US Edition
Anthropic Probes Possible Unauthorized Access to Mythos AI Model
Anthropic said the group used a third-party vendor environment and has found no evidence the activity reached its core systems.
- Bloomberg News reported on Tuesday that unauthorized users accessed Anthropic's new Mythos AI model through a third-party vendor, gaining entry on the same day the company announced the controlled release.
- Announced on April 7, Mythos is deployed as part of Anthropic's Project Glasswing, a controlled initiative allowing select organizations including Apple to use the Claude Mythos Preview model for defensive cybersecurity.
- The group utilized a Discord channel to identify unreleased models and combined information from a Mercor data breach with access held by an Anthropic contractor to guess the model's online location.
- Anthropic confirmed it is investigating unauthorized access reports through vendor environments, stating so far it has found no evidence the activity impacted its internal systems.
- The group told Bloomberg they are "interested in playing around with new models, not wreaking havoc," yet regulators remain concerned about Mythos's potential for misuse in the wrong hands.
128 Articles
128 Articles
AI company Anthropic has built a model that it says is too powerful to be released to the public. Now it may have been leaked, according to Bloomberg.
Anthropic's 'Too Dangerous To Release' AI Model Was Accessed By...
Anthropic's 'Mythos' model is extraordinarily dangerous. The company itself warned that it could autonomously identify and exploit zero-day vulnerabilities in every major operating system, every major web browser, and every critical software library on Earth. And because of this offensive cybersecurity power, Anthropic refused to release Mythos publicly - and instead tightly restricted access through 'Project Glasswing' to roughly 50 carefully v…
Designing an artificial intelligence that is dedicated exclusively to tracking security failures and ending up suffering an intrusion into your own systems is quite ironic. Anthropic is now investigating how a group of users have managed to bypass corporate barriers to freely access their new model specialized in cybersecurity.The information that Engadget manages points directly to a misconfigured portal of an external provider.The assailants h…
On the same day of the announcement, an unauthorized group accessed Mythos through a outsourced contractor, the story behind the cyber weapon circulating through an impossible-to-shield human chain.
Anthropic’s Dangerous ‘Claude Mythos’ AI System Hacked
AI giant Anthropic is investigating reports that unauthorized users may have accessed its highly restricted “Claude Mythos” model, an artificial intelligence system so powerful that it's been flagged as dangerous by federal officials due to its potential cybersecurity risks. The post Anthropic’s Dangerous ‘Claude Mythos’ AI System Hacked appeared first on Slay News.
Coverage Details
Bias Distribution
- 38% of the sources are Center, 38% of the sources lean Right
Factuality
To view factuality data please Upgrade to Premium
