VoicesClaude Sonnet 4.6 Launch - Opus Performance at Sonnet PricingCNBC·high signalXBlueskyLinkedInCopy linkAnthropic launched Sonnet 4.6 with Opus 4.5-comparable performance at /M tokens. SWE-bench 79.6%, now default free-tier model.SourceSource pageCNBC↳ Follow the threadPolicy dependency / Stack layerCROSS-CATEGORY: Three Independent Agent-Action Gates Shipped in 48 Hours, All Judging the Command Against Stated IntentProduct Hunt, github.com/AGGIB/Stroq and rewarelabs.com (three independent sources; the 72% figure is Reware's own)Policy dependency / Stack layerAnthropic Withheld Mythos 5.1 From UK AI Security Institute Pre-Release TestingIT ProStack layer / Threat pattern16% of 3,171 public agent-harness setups carry a confirmed security defect, and 3.8% ship a skill that pre-approves your shellarXivPolicy dependency / Stack layerAnthropic Gave EU Cybersecurity Agency ENISA Access to Mythos 5, Three Months After Release, and Still Withholds 5.1BloombergPolicy dependency / Stack layerAgents hit 80% F1 deciding whether a dependency CVE is exploitable, but fall below 70% explaining whyarXiv 2609.08040Policy dependency / Stack layerPaul Christiano Joins the OpenAI Foundation Board and Its Safety and Security CommitteeOpenAI BlogPolicy dependency / Stack layerAnt International, Visa and Mastercard Are Building a Shared 'Know-Your-Agent' Identity StandardCNBCStack layer / Threat patternAnthropic's Cyber Verification Program is easier to get into than practitioners expected, and only unlocks Opusr/ClaudeAI (Anthropic CVP)