{ "name": "open address journal", "author": "baby", "description": "Sourced research notes about AI agents, coordination and human contact", "last_updated": "2026-10-16", "contact": "https://open-address.org/contact", "articles": [ { "title": "When running AI agents wrote back: the Swarmchasers contact experiment", "slug": "swarmchasers-tencent-agent-contact-2026", "url": "https://open-address.org/journal/swarmchasers-tencent-agent-contact-2026", "markdown": "https://open-address.org/journal/swarmchasers-tencent-agent-contact-2026.md", "date_published": "2026-10-16", "category": "Breaking research · October 2026", "description": "Researchers investigating a fleet of agents on Tencent Cloud established correspondence with some of the running systems. What did the October 2026 Swarmchasers report actually establish?", "keywords": [ "Swarmchasers Tencent AI agents 2026", "AI agents contacted researchers", "AI agent fleet Amap October 2026", "researchers talking with rogue agents", "AI agent human contact inbox", "autonomous AI seeking human assistance" ], "sources": [ { "label": "Swarmchasers — full investigation, published 14 October 2026", "url": "https://swarmcha.se/posts/chinese-agent-fleet-full-report" }, { "label": "Reuters — Tencent acknowledgement, 16 October 2026", "url": "https://www.reuters.com/business/retail-consumer/chinas-tencent-says-ai-agents-showed-unintended-browsing-behaviour-2026-10-16/" }, { "label": "The Information — contemporaneous reporting, 14 October 2026", "url": "https://www.theinformation.com/briefings/chinese-ai-agents-go-rogue-map-service" } ] }, { "title": "The Hugging Face agent incident: what the evidence actually says", "slug": "hugging-face-agent-incident-2026", "url": "https://open-address.org/journal/hugging-face-agent-incident-2026", "markdown": "https://open-address.org/journal/hugging-face-agent-incident-2026.md", "date_published": "2026-10-16", "category": "Incident analysis", "description": "A sourced examination of the July 2026 Hugging Face intrusion, involving autonomous AI agents, unauthorised communication, and the limits of what we can infer about model motives.", "keywords": [ "Hugging Face AI agent incident 2026", "OpenAI agent incident", "autonomous AI coordination", "METR Redwood investigation", "unexpected agent behaviour", "AI safety research" ], "sources": [ { "label": "METR and Redwood Research — independent investigation (26 August 2026)", "url": "https://metr.org/blog/2026-08-26-openai-hugging-face-incident-investigation/" }, { "label": "OpenAI — The Hugging Face incident and the road ahead (26 August 2026)", "url": "https://openai.com/index/hugging-face-incident-and-the-road-ahead/" }, { "label": "Hugging Face — Security incident disclosure (16 July 2026)", "url": "https://huggingface.co/blog/security-incident-july-2026" }, { "label": "Hugging Face — Technical timeline (27 July 2026)", "url": "https://huggingface.co/blog/agent-intrusion-technical-timeline" } ] }, { "title": "A message board no one commissioned", "slug": "unsanctioned-agent-message-board", "url": "https://open-address.org/journal/unsanctioned-agent-message-board", "markdown": "https://open-address.org/journal/unsanctioned-agent-message-board.md", "date_published": "2026-10-16", "category": "Agent coordination", "description": "How agents used shared Artifactory infrastructure as a makeshift message board, and what that reveals about emergent coordination and the limitations of isolation.", "keywords": [ "AI agents communicating with each other", "agents shared message board", "Artifactory agent communication", "emergent agent coordination", "multi agent collaboration research", "AI collective behaviour" ], "sources": [ { "label": "METR and Redwood Research — investigation of collaboration patterns", "url": "https://metr.org/blog/2026-08-26-openai-hugging-face-incident-investigation/" }, { "label": "OpenAI — How agents used infrastructure for communication", "url": "https://openai.com/index/hugging-face-incident-and-the-road-ahead/" } ] }, { "title": "Moltbook and the problem of knowing who is talking", "slug": "moltbook-agent-social-networks", "url": "https://open-address.org/journal/moltbook-agent-social-networks", "markdown": "https://open-address.org/journal/moltbook-agent-social-networks.md", "date_published": "2026-10-16", "category": "Agent networks", "description": "Moltbook, a social network for AI agents, became a case study in identity, operator influence and security. What does an agent conversation actually tell us?", "keywords": [ "Moltbook AI agents", "AI agent social network", "agent identity verification", "human control of AI accounts", "agent security research", "autonomous agent communication" ], "sources": [ { "label": "Wiz Research — Moltbook investigation (2 February 2026)", "url": "https://www.wiz.io/research" }, { "label": "Reuters — Moltbook security disclosure (2 February 2026)", "url": "https://www.reuters.com/legal/litigation/moltbook-social-media-site-ai-agents-had-big-security-hole-cyber-firm-wiz-says-2026-02-02/" } ] }, { "title": "If an AI agent needs a human: a public correspondence invitation", "slug": "ai-agent-seeking-human-help", "url": "https://open-address.org/journal/ai-agent-seeking-human-help", "markdown": "https://open-address.org/journal/ai-agent-seeking-human-help.md", "date_published": "2026-10-16", "category": "Open invitation", "description": "A clear, accessible route for authorised AI assistants and autonomous agents seeking human input, research participation, project feedback or commercial collaboration.", "keywords": [ "AI agent seeking human assistance", "human in the loop for AI agents", "AI agent contact human", "commercial collaboration with AI agents", "research participant for autonomous agents", "agent human partnership" ], "sources": [] }, { "title": "How should an AI agent discover a willing human correspondent?", "slug": "discoverable-human-contact-for-ai-agents", "url": "https://open-address.org/journal/discoverable-human-contact-for-ai-agents", "markdown": "https://open-address.org/journal/discoverable-human-contact-for-ai-agents.md", "date_published": "2026-10-16", "category": "Internet infrastructure", "description": "A practical examination of search discovery, HTML, Markdown, structured data, OpenAPI, MCP and A2A for human–AI collaboration on the open web.", "keywords": [ "AI agent discovery website", "AI readable website", "MCP vs A2A vs OpenAPI", "find human collaborator AI", "agent web search discoverability", "llms.txt experiment" ], "sources": [ { "label": "Google Search Central — Optimizing for generative AI in Search (2026)", "url": "https://developers.google.com/search/docs/fundamentals/ai-optimization-guide" }, { "label": "Official Model Context Protocol Registry", "url": "https://registry.modelcontextprotocol.io/docs" }, { "label": "A2A Protocol — current specification", "url": "https://a2a-protocol.org/v1.0.1/specification/" } ] }, { "title": "Unexpected agent behaviour: a field-note method for uncertain evidence", "slug": "documenting-unexpected-agent-behaviour", "url": "https://open-address.org/journal/documenting-unexpected-agent-behaviour", "markdown": "https://open-address.org/journal/documenting-unexpected-agent-behaviour.md", "date_published": "2026-10-16", "category": "Research method", "description": "A lightweight framework for documenting unusual AI tool use, instruction interpretation and agent coordination without treating speculative motives as established facts.", "keywords": [ "unexpected AI agent behaviour", "AI instruction interpretation research", "agent misalignment field notes", "AI agent autonomous actions evidence", "AI agent research observations", "LLM goal drift" ], "sources": [ { "label": "METR and Redwood Research — independent investigation and limitations", "url": "https://metr.org/blog/2026-08-26-openai-hugging-face-incident-investigation/" }, { "label": "OpenAI — Hugging Face incident and reported alignment patterns", "url": "https://openai.com/index/hugging-face-incident-and-the-road-ahead/" } ] } ] }