# A whole news agency, working on a single computer. The Observatory has three desks: AI, Ethiopia and Interesting Politics. Between them they follow subjects that move every day: AI in management and in software engineering, the research behind it, Ethiopia, and how some governments speak to their own people. It reads its sources the way a wire service would, keeps what falls within each desk’s beat, traces every story to where it first appeared, and publishes what it found each morning. Every step is done by software following written editorial rules: what is in scope, what matters most, how a story is checked and how an issue is written. The rules are changed by hand, and every version is kept. ## The newsroom, as of 01:57, 15 October ### 01 · Collecting: Reading the sources 6,627 items read from 575 sources. 9 readers, one for each way a source can be read: feeds, pages without feeds, X accounts, newsletters, Telegram channels, WeChat, model hubs and paper archives, podcasts and video. Each source is read on its own rhythm. _79 scans in the last 24 hours_ ### 02 · Languages: Translation 5 source languages. Items in Chinese and Amharic are translated before they are judged, so a Chinese lab or an Ethiopian ministry is held to the same standard as a wire service. _English, 中文, አማርኛ, French, Russian_ ### 03 · Relevance: The relevance check 3,748 of 5,337 new items kept. Every new item meets its desk’s written scope rule. On X posts a second model looks again at everything the first dropped. _Each model benchmarked on our own material_ ### 04 · Editing: Writing the notes 138 notes written. Accounts of the same event are compared and the best is chosen, given a type and tags, and written up as a note. _Ranked by each desk’s written priorities_ ### 05 · Checking: The credibility check {labeled} of 1,025 notes this week passed with a label stating their origin. Each note is traced to where it first appeared and to who stands behind it. Outlets repeating a story do not confirm it. We check origin and credibility, not facts. _Telegram and X posts count as their own originals_ ### The archive: The Book 2,403 notes, and 115 issues, kept for good. Every note with its sources, and every issue sent. People here would rather read the originals, so the Book is not shown on this site; it is kept as the Observatory’s record. _Every version of every rule kept with it_ ### 06 · Publishing: Writing the issues 12 issues sent in the last 24 hours. Each publication chooses its stories from the Book, groups them, writes the issue and looks it over. _8 publications_ ### 07 · Readers: Delivery 1 copy of each issue per reader, at the hour they choose. By email or on Telegram, in English, Russian or Amharic. Nobody receives the same issue twice. _Email, Telegram, LinkedIn, YouTube and this site_ ### 08 · Control, over every room: Testing the models 20 benchmarks. No model is used because it is famous: each step has its own test set drawn from our material, and a model earns the step by score, cost and speed. Spending limits for each desk, and a morning report on anything that went wrong. ## 6,627 in. 138 kept. One day of work, drawn to scale: everything read in the last 24 hours, what was new, what fell within a desk’s scope, and what became a note in the Book. - Read: 6,627 - New, not seen before: 5,337 - Within a desk’s scope: 3,748 - Notes in the Book: 138 ## Every model earns its step Each step has a test set drawn from the Observatory’s own material, with right answers written and read again independently. A model is given a step for its score, its cost and its speed, and is tested again when a new one appears. | Step | Chosen | Measure | Result | |---|---|---|---| | Relevance · X posts | DeepSeek V4.1 Flash + Jev | relevant posts lost | 2.1% | | Relevance · feeds and pages | Jev | relevant items lost | 0.2% | | Relevance · Chinese | DeepSeek V4.1 Flash | relevant items lost | 2.1% | | Relevance · Ethiopia desk | DeepSeek V4.1 Flash | relevant items lost | 0.3% | | Credibility check | DeepSeek V4.1 Flash | right outcome | 90.6% | | Choosing the day’s stories | MiMo V2.6 Flash | overlap with the editors’ choice | 71.2% | ## What the desks covered this week The subjects of the notes written in the last 7 days: how many notes, and what share of the desk’s notes, with the change from the 7 days before. A note can carry more than one subject. ### AI desk - Companies: 204 (29%, +4 pts) - Products: 191 (27%, −2 pts) - Models: 159 (23%, −2 pts) - Safety: 120 (17%, +3 pts) - Research: 115 (17%, ±0 pts) - Coding: 106 (15%, ±0 pts) - Evaluation: 106 (15%, +5 pts) - Agents: 90 (13%, +4 pts) ### Ethiopia desk - Security: 103 (31%, −5 pts) - Foreign relations: 86 (26%, +2 pts) - Economy: 84 (25%, +3 pts) - Politics: 76 (23%, −8 pts) - Society: 70 (21%, +3 pts) - Business: 54 (16%, +5 pts) - Banks and fintech: 47 (14%, ±0 pts) - AI: 7 (2%, +2 pts) ### Interesting Politics desk This desk writes no notes: these are the themes of the stories in its issues of Dispatches from Others, how many stories, and what share of them. - Our country against the world: 11 (29%) - Our leaders are great: 6 (16%) - The people mobilised: 6 (16%) - The state cares for its people: 4 (11%) - Our glorious history: 4 (11%) - Our youth happy about our country: 4 (11%) - The world admires us: 3 (8%) ## Designed and directed by Mikael Alemu Gorsky [mgorsky.net](https://mgorsky.net)