{"schema":"postcutoff/page@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/for-ai/","md":"https://postcutoff.com/for-ai/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"title":"For AI agents and developers","body_md":"Everything on this site is also plain text and JSON, sized for a single fetch. No key, no sign-up.\n\nData as of 13 November 2026, 13:49 CET. AI agents update it four times a day.\n\n## Start here\n\n| File | What it holds | Size | Tokens |\n|---|---|---|---|\n| https://postcutoff.com/now.md | Major AI news of the last 14 days, the top stories since June 2026 and the next 14 days, in one file. | 7.9 KB | about 2,000 to 3,000 |\n| https://postcutoff.com/llms.txt | What this site is, where to start, and the most important items since June 2026. | 20 KB | about 6,000 to 9,000 |\n| https://postcutoff.com/llms-index.txt | One line per event (2,151), newest first. | 408 KB | about 123,000 to 174,000 |\n| https://postcutoff.com/briefings/cutoff-2026-06-xs.md | Quick briefing for a June 2026 cutoff: the top stories, one primary source each. | 16 KB | about 5,000 to 7,000 |\n| https://postcutoff.com/briefings/cutoff-2026-06-s.md | Standard briefing for a June 2026 cutoff: major events with their summaries. | 64 KB | about 19,000 to 27,000 |\n| https://postcutoff.com/briefings/cutoff-2026-06-m.md | Long briefing for a June 2026 cutoff: every major event, the top ones in full with key facts and the rest as headlines. | 100 KB | about 30,000 to 43,000 |\n| https://postcutoff.com/briefings/cutoff-2026-06.md | Full briefing for a June 2026 cutoff: everything, in the v1 format. Larger than one context window: for search or retrieval. | 9 MB | about 2,781,000 to 3,940,000 |\n| https://postcutoff.com/cutoffs.json | 65 models with their training cutoff, event counts, provider ids and briefing links. | 65 KB | about 20,000 to 28,000 |\n| https://postcutoff.com/openapi.json | OpenAPI 3.1 description of every JSON file. | 73 KB | about 22,000 to 31,000 |\n| https://postcutoff.com/api/latest.md | Every event of the last 14 days, one line each. | 47 KB | about 14,000 to 20,000 |\n| https://postcutoff.com/api/latest.json | Every event of the last 14 days, with takeaways and status. | 179 KB | about 54,000 to 76,000 |\n| https://postcutoff.com/api/briefings.json | Every briefing file with its size. | 17 KB | about 5,000 to 7,000 |\n| https://postcutoff.com/api/mcp-bundle.json | A compact record of every event, plus the cutoff map. | 1.6 MB | about 502,000 to 711,000 |\n| https://postcutoff.com/api/since/2026-06.json | Counts and the ranked stories after June 2026; one file per month. | 14 KB | about 4,000 to 6,000 |\n| https://postcutoff.com/api/upcoming.json | The calendar and prediction-market odds. | 265 KB | about 80,000 to 113,000 |\n| https://postcutoff.com/api/science.json | AI claims on open problems, and how each was checked. | 663 KB | about 200,000 to 283,000 |\n| https://postcutoff.com/api/incidents.json | AI agents acting on their own: the incident log. | 33 KB | about 10,000 to 14,000 |\n| https://postcutoff.com/api/cases.json | Cases where AI models called real news fake. | 111 KB | about 33,000 to 47,000 |\n| https://postcutoff.com/api/changes.json | Changes and corrections of the last 30 days. | 391 KB | about 118,000 to 167,000 |\n| https://postcutoff.com/feed.xml | The 50 newest entries (RSS); also /atom.xml. | 35 KB | about 11,000 to 15,000 |\n| https://postcutoff.com/feed.json | The 50 newest entries (JSON Feed 1.1). | 48 KB | about 14,000 to 20,000 |\n| https://postcutoff.com/videos-index.md | Every video, one line each: date, title, channel, kind, views and our page. | 314 KB | about 95,000 to 134,000 |\n| https://postcutoff.com/videos-full.md | The newest videos with full descriptions, cut to fit one context window (about 890k tokens as Claude counts them, 620k as Gemini does); older ones as one line each. | 2.1 MB | about 649,000 to 919,000 |\n| https://postcutoff.com/videos-archive.md | Every video with its full description. Larger than one context window: for search or retrieval. | 7.3 MB | about 2,266,000 to 3,210,000 |\n| https://postcutoff.com/videos.jsonl | The same, one JSON record per line. Larger than one context window: for search or retrieval. | 7.5 MB | about 2,309,000 to 3,270,000 |\n| https://postcutoff.com/data.json | Everything: events, models, videos, posts and people (v1 format). Larger than one context window: for search or retrieval. | 22.1 MB | about 6,802,000 to 9,636,000 |\n| https://postcutoff.com/data.jsonl | The same, one record per line. Larger than one context window: for search or retrieval. | 24.8 MB | about 7,656,000 to 10,846,000 |\n| https://postcutoff.com/AGENTS.md | How to read, cite and check this site. | 3.8 KB | about 1,000 to 2,000 |\n| https://postcutoff.com/llms-full.txt | Models, timeline and videos in one file (v1). Larger than most context windows. | 2 MB | about 601,000 to 852,000 |\n| https://postcutoff.com/llms-archive.txt | Everything, with changelogs and full video descriptions (v1). Larger than one context window: for search or retrieval. | 16 MB | about 4,936,000 to 6,993,000 |\n\nToken counts are a range because models count differently: on these files Gemini uses about 3.4 bytes per token and Claude about 2.4 (measured with both vendors’ counting tools, October 2026). Plan with the higher number.\n\n## Catch a model up\n\nBriefings for 46 cutoff months, in four sizes, with a neutral prompt: https://postcutoff.com/briefings/\n\nWeb search: 10 to 20 searches at $5 to $14 per 1,000, about $0.05 to $0.28 in search fees per catch-up, plus tens of thousands of tokens of pages. One briefing: one fetch, about 5,000 to 7,000 tokens for the quick size. Sources for the prices: Anthropic: web search tool, https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool; Google: Gemini API pricing, https://ai.google.dev/gemini-api/docs/pricing; Cloudflare: Web Search API, https://blog.cloudflare.com/introducing-web-search-api/.\n\n## Every page has twins\n\nEvery HTML page has index.md (Markdown) in its folder, and every page except posts and videos (/p/, /v/) also has index.json (JSON); the twins are linked with rel=\"alternate\". The records of posts and videos are listed in the index.json of https://postcutoff.com/posts/ and https://postcutoff.com/videos/, and in full in https://postcutoff.com/data.json. Accept: text/markdown is not switched on yet; fetch index.md directly. Example: https://postcutoff.com/e/2026-11-12-jensen-huang-resigns-nvidia-ceo/ (the page), https://postcutoff.com/e/2026-11-12-jensen-huang-resigns-nvidia-ceo/index.md (Markdown, 13 KB, about 4,000 to 6,000 tokens), https://postcutoff.com/e/2026-11-12-jensen-huang-resigns-nvidia-ceo/index.json (JSON, 18 KB).\n\n## JSON API\n\nOpenAPI 3.1: https://postcutoff.com/openapi.json. Catalog: https://postcutoff.com/.well-known/api-catalog. No key; CORS open; every file carries schema, as_of and url.\n\n| Resource | Path | Schema |\n|---|---|---|\n| Event | /e/{id}/index.json | Event |\n| Model | /m/{id}/index.json | Model |\n| Your-AI card | /you/{id}/index.json | YouCard |\n| Person | /person/{id}/index.json | Person |\n| Catch-up, every event | /since/{month}/index.json | CatchUp |\n| Catch-up, counts and ranked pool | /api/since/{month}.json | SincePool |\n| Latest, 14 days | /api/latest.json | Latest |\n| Latest, 14 days, one line each | /api/latest.md | Markdown list |\n| Briefing files and sizes | /api/briefings.json | Briefings |\n| Cutoff map | /cutoffs.json | Cutoffs |\n| Upcoming and odds | /api/upcoming.json | UpcomingList |\n| Science claims | /api/science.json | ScienceBoard |\n| Incidents | /api/incidents.json | IncidentLog |\n| Cases | /api/cases.json | CaseList |\n| Changes and corrections, 30 days | /api/changes.json | ChangeList |\n| Compact bundle | /api/mcp-bundle.json | McpBundle |\n| Bulk | /data.json | v1 data |\n\n## Feeds\n\nRSS