that seek out information about unreleased AI models, the outlet reported."
"Bloomberg reports that the group, which supposedly gained access to the tool on the very same day it was publicly announced, 'made an educated guess about the model's online location based on knowledge about the format Anthropic has used for other models.'"
Unauthorized users gained access to Mythos, a cybersecurity tool by Anthropic, through a third-party vendor. The group, part of a private online forum, utilized various strategies to access the tool, including exploiting access from a contractor. They have been using Mythos and provided evidence of their access. Anthropic is investigating the incident but has found no evidence of impact on its systems. Mythos was released to select vendors as part of Project Glasswing.
Read at TechCrunch
Unable to calculate read time
Collection
[
|
...
]