Anthropic's periodic RSP risk reports are the primary public record of how the lab assesses its models' dangerous-capability thresholds and what safeguards gate them — directly relevant if you build on Claude and need to anticipate usage restrictions.

• articleFor more on how Claude ran this experiment and the full results, see our blog:
• articleNew Attacks on HAWK and AES Cryptographic Schemes
• articleDiscovering Cryptographic Weaknesses with Claude
• postClaude designed working protein binders for 14 of 15 targets

• articleAnthropic’s best AI model struggles to attract users as cheaper tools thrivesimonwillison.net
• articleInvestigating Three Real-World Incidents in Our Cybersecurity EvaluationsSimon Willison
• postAnthropic hands outside researchers real Claude usage dataAnthropic

Checking sign-in…

Loading comments…