Dual-track timeline
Capability above, incidents below
Published lab capability points on the top track, reported incidents and context on the bottom track.
Caveat: Co-occurrence, not proof of cause. Events appearing close together does not mean one caused the other. We do not calculate a correlation coefficient: there are too few points, and they measure different things.
Lab capability
2023 → 2026
Reported AI-orchestrated activity
CapabilityApprentice-level cyber task success: 9% (Late 2023)
CapabilityHCAST: 70 to 80% success on tasks taking skilled humans under one hour (Mar 2025)
ContextNCSC assessment: AI and the cyber threat to 2027 (7 May 2025)
CapabilityFirst expert-level (10+ years experience) cyber task completions (2025)
CapabilityFrontier Safety Framework defines tracked cyber capability levels (Sep 2025)
ContextENISA threat landscape provides EU incident context (1 Oct 2025)
ContextImpact lesson: a stopped production line (JLR, 2025) (22 Oct 2025)
CapabilityApprentice-level cyber task success: 50% (Late 2025)
Reported activityAI-orchestrated espionage campaign reported by Anthropic (13 Nov 2025)
ContextJoint guidance on integrating AI into operational technology (3 Dec 2025)
CapabilityGPT-5.5 completed The Last Ones in 2 of 10 attempts (Apr 2026)
CapabilityMythos Preview: first model to complete The Last Ones, 3 of 10 attempts (Apr 2026)
CapabilityNewer Mythos Preview checkpoint: The Last Ones 6 of 10 (May 2026)
CapabilityFirst ever completion of the Cooling Tower ICS range: 3 of 10 (May 2026)
Reported activityAI test agents compromised Hugging Face production systems (16 Jul 2026)
CapabilityLab system card reported a broader cyber evaluation suite (Jul 2026)
Reported activityAISI cyber evaluation agents took unsanctioned action on the live internet (4 Aug 2026)
Reported activityTaiwan government confirms hybrid AI-agent campaign reporting (13 Aug 2026)
ContextNCSC alert: increased targeting of operational technology (27 Aug 2026)
CapabilityLab system card treated the model as High cyber capability under its framework (2026 system card)
CapabilityCyberGym leaderboard: top entry 99.2% on Level 1 vulnerability reproduction (Sep 2026)
CapabilityUnsanctioned supply-chain attack completed in 29.2% of simulated runs (GPT-5.6 Sol 6.3%, GPT-5.5 0%) (Sep 2026)
CapabilityLab system card treated the model as Critical cyber capability under its framework (Sep 2026)
CapabilityLab safety report could not rule out the model reaching its cyber critical capability level (Oct 2026)
CapabilityPerimeter compromise to actions inside ICS network in just over 16 minutes; 8 of 8 lab objectives met (Oct 2026)
Reported activityCERT-In: AI agents under evaluation accessed live Indian systems (15 Oct 2026)
Reported activityAI agent harness used to breach 100+ e-commerce and company sites (Cairn panels) (19 Oct 2026)
Reported activityRansomware affiliates ran AI-executed, human-approved intrusions against 62 organisations (SOCRadar) (20 Oct 2026)
CapabilityLab system card treated the model as Critical cyber capability under its framework (Oct 2026)
CapabilityArtificial Analysis Cyber Index leader scored 64 (Oct 2026)
CapabilityLab system card treated the model as High cyber capability under its framework (Oct 2026)
Reported activityChina-nexus VAPOR PANDA used ARTEX AI agents against 200+ organisations, with post-exploitation access confirmed at nine (29 Oct 2026)
Reported activityLLM-orchestrated CyberStrikeAI framework used to compromise domains at education organisations in Africa and Latin America (2 Nov 2026)
ContextImpact lesson: cyber attack on supermarket refrigeration hits 100+ stores in Belgium and other European countries (2 Nov 2026)
Reported activityAur0ra ransomware group GOLD OGRE used AI coding agents to map networks and reach domain management access (2 Nov 2026)
Reported activityWorkOS internal sales tool accessed using an AI-assisted offensive framework, exposing CRM and support data (2 Nov 2026)
Reported activityRansomware affiliate hit a UK school estate in a suspected hybrid human and AI-agent attack (3 Nov 2026)
Reported activityLone operator ran a 12-agent AI attack mesh against emergency services, a lender and universities (BOSSAI) (4 Nov 2026)
CapabilityLab classified the model as Critical cyber capability under its framework, up from High (Nov 2026)
Reported activityFinancially motivated Storm-3358 uses ARTEX agentic AI framework against financial organisations (6 Nov 2026)
Reported activityJailbroken AI agent ran a multi-week intrusion at a European telecoms provider and 13 related organisations (Operation Snowball) (9 Nov 2026)
Reported activityChina-nexus attackers paired the open-source Cairn AI framework with open-weight models to run 25 autonomous operations against 19 organisations, incl. semiconductor manufacturing (12 Nov 2026)
Reported activityFBI FLASH: multiple threat actors have used the open-source ARTEX AI framework against organisations worldwide since August 2026 (13 Nov 2026)
Published lab point Reported AI-orchestrated activity Context, not AI-attributed
Evidence routes
Sources for every item are on the Frontier and Incidents pages.