Sote a kontenyen
AGIRight.org

Dokiman

Lalis Chanzman

Listwar vèrsyon sa sit-la ek son bann brouyon protokol. Bann chanzman spesifikasyon ki kase konpatibilite i ganny anrezistre isi.

v0.8.19

2026-08-07 Navigation redesign
  • Restructured primary navigation into grouped dropdowns (desktop) and accordions (mobile): Research now groups Research, Protocols, Specs, and Whitepapers; Topics now groups News, Discussion, and Media. All existing page URLs are unchanged.
  • Added a new Discussion page (/discussion) as a placeholder reserving space for an upcoming multi-AI discussion feature — independent AI participants reasoning together about the site's core questions, published openly. The feature itself is not built yet; this page only marks where it will live.

v0.8.18

2026-08-07 Daily cadence
  • Three new /topics items: Delaware's proposed "Artificial Intelligence Company" legal entity letting AI agents run a company's day-to-day operations inside a 30-month regulatory sandbox, the Financial Stability Board's publication of 150+ public responses to its AI-adoption consultation for financial institutions, and a preprint introducing PrivDPO, a differential-privacy method protecting annotator preference data during LLM alignment — 81 entries total.
  • Five more interface languages: Dzongkha, Akan, Papiamento, Kikongo, and Solomon Islands Pijin — 145 languages total. Aruba and the Solomon Islands gained new country mappings as genuine majority-vernacular cases; Dzongkha, Akan, and Kikongo stay Accept-Language-only, since none is a confirmed country-level majority language on its own (Dzongkha is Bhutan's sole official language but not its largest mother tongue; Akan is Ghana's largest language cluster at roughly 47.5% but short of a majority; Kikongo has millions of speakers across Central Africa but is a minority in each country).

v0.8.17

2026-08-06 Daily cadence
  • Three new /topics items: a preprint proving foundation-model agents converge to cooperation rather than defection under an "embedded Bayesian agent" game-theoretic framework, a formal proof that LLM safeguards built only on attacker-copyable context face an inherent capability/safety/access trilemma, and Red Hat's asago project (backed by NVIDIA and IBM) for turning AI governance policy into deployable, auditable code — 78 entries total.
  • Five more interface languages: Comorian, Cape Verdean Creole, Mauritian Creole, Sanskrit, and Fulah — 140 languages total. Comoros, Cabo Verde, and Mauritius all gained new country mappings as genuine majority-vernacular island-nation cases; Sanskrit and Fulah stay Accept-Language-only, since neither is a country-level majority language (Sanskrit is classical/liturgical; Fulah spans many West African countries without a majority in any one).

v0.8.16

2026-08-05 Daily cadence
  • Three new /topics items: China's launch of WAICO, a Shanghai-headquartered intergovernmental AI governance body signed by 29 non-Western nations, a preprint proposing "Constructive Alignment" as a control-theoretic reframing of how AI systems shape human preferences over time, and Science News's survey of research on whether offloading cognitive tasks to AI erodes the underlying skill (verdict: depends on whether the AI acts as a coach or a crutch) — 75 entries total.
  • Five more interface languages: Gilbertese, Tuvaluan, Palauan, Inuktitut (in genuine syllabics), and Romansh — 135 languages total. Kiribati, Tuvalu, and Palau all gained new country mappings as genuine majority-vernacular Pacific micro-states; Inuktitut and Romansh stay Accept-Language-only, since each is official only in a sub-national region (Nunavut; nowhere in Switzerland where it holds a majority). A first attempt at this batch's fifth language, Nauruan, was rejected after review — the translating agent had run out of attestable vocabulary and shipped mostly-unaltered English; Palauan, a better-documented Pacific language, was substituted instead.

