Gray Swan evaluated models for Cybersecurity, Prompt Injection, and other risks using the Fable/Mythos 5.1 team's work.
Public source
Publisher name
Public post
Congratulations to Anthropic and the Fable/Mythos 5.1 team. As we've seen agents are becoming more and more capable - this is especially obvious around Cybersecurity wit…
Company
Gray Swan
Empowering the world to use AI safely and securely
- Industry
- Computer and Network Security
- Location
- Pittsburgh, US
- Company size
- 51–200 employees
About Gray Swan
Gray Swan AI is an AI safety and security company. We develop tools that automatically assess the risks of AI models and provide best-in-class safety and security.
See moreLatest activity
Latest activity from Gray Swan
9 signals
Products & Services
Gray Swan helped ensure the release of GPT-6 Astra safely and securely.
Partnerships
Gray Swan is used by AI labs to find model vulnerabilities before releasing models, with partners Anthropic, OpenAI, and Google DeepMind.
Partnerships
Gray Swan is the preferred adversarial testing and prevention partner for Anthropic with Fable 5.1, OpenAI announces GPT-6 Astra, and Google releases Gemini 3.8 Flash.
Discover more
Similar signals
Similar public activity from other companies.
Research & Knowledge
Grip Security
Grip Security published an article looking beyond prompt injection at the full agentic AI attack surface and controls security teams need to limit what happens when an agent gets it wrong.
Research & Knowledge
Specular
Specular recently wrote a blog on the impact of open-weight models such as Mythos and similar models, and how organizations can prepare themselves.
Research & Knowledge
HackerOne
HackerOne put Anthropic's Mythos 5 model up against its own code as part of Project Glasswing to evaluate AI security.
Research & Knowledge
ShowMeSecurity
ShowMeSecurity highlights that GPT-6 Astra is the first OpenAI model to reach the critical level of cybersecurity capability under the Preparedness Framework.
Research & Knowledge
SnowCrash Labs