{"data":{"id":"95726588-9e2d-48f2-a233-892443e7be31","title":"AI R&D-relevant model capabilities are improving rapidly and are getting harder to measure","summary":"This METR research post presents evidence from capability evaluations of public models relevant to AI R&D acceleration, up to Opus 5.5 and GPT-6 Astra. The authors say current public evidence is insufficient to rule out drastic AI R&D acceleration within the next couple of years, which they define as capabilities improving so fast that humans can no longer meaningfully assess and react to catastrophic risks. Their results include models usually matching or outperforming skilled humans on coding and optimization tasks, and time horizons on the combined TH1.1 and TH2 suite doubling roughly every 3.6 months.","solution":"N/A -- no mitigation discussed in source.","labels":["research","industry"],"sourceUrl":"https://metr.org/blog/2026-11-20-q4-2026-capability-update/","publishedAt":"2026-11-20T08:00:00.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["OpenAI","Anthropic"],"affectedVendorsRaw":["Opus 5.5","GPT-6 Astra"],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-11-20T08:00:00.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":null,"aiComponentTargeted":null,"llmSpecific":true,"classifierConfidence":0.85,"researchCategory":"industry","atlasIds":null}}