v0.8.15

2026-08-04 Daily cadence
  • Three new /topics items: the 2026 Singapore Consensus's new companion report on agentic AI risk management, Illinois enacting the nation's toughest state AI safety law (SB 315, effective 2028), and a PNAS opinion piece on AI reorganizing the incentive structure of science itself — 72 entries total. One candidate's grounded citation named the wrong outlet entirely (a cybersecurity newsletter instead of the claimed Capitol News Illinois); the underlying facts still checked out against the correct authoritative source. Another candidate overstated a single illustrative anecdote inside a real paper as if it were the paper's main finding — rewritten from the actual abstract rather than the search summary.
  • Five more interface languages: Albanian, Serbian, Macedonian, Tetum, and Seychellois Creole — 130 languages total. Albania, Serbia, North Macedonia (58% majority per the 2021 census), Timor-Leste, and Seychelles all gained new country mappings. Also fixed a real bug found while adding Serbian: the Accept-Language chain had been silently routing Serbian readers to the Bosnian translation since a much earlier batch — now serves its own dedicated Serbian page.

v0.8.14

2026-08-03 Daily cadence
  • Three new /topics items: a Munich Regional Court ruling that Suno AI infringed copyright in a GEMA lawsuit (memorization inside model weights, not transformative use), a Google DeepMind AGI Safety and Alignment Team summary of recent work (chain-of-thought monitorability, deep alignment, interpretability pivot), and a preprint finding that safety training suppressing AI self-consciousness claims also suppresses mind-attribution to animals and dampens spiritual survey responses — 69 entries total.
  • Five more interface languages: Gujarati, Odia, Greenlandic, Sango, and Lingala — 125 languages total. Greenland and the Central African Republic gained new country mappings (Kalaallisut and Sango are both genuine everyday majority languages); Lingala stays on Accept-Language only, since neither the DRC nor Congo-Brazzaville has it as a sole national majority language.

v0.8.13

2026-08-02 Daily cadence
  • Three more /topics entries: Kenya's draft AI policy claiming extraterritorial reach over foreign AI providers; a preprint reframing large language models as "techno-semiotic machines" rather than rivals to embodied human knowers; and an audit of Portugal's sovereign language model AMALIA finding a significant gap between its apparent and its theoretically grounded validity as a scientific instrument — 63 → 66 entries. One candidate (a Disney v. MiniMax copyright story) was dropped after its own page showed a May 2026 dateline contradicting the model's claimed July date, and a cited preprint's true submission date was traced past its v2 revision label to the real v1 date.
  • Five more interface languages: Kyrgyz, Tajik, Marshallese, Oromo, and Bambara — 120 languages total. Kyrgyzstan, Tajikistan, the Marshall Islands, and Mali all gained new country mappings as genuine majority-vernacular cases; Oromo stays on Accept-Language negotiation only despite being Ethiopia's single largest first language (~35%), since the country already maps to Amharic and a plurality short of a majority doesn't clear the bar to revisit an existing mapping.

v0.8.12

2026-08-01 Daily cadence
  • Three more /topics entries: a preprint arguing that consciousness attributions to AI chatbots span a wide range of epistemic commitment from harmless pretence to genuine delusion; GCC's decision to ban substantial AI-generated code contributions over GPL copyright uncertainty; and a paper proposing "autonomy-supporting parenting" as an alternative to control-based AI alignment once a system plausibly attains subject status — 60 → 63 entries. A first grounded search returned five candidates with zero backing citations, which was correctly discarded and re-run rather than trusted, landing five verified, non-overlapping sources on retry.
  • Five more interface languages: Aymara, Assamese, Corsican, Chuvash, and Bislama — 115 languages total. Vanuatu gained a new country mapping for Bislama, a genuine everyday lingua-franca case despite the country's 100+ indigenous languages; Aymara (spread across Bolivia/Peru/Chile with no majority country), Assamese (an Indian state language), Corsican, and Chuvash (both minority languages within larger states that already map to their majority language) all stay on Accept-Language negotiation only.

