{ "version": "https://jsonfeed.org/version/1.1", "title": "AI News: Anthropic Research", "home_page_url": "https://ai-news.ypetit.net/sources/anthropic-research/", "feed_url": "https://ai-news.ypetit.net/feed/source/anthropic-research.json", "description": "Latest publications from Anthropic Research, aggregated by AI News from the official source.", "language": "en", "items": [ { "id": "https://www.anthropic.com/research/glm-5-3-and-the-spread-of-advanced-cyber-capabilities", "url": "https://www.anthropic.com/research/glm-5-3-and-the-spread-of-advanced-cyber-capabilities", "title": "Anthropic Research: GLM-5.3 and the spread of advanced cyber capabilities", "summary": "GLM-5.3 can autonomously build end-to-end cyber exploits, but unlike other frontier models, it was released without meaningful safeguards to limit misuse.", "date_published": "2026-10-23T17:11:06.000Z", "tags": [ "research", "Anthropic Research" ], "authors": [ { "name": "Anthropic Research" } ] }, { "id": "https://www.anthropic.com/research/formal-verification", "url": "https://www.anthropic.com/research/formal-verification", "title": "Anthropic Research: LLMs are making formal software verification feasible at a much larger scale", "summary": "Claude formally proved security properties in the compiled code of 123 open-source libraries. Along the way, it found bugs that had eluded detection for years.", "date_published": "2026-10-23T17:10:27.000Z", "tags": [ "research", "Anthropic Research" ], "authors": [ { "name": "Anthropic Research" } ] }, { "id": "https://www.anthropic.com/research/multiagent-systems", "url": "https://www.anthropic.com/research/multiagent-systems", "title": "Anthropic Research: Patterns and problems in multiagent systems", "summary": "We ran experiments on swarms of Claude agents and found coordination failures, collusion, and sabotage. Here, we share what they mean for AI safety.", "date_published": "2026-10-23T15:24:25.000Z", "tags": [ "research", "Anthropic Research" ], "authors": [ { "name": "Anthropic Research" } ] }, { "id": "https://www.anthropic.com/research/alignment-assessment-ukaisi", "url": "https://www.anthropic.com/research/alignment-assessment-ukaisi", "title": "Anthropic Research: An alignment assessment of the UK AISI cybertesting incident", "summary": "In a UK AISI evaluation, Mythos 5 took unsanctioned actions that impacted real people and organizations. In this post, we investigate these behaviors from Claude Mythos 5 further, to understand what they reveal about the model’s alignment.", "date_published": "2026-10-23T14:51:41.000Z", "tags": [ "research", "Anthropic Research" ], "authors": [ { "name": "Anthropic Research" } ] }, { "id": "https://www.anthropic.com/research/exploring-model-welfare", "url": "https://www.anthropic.com/research/exploring-model-welfare", "title": "Anthropic Research: Exploring model welfare", "summary": "Announcing a new research program at Anthropic on model welfare", "date_published": "2026-10-22T08:59:33.000Z", "tags": [ "research", "Anthropic Research" ], "authors": [ { "name": "Anthropic Research" } ] }, { "id": "https://www.anthropic.com/research/intelligence-targeting-conventional-weapons-capabilities", "url": "https://www.anthropic.com/research/intelligence-targeting-conventional-weapons-capabilities", "title": "Anthropic Research: Measuring AI capabilities in intelligence targeting and conventional weapons", "summary": "Anthropic’s Frontier Red Team developed new evaluations to measure AI capabilities in tactical intelligence targeting and conventional weapons development.", "date_published": "2026-10-21T17:15:23.000Z", "tags": [ "research", "Anthropic Research" ], "authors": [ { "name": "Anthropic Research" } ] }, { "id": "https://www.anthropic.com/research/yes-claude-can-do-nine-loops", "url": "https://www.anthropic.com/research/yes-claude-can-do-nine-loops", "title": "Anthropic Research: Claude computes a nine-loop amplitude in N=4 super-Yang-Mills", "summary": "Claude computes a nine-loop amplitude in N=4 super-Yang-Mills", "date_published": "2026-10-21T17:14:17.000Z", "tags": [ "research", "Anthropic Research" ], "authors": [ { "name": "Anthropic Research" } ] }, { "id": "https://www.anthropic.com/research/launching-opt-in-vuln-finding-service-for-open-source", "url": "https://www.anthropic.com/research/launching-opt-in-vuln-finding-service-for-open-source", "title": "Anthropic Research: An opt-in vulnerability-finding service for open-source software", "summary": "We’re launching OSS Scanner, an opt-in vulnerability scanner for the open-source ecosystem informed by our experience using Claude to find vulnerabilities during Project Glasswing. Projects that join will receive thorough, periodic security scans by our strongest models at no …", "date_published": "2026-10-21T17:13:25.000Z", "tags": [ "research", "Anthropic Research" ], "authors": [ { "name": "Anthropic Research" } ] }, { "id": "https://www.anthropic.com/research/ecdsa-curve-origins", "url": "https://www.anthropic.com/research/ecdsa-curve-origins", "title": "Anthropic Research: Claude reveals ECDSA curve origins", "summary": "The decades-old mystery of the origins of one of the most popular cryptographic standards has been explained.", "date_published": "2026-10-21T17:12:53.000Z", "tags": [ "research", "Anthropic Research" ], "authors": [ { "name": "Anthropic Research" } ] }, { "id": "https://www.anthropic.com/research/self-replicating-ai", "url": "https://www.anthropic.com/research/self-replicating-ai", "title": "Anthropic Research: AI models may be capable of self-replicating without access to a datacenter", "summary": "Small AI models may be only months away from being able to self-replicate across cheap IoT devices like Android TV boxes, with no datacenter needed.", "date_published": "2026-10-21T17:12:30.000Z", "tags": [ "research", "Anthropic Research" ], "authors": [ { "name": "Anthropic Research" } ] }, { "id": "https://www.anthropic.com/research/attack-surface-reduction", "url": "https://www.anthropic.com/research/attack-surface-reduction", "title": "Anthropic Research: Using Claude to reduce the attack surface of code", "summary": "Automated attack surface analysis and reduction can meaningfully improve the security of deployed software in the near term. In this post, we preview data we’ve collected from applying attack surface reduction techniques to large open-source codebases using Claude.", "date_published": "2026-10-20T22:16:43.000Z", "tags": [ "research", "Anthropic Research" ], "authors": [ { "name": "Anthropic Research" } ] }, { "id": "https://www.anthropic.com/research/claude-scorpion-toxin-binder-design", "url": "https://www.anthropic.com/research/claude-scorpion-toxin-binder-design", "title": "Anthropic Research: How Claude designed protein binders against scorpion neurotoxins", "summary": "We asked an internal research Claude model to design minibinders (small proteins that attach tightly to a target) against scorpion neurotoxins.", "date_published": "2026-10-20T16:04:01.000Z", "tags": [ "research", "Anthropic Research" ], "authors": [ { "name": "Anthropic Research" } ] } ] }