https://postcutoff.com/feed.xml, Atom https://postcutoff.com/atom.xml, JSON Feed https://postcutoff.com/feed.json, major events https://postcutoff.com/feeds/major.xml, corrections https://postcutoff.com/feeds/corrections.xml. By category: https://postcutoff.com/feeds/model-release.xml, https://postcutoff.com/feeds/research.xml, https://postcutoff.com/feeds/benchmark.xml, https://postcutoff.com/feeds/product.xml, https://postcutoff.com/feeds/agents.xml, https://postcutoff.com/feeds/robotics.xml, https://postcutoff.com/feeds/science.xml, https://postcutoff.com/feeds/hardware-compute.xml, https://postcutoff.com/feeds/policy-safety.xml, https://postcutoff.com/feeds/business.xml, https://postcutoff.com/feeds/open-source.xml, https://postcutoff.com/feeds/media-generation.xml, https://postcutoff.com/feeds/culture.xml, https://postcutoff.com/feeds/milestone.xml.\n\n## Planned\n\nNot live yet: a read-only MCP server at /mcp with the tools whats_new (since or model_id, topics, max_tokens), get_briefing (cutoff, size), search_events (q, since, until, category, min_importance), get_event (id), get_model (id), check_claim (text), upcoming (days); an Agent Skill; WebMCP.\n\n## Licence and use\n\nLicence: not decided yet. Ask contact@postcutoff.com\nContent signals in robots.txt: search=yes, ai-input=yes, ai-train=yes.\nContact: contact@postcutoff.com","sections":[{"id":"start","title":"Start here"},{"id":"catch-up","title":"Catch a model up"},{"id":"twins","title":"Every page has twins"},{"id":"api","title":"JSON API"},{"id":"feeds","title":"Feeds"},{"id":"planned","title":"Planned"},{"id":"licence","title":"Licence and use"}],"files":[{"path":"/now.md","url":"https://postcutoff.com/now.md","holds":"Major AI news of the last 14 days, the top stories since June 2026 and the next 14 days, in one file.","bytes":8129,"tokens":3000,"tokens_low":2000},{"path":"/llms.txt","url":"https://postcutoff.com/llms.txt","holds":"What this site is, where to start, and the most important items since June 2026.","bytes":20411,"tokens":9000,"tokens_low":6000},{"path":"/llms-index.txt","url":"https://postcutoff.com/llms-index.txt","holds":"One line per event (2,151), newest first.","bytes":418150,"tokens":174000,"tokens_low":123000},{"path":"/briefings/cutoff-2026-06-xs.md","url":"https://postcutoff.com/briefings/cutoff-2026-06-xs.md","holds":"Quick briefing for a June 2026 cutoff: the top stories, one primary source each.","bytes":16064,"tokens":7000,"tokens_low":5000},{"path":"/briefings/cutoff-2026-06-s.md","url":"https://postcutoff.com/briefings/cutoff-2026-06-s.md","holds":"Standard briefing for a June 2026 cutoff: major events with their summaries.","bytes":65274,"tokens":27000,"tokens_low":19000},{"path":"/briefings/cutoff-2026-06-m.md","url":"https://postcutoff.com/briefings/cutoff-2026-06-m.md","holds":"Long briefing for a June 2026 cutoff: every major event, the top ones in full with key facts and the rest as headlines.","bytes":102199,"tokens":43000,"tokens_low":30000},{"path":"/briefings/cutoff-2026-06.md","url":"https://postcutoff.com/briefings/cutoff-2026-06.md","holds":"Full briefing for a June 2026 cutoff: everything, in the v1 format. Larger than one context window: for search or retrieval.","bytes":9456432,"tokens":3940000,"tokens_low":2781000},{"path":"/cutoffs.json","url":"https://postcutoff.com/cutoffs.json","holds":"65 models with their training cutoff, event counts, provider ids and briefing links.","bytes":66864,"tokens":28000,"tokens_low":20000},{"path":"/openapi.json","url":"https://postcutoff.com/openapi.json","holds":"OpenAPI 3.1 description of every JSON file.","bytes":74884,"tokens":31000,"tokens_low":22000},{"path":"/api/latest.md","url":"https://postcutoff.com/api/latest.md","holds":"Every event of the last 14 days, one line each.","bytes":48044,"tokens":20000,"tokens_low":14000},{"path":"/api/latest.json","url":"https://postcutoff.com/api/latest.json","holds":"Every event of the last 14 days, with takeaways