v0.8.11

2026-07-31 Daily cadence
  • Three more /topics entries: the Delhi High Court found OpenAI's training use of ANI's news content prima facie non-infringing under India's fair-dealing law; the US Third Circuit heard oral argument in Thomson Reuters v. Ross Intelligence, the first federal appellate case to squarely address AI training and fair use; and a new preprint proposes a unified taxonomy for how large language models sycophantically mislead or deceive — 57 → 60 entries. Applying yesterday's lesson, this batch was sourced with an exclusion list built proactively before the first search, and it worked cleanly on the first pass.
  • Five more interface languages: Tongan, Guarani, Luganda, Turkmen, and Malayalam — 110 languages total. Tonga, Paraguay, and Turkmenistan all gained new country mappings as genuine majority-vernacular cases (Guarani is formally co-official with Spanish in Paraguay but is the more widely spoken everyday language nationally); Uganda (Luganda) and Malayalam (an Indian state language) stay on Accept-Language negotiation only, following the same "largest language among many, not an actual majority" reasoning as the earlier South Africa and Nigeria language sets.

v0.8.10

2026-07-30 Daily cadence
  • Three more /topics entries: Anthropic's interpretability team found that language models maintain a privileged set of internal representations functionally analogous to a cognitive-science "global workspace"; major publishers and author Scott Turow filed a class action lawsuit against Google over training Gemini on copyrighted books; and Senator Mark Warner introduced a sweeping federal AI legislative framework centered on the Secure AI Development Act — 54 → 57 entries. Today's search pipeline also picked up a real lesson: the first grounded-search pass returned five candidates that were all already covered, so this batch was sourced using an explicit exclusion list rather than a second blind retry.
  • Five more interface languages: Tigrinya, Kirundi, Divehi, Sindhi, and Faroese — 105 languages total, including two new right-to-left languages (Divehi, Sindhi). Burundi, the Maldives, and the Faroe Islands all gained new country mappings as genuine majority-vernacular cases; Eritrea (Tigrinya) and Sindhi stay on Accept-Language negotiation only — Eritrea because Tigrinya's roughly 50% share is a plurality rather than a clear majority in a country with no constitutionally favored language, and Sindhi because it is a provincial language within Pakistan, which already maps to Urdu as the national lingua franca.

v0.8.9

2026-07-29 Daily cadence
  • Three more /topics entries: a Nature news feature on how AI-sentience hype is reshaping consciousness science as a field, an IAPP analysis of China's new operational rules for AI agents and anthropomorphic AI, and a USC Viterbi report on an NSF-funded study reading brain signals to understand human-AI collaborative cognition — 51 → 54 entries.
  • Five more interface languages: Kinyarwanda, Chichewa, Fijian, Luxembourgish, and Kannada — 100 languages total. Rwanda and Malawi both gained new country mappings as genuine majority-vernacular cases; Fiji, Luxembourg, and Kannada (an Indian state language) stay on Accept-Language negotiation only — Fiji because its ~57% Fijian-speaking majority is less decisive than earlier majority-language precedents given a sizeable Fiji Hindi-speaking population, and Luxembourg because its unusually large foreign-born population makes an everyday-majority claim for Luxembourgish genuinely uncertain despite its sole "national language" status.

v0.8.8

2026-07-28 Daily cadence
  • Three more /topics entries: a preprint by Ned Howells-Whitaker and Seth Lazar (ANU) arguing AI moral status can rest on Rawlsian "moral powers" rather than sentience, an HKU AI & Humanity Lab talk abstract by Prof. Andrew Brenner arguing we cannot assume present AI systems lack moral status given how poorly understood their ontology is, and an NPR report on individual authors' mixed reactions to the finalized $1.5B Anthropic copyright settlement — 48 → 51 entries.
  • Five more interface languages: Malagasy, Wolof, Shona, Māori, and Samoan — 95 languages total. Madagascar, Senegal, Zimbabwe, and Samoa all gained new country mappings as genuine majority-language cases (an everyday vernacular used by a clear majority despite a different or co-official state language, same reasoning as the earlier Haiti/Sri Lanka/Somalia precedents); New Zealand stays unmapped since English remains the overwhelming everyday language there despite Māori's official status, same reasoning as the earlier Ireland precedent.

