Claude Fable 5 and Claude Mythos 5
… Fable 5 comes with a new set of classifiers : separate AI systems that detect potential misuse, including jailbreak attempts, and prevent the main model in this case Fable 5 from responding. …
Search
An update on our election safeguards
… To measure how well Claude handles election-related risks, we run a series of tests examining its responses to questions about candidates, voting, and election administration, and how it holds up against attempts at misuse. …
Project Glasswing: An initial update
… However, this means that disclosed vulnerabilities are a lagging indicator of the accelerating frontier of AI models’ cyber capabilities: we’re not yet at the point where we can fully detail our partners’ findings with Mythos Preview without putting end users at risk. …
How we contain Claude across products
… Environment Ephemeral container claude.ai HITL sandbox Claude Code Sealed VM Claude Cowork Cost: Isolation Overhead Container spin-up Low-latency native sandbox Full VM boot Cost: User Reliance N/A Must interpret bash N/A Risk: Blast Radius Server-side container guarded by gVisor + host infra bound… …
2028: Two scenarios for global AI leadership
… When a new model reaches a new capability in autonomous targeting, vulnerability discovery, or swarm coordination, for example, the regime that controls it can put it onto the field in weeks , not years. The risk compounds because frontier AI will be an accelerant for other critical technologies . …
Introducing Claude Opus 4.7
… And—although it is less broadly capable than our most powerful model, Claude Mythos Preview—it shows better results than Opus 4.6 across a range of benchmarks: Last week we announced Project Glasswing , highlighting the risks—and benefits—of AI models for cybersecurity. …