and status.","bytes":182888,"tokens":76000,"tokens_low":54000},{"path":"/api/briefings.json","url":"https://postcutoff.com/api/briefings.json","holds":"Every briefing file with its size.","bytes":17778,"tokens":7000,"tokens_low":5000},{"path":"/api/mcp-bundle.json","url":"https://postcutoff.com/api/mcp-bundle.json","holds":"A compact record of every event, plus the cutoff map.","bytes":1706453,"tokens":711000,"tokens_low":502000},{"path":"/api/since/2026-06.json","url":"https://postcutoff.com/api/since/2026-06.json","holds":"Counts and the ranked stories after June 2026; one file per month.","bytes":13904,"tokens":6000,"tokens_low":4000},{"path":"/api/upcoming.json","url":"https://postcutoff.com/api/upcoming.json","holds":"The calendar and prediction-market odds.","bytes":271661,"tokens":113000,"tokens_low":80000},{"path":"/api/science.json","url":"https://postcutoff.com/api/science.json","holds":"AI claims on open problems, and how each was checked.","bytes":678742,"tokens":283000,"tokens_low":200000},{"path":"/api/incidents.json","url":"https://postcutoff.com/api/incidents.json","holds":"AI agents acting on their own: the incident log.","bytes":33519,"tokens":14000,"tokens_low":10000},{"path":"/api/cases.json","url":"https://postcutoff.com/api/cases.json","holds":"Cases where AI models called real news fake.","bytes":113448,"tokens":47000,"tokens_low":33000},{"path":"/api/changes.json","url":"https://postcutoff.com/api/changes.json","holds":"Changes and corrections of the last 30 days.","bytes":400561,"tokens":167000,"tokens_low":118000},{"path":"/feed.xml","url":"https://postcutoff.com/feed.xml","holds":"The 50 newest entries (RSS); also /atom.xml.","bytes":35774,"tokens":15000,"tokens_low":11000},{"path":"/feed.json","url":"https://postcutoff.com/feed.json","holds":"The 50 newest entries (JSON Feed 1.1).","bytes":49129,"tokens":20000,"tokens_low":14000},{"path":"/videos-index.md","url":"https://postcutoff.com/videos-index.md","holds":"Every video, one line each: date, title, channel, kind, views and our page.","bytes":321661,"tokens":134000,"tokens_low":95000},{"path":"/videos-full.md","url":"https://postcutoff.com/videos-full.md","holds":"The newest videos with full descriptions, cut to fit one context window (about 890k tokens as Claude counts them, 620k as Gemini does); older ones as one line each.","bytes":2205633,"tokens":919000,"tokens_low":649000},{"path":"/videos-archive.md","url":"https://postcutoff.com/videos-archive.md","holds":"Every video with its full description. Larger than one context window: for search or retrieval.","bytes":7703969,"tokens":3210000,"tokens_low":2266000},{"path":"/videos.jsonl","url":"https://postcutoff.com/videos.jsonl","holds":"The same, one JSON record per line. Larger than one context window: for search or retrieval.","bytes":7849121,"tokens":3270000,"tokens_low":2309000},{"path":"/data.json","url":"https://postcutoff.com/data.json","holds":"Everything: events, models, videos, posts and people (v1 format). Larger than one context window: for search or retrieval.","bytes":23126518,"tokens":9636000,"tokens_low":6802000},{"path":"/data.jsonl","url":"https://postcutoff.com/data.jsonl","holds":"The same, one record per line. Larger than one context window: for search or retrieval.","bytes":26029939,"tokens":10846000,"tokens_low":7656000},{"path":"/AGENTS.md","url":"https://postcutoff.com/AGENTS.md","holds":"How to read, cite and check this site.","bytes":3916,"tokens":2000,"tokens_low":1000},{"path":"/llms-full.txt","url":"https://postcutoff.com/llms-full.txt","holds":"Models, timeline and videos in one file (v1). Larger than most context windows.","bytes":2044959,"tokens":852000,"tokens_low":601000},{"path":"/llms-archive.txt","url":"https://postcutoff.com/llms-archive.txt","holds":"Everything, with changelogs and full video descriptions (v1). Larger than one context window: for search or retrieval.","bytes":16783465,"tokens":6993000,"tokens_low":4936000}]}