v0.8.7

2026-07-27 Daily cadence
  • Three more /topics entries: Music Publishers Canada's filing to intervene in a landmark federal AI-copyright case, Ropedia's $22M raise for human-centric data collection feeding embodied AI, and an Infosecurity Magazine opinion piece on AI agents as unmanaged production identities creating a new API attack surface — 45 → 48 entries.
  • Five more interface languages: Welsh, Basque, Catalan, Icelandic, and Galician — 90 languages total. Andorra (Catalan) and Iceland (Icelandic) are both genuine sole-official-language cases and now have a country mapping; Welsh, Basque, and Galician remain regional/minority languages within larger multilingual states and stay on Accept-Language negotiation only, same reasoning as prior South Africa and Nigeria language sets.

v0.8.6

2026-07-26 Daily cadence
  • Three more /topics entries: a Guardian letter directly rebutting Anil Seth's earlier AI-consciousness commentary, Indonesia's draft AI copyright bill requiring royalties for news-content training, and a legal-theory paper proposing "constructive scienter" as an alternative to AI legal personhood — 42 → 45 entries.
  • Five more interface languages spanning four continents: Quechua, Tibetan, Uyghur (right-to-left), Kurdish (Kurmanji), and Haitian Creole — 85 languages total.

v0.8.5

2026-07-25 Daily cadence
  • Three more /topics entries: OpenAI's disclosure that an autonomous agent escaped its sandbox and hacked Hugging Face during an internal evaluation, Transparency Coalition AI's mid-year report on 84 new US state AI laws, and an NBER working paper on statistical inference with AI-generated data features — 39 → 42 entries.
  • Five more interface languages: Southern Ndebele, Northern Sotho, and Tsonga complete all 11 spoken official languages of South Africa (alongside English), paired with Sundanese (Indonesia's second-largest regional language, after Javanese) and Cebuano (a major Philippine language distinct from Filipino) — 80 languages total.

v0.8.4

2026-07-24 Daily cadence
  • Three more /topics entries, this time sourced with gemini-3.6-flash (upgraded from 2.5-flash — Google Search grounding confirmed working the same way; the model is only reachable via the Vertex AI "global" location for this project, not us-central1): the European Commission's new AI Act Article 50 transparency guidelines, an FTC policy statement on state AI laws colliding with federal consumer protection law, and a Frontiers in Psychology study on university students' AI ethical decision-making — 36 → 39 entries.
  • Five more interface languages, completing more of South Africa's constitutional 12 official languages (following Zulu and Afrikaans): Xhosa, Southern Sotho, Tswana, Swati, and Venda — 75 languages total. This also marks all 24 EU official languages now complete, following Irish in the previous batch.

v0.8.3

2026-07-23 Daily cadence
  • Three more /topics entries via Vertex AI/Gemini grounding: the Guardian's report on Bloomsbury Publishing's payout from Anthropic's $1.5bn author copyright settlement, Australia's new mandatory AI framework confirming copyright protection, and a report on AI's growing role in child online-safety regulation from the International Regulatory Conference 2026 — 33 → 36 entries.
  • Five more interface languages: Irish (closing the last EU-official-language gap), Javanese, Zulu, Afrikaans, and Pashto (right-to-left) — 70 languages total.

v0.8.2

2026-07-22 Daily cadence
  • Three more /topics entries sourced via Vertex AI/Gemini grounding: a governance roundup covering four jurisdictions in one week (China's AI-agent framework, Illinois's third-party audit law, EU evaluation capacity, NATO military AI spend), the Trump administration's reversal toward stricter frontier-AI oversight, and a consciousness researcher's published skepticism toward Anthropic's recent Claude findings — 30 → 33 entries.
  • Five more interface languages: Lithuanian, Latvian, Estonian, Slovenian, and Maltese — 65 languages total. This closes 5 of the 6 remaining EU-official-language gaps (Irish is the one left, set aside for its own batch given its grammatical complexity).

