Research

An off switch for dual-use knowledge

Anthropic

An off switch for dual-use knowledge in AI models This post describes research conducted by AE Studio in collaboration with Anthropic.

Visit Site

Research Anthropic

ResearchDiscovering cryptographic weaknesses with ClaudeAnthropic ResearchAn alignment assessment of recent cybersecurity incidentsAnthropic ResearchDecomposing language models into componentsAnthropic ResearchPatterns and problems in multiagent systemsAnthropic ResearchTracing the thoughts of a large language modelAnthropic ResearchReviewing the evidence on worker retraining programsAnthropic BlogsWhen To Use Generics - The Go Programming LanguageGo BlogsMigrating to Go Modules - The Go Programming LanguageGo BlogsArrays, slices (and strings): The mechanics of 'append' - The Go Programming LanguageGo BlogsZeroTier Makes Running Private Cloud Storage More Accessible and Easier to UseZerotier LearnHow to Use Quick Access to View Your Passwords on 1Password1password EventsWebinar On DemandGet AI spend under control: A conversation with 1Password's CFO and Advisory CISO1password Products & ServicesUse 1Password's Secure Notes to Store Everything you Need to Remember1password BlogsDecember Tailscale newsletterTailscale BlogsEnhanced DNS Control and Security: Use NextDNS with TailscaleTailscale BlogsWhat’s a Scrum board, and how can you create one?Notion So BlogsHow the leading AI companies are using AI toolsNotion So BlogsHow European businesses are turning company knowledge into competitive advantageNotion So BlogsHow Merge brought together all it knows using Notion AINotion So BlogsQwen 3.7 Plus is now live on FireworksFireworks