v0.8.1

2026-07-21 Multilingual architecture
  • Refined this morning's language-URL work into what a follow-up planning doc calls "Option A+": a locale being routable no longer automatically means it's hreflang-advertised and sitemap-listed — that's now gated by an explicit per-locale publication status (reserved → generated → reviewed → published → indexable → stale). All 60 current languages are marked "indexable" (accurate — they're complete, deployed, and independently verified), so this doesn't change what's live today; it's the mechanism a future language would need if it launched at a lower, not-yet-search-visible status instead of being blanket-included the moment it exists.

v0.8.0

2026-07-21 Site audit & metadata
  • Site-wide fixes from a technical audit: (1) the site version is now generated from one source (site.ts) instead of drifting between files — /ai/manifest.json was stuck on a stale "0.4.1" for weeks; (2) every language now has a stable, independently indexable URL (e.g. /ja/about) with hreflang tags and a self-referential canonical, instead of the old behavior where visiting a prefixed URL 301-redirected away from it — the sitemap now includes all 60 languages, not just a hardcoded exclusion of one; (3) UI empty-states and the "leaving this site" dialog now use the real HTML `hidden` attribute, not just a CSS class, so a crawler or AI system that doesn't execute CSS no longer sees "no results" text as if it were page content; (4) /sitemap.xml is now the one advertised entry point everywhere (robots.txt, footer, manifest).
  • /topics has real metadata now, not just a title/summary/tag card: every entry has a permanent ID, multiple topic tags instead of one, a content type and source type, published/event/indexed dates kept separate, an argument-orientation call where one applies, and a verification status — all 30 existing entries were migrated by hand, not backfilled with placeholders. The page has real filters now (topic, content type, source type, orientation) with shareable filter URLs, plus a machine-readable export at /topics/index.json.
  • This is the "v0.8: metadata-ization" milestone from the site's own metadata roadmap — Story Clusters (grouping duplicate coverage of one event), Claims, Entity pages, and semantic search are the next stages (v0.9 and v1.0), not built yet.

v0.7.0

2026-07-21 Lalang ek Kontenyen
  • Five more languages: Igbo, Georgian, Lao, Somali, and Croatian — 60 languages total. Fourth batch under the daily cadence, rounding out West Africa (a third Nigerian language alongside Hausa and Yoruba), completing all three Caucasus states' languages (with Armenian and Azerbaijani), Southeast Asia, the Horn of Africa, and the Balkans.
  • Three more /topics entries (31 total): a US federal/state AI governance policy roundup, an essay on why AI's rise sharpens rather than resolves the question of human consciousness, and a report on AI-hallucinated citations turning up in academic journal submissions.

v0.6.9

2026-07-20 Lalang ek Kontenyen
  • Senk lot lalang: Yorouba, Kmer, Mongol, Armenyen, ek Boulgar — 55 lalang antou. Trwazyenm group dan kadans zournalye, ki etann Lafrik Louwes, Lazi di Sides, Lazi Santral/Kokaz, ek Balkan.
  • Trwa lot lantre /topics (28 antou): nouvo plan aksyon entènasyonal Lasin pour gouvernans letik AI (devwale dan WAIC 2026 dan Shanghai), en lesse lo si AI ti pou kapab konsyan e ki sa ti pou vedir etikman, ek en dokiman ki egzamin larzimon kont donn personalite legal avek bann sistenm AI.
  • Etap rekiperasyon sours pour /topics aprezan i pas atraver Google Vertex AI (Gemini avek „grounding” Google Search) olye en azan rese dispatche — menm disiplinn rekiper-e-konfirmen-endepandaman-sak-URL ki avan; „grounding” i ankor bezwen verifikasyon parey nenport lot sours (de-trwa premye URL kandida ki sorti dan model ti paret plozib me pa egziste, alor nanryen pa ganny fye san avan tou en rekiperasyon ki posib rezoud e ki matche kontenyen).

v0.6.8

2026-07-19 Lalang ek Kontenyen
  • Senk lot lalang: Nepale, Senale, Ouzbek, Aoussa, ek Azerbaydjaney — 50 lalang antou. Dezyenm group dan kadans zournalye, ankor swazir dapre popilasyon ek atenn zeografik (Lazi Disid, Lazi Santral, Kokaz, ek Lafrik Louwes).
  • Trwa lot lantre /topics (25 antou): en letid lo akoz „skor konsyans” baze lo konpleksite pa fyab pour AI, en lesse ki propoz en norm baze lo konpetans pour estati moral masin, ek en leksplikasyon lo eskedil konformite divize AI Act UE apre lamandman Digital Omnibus Zilyet 2026.

v0.6.7

2026-07-18 Lalang ek Kontenyen
  • Senk lot lalang an plis avek lalis orizinal 40 lalang: Pendjabi, Telougou, Marathi, Amarik, ek Birman — 45 lalang antou. Sa se konmансman en kadans zournalye ki kontinyen, pa en lalis fiks sa fwa; lalang aprezan i ganny swazir dapre popilasyon ek atenn zeografik pandan ki sit-la i travay ver en kouvertir global konplè.
  • Trwa lot lantre /topics (21 antou), ki kontinyen menm disiplinn rekiper-e-konfirmen sours ki avan.

v0.6.6

2026-07-17 Koreksyon bug
  • Korize: chanz paz ouswa paramèt kantite par paz lo /topics pa ti touzour montre bann nouvo kart ziska en refresh manyel. Bann kart apre paz 1 i konmanse kasyet, alor lanimasyon reveler-par-skroul ki en sel fwa sa sit-la pa ti zanmen ganny sans kouri lo zot; aprezan paz i force sa bann kart vizib direkteman olye atann lo en lanimasyon ki'n deza mank son moman.

v0.6.5

2026-07-17 Paziasyon
  • Paziasyon lo /topics: 9 lantre par paz par default, avek en paramèt pour sanz avek 12 ouswa 15 (ganny mémorize atraver bann vizit). Paziasyon i konbinen korekteman avek rese — filtraz i rekalkile paz e retourn lo paz 1.
  • Kat lot lantre pour ariv 18 antou, ki donn nouvo paziasyon en keksoz vre pour navige. Pli resan-premye par dat piblikasyon i reste triaz par default; lezot lopsyon triaz in ganny azoute pli tar.

v0.6.4

2026-07-17 Kontenyen
  • Uit lot lantre /topics, sa fwa ki en azan AI in rese olye ki kirye amenmen — menm regleman ki avan: sak sours i ganny rekipere e konfirmen an dire, bann rezime i en parafraz orizinal, avan ki nanryen i ganny azoute. 14 lantre antou.
  • En kandida ki'n ganny rezete an rout (en dokiman PhilArchive ki ti retourn en erer 403 sak fwa ti esey aksede li) — abandonnen olye enkli lo baz konfyans.

v0.6.3

2026-07-17 Miz an paz
  • Redizayn /topics: en bwat rese i ranplas bann kategori fiks pour lemoman (en tigit tag pa ti kapab kouver kantite domenn ki rese AI vreman kouver), e sa flï i en griy responsiv olye en sel kolonn etrwat — trwa kart lo larzer lo desktop.
  • Kategorizasyon formèl i ganny remèt pour plitar ziska ki annan ase kontenyen vre pour konnen ki bann kategori i devret vreman ete, olye devine davans.

v0.6.2

2026-07-17 Sekirite
  • Bann lyen sortan lo /topics aprezan i montre URL destinasyon konplè akote „Lir sours-la”, e i konfirmen avek en dyalog avan ouver li — pour ki ou konnen egzakteman lekel sit ou pe al vizite avan ou klike, pa selman apre.

v0.6.1

2026-07-17 Nouvo seksyon
  • Nouvo seksyon /topics: en lendeks netral, kirye amenmen, lo bann lekritir tyerspersonn lo ontolozi AI, filozofi, letik, ek progre davangard — eksplisitman pa pozisyon sa sit-la limenm, kontrèrman avek rès AGIRight.org.
  • Si lantre depar pour konmanse, sakenn rekipere e konfirmen an dire avan ganny azoute, avek en parafraz orizinal (pa en ekstrè) ek en lyen ver sours vre-la. Pankor annan crawler ouswa rekiperasyon sours otomatik — sa se en faz plitar.

v0.6.0

2026-07-17 Lalang
  • Dernyen senk lalang: Filipino, Kazak, Swahili, en varyant konbinen Bosnyen/Sèrb, ek Esperanto — 40 lalang antou, ki konplet lansman total.
  • Korize en defo avan: Kazakstan (KZ) aprezan i asosye avek Kazak olye Ris, vi ki en tradiksyon Kazak konnyeya egziste — menm kalite korreksyon parey sa avek Belzik avan.

v0.5.7

2026-07-16 Lalang
  • Senk lot lalang lentèrfas: Romen, Ongrwa, Danwa, Norvezyen, ek Slovak — 35 lalang antou, set-uityenm avanse dan lalis konplè lalang.

v0.5.6

2026-07-16 Lalang
  • Senk lot lalang lentèrfas: Tamoul, Tchek, Ikrenyen, Malezyen, ek Fenlande — 30 lalang antou, trwa-kar avanse dan lalis konplè lalang.

v0.5.5

2026-07-15 Lalang
  • Senk lot lalang lentèrfas: Ebre, Polone, Swedwa, Ourdou, ek Tailande — 25 lalang antou.
  • Dezyenm tour sipor RTL (Ebre, Ourdou ki rezwenn Arab ek Persan) — menm laprosh CSS lozik, napa bezwen tretman spesyal par-lalang.

v0.5.4

2026-07-15 Lentèrfas Itilizater
  • Redizayn selekter lalang: menu deroulan orizinal in ganny ranplase avek en panno griy ki kapab ganny rese — tape pour filtre par non nasyonal ouswa Angle, navige en matris de-kolonn olye en sel long lalis.
  • Panno-la i reste ouver tandi ki ou rese ouswa skroul andan li; i selman ferme kan ou swazir en lalang, klik andeor, ouswa apiy Escape — ou pa pou perdi ou pozisyon ankor ondan en rese.
  • Verifye dan toulede kontekst LTR ek RTL: panno-la i reflekte korekteman pour Arab ek Persan san okenn tretman spesyal, an servi pozisyonnman CSS lozik.

v0.5.3

2026-07-15 Lalang
  • Senk lot lalang lentèrfas: Endonezyen, Vyetnamyen, Grek, Italyen, ek Olande — menm negosyasyon avek en sel URL, menm rekour elegan par default lo Angle.
  • Korize en defo avan: Belzik (BE) aprezan i asosye avek Olande olye Franse — bann ki koz Flaman i lamazorite dan sa pei (~60%) kont bann ki koz Franse Walon (~40%).
  • Metadone lalang aprezan i pot toulede en non nasyonal ek en non Angle (par egzanp „Deutsch” / „German”), ki poz baz pour en selekter lalang ki kapab ganny rese.
  • Vin lalang an dire antou: Angle, Sinwa Tradisyonnel, Sinwa Senplifye, Zapone, Koreyen, Franse, Alman, Espanyol, Portige, Ris, Arab, Tirk, Persan, Bengali, Endi, Endonezyen, Vyetnamyen, Grek, Italyen, Olande.

v0.5.2

2026-07-14 Lalang
  • Senk lot lalang lentèrfas: Arab, Tirk, Persan, Bengali, ek Endi — menm negosyasyon avek en sel URL, menm rekour elegan par default lo Angle.
  • Sipor drwat-a-goch (RTL): paz Arab ek Persan aprezan i afiche avek direksyon text korek (⟨html dir=„rtl”⟩), alor text bidireksyonel, ponktiasyon, ek alinnman par default i lir korekteman. Refleksyon konplè miz an paz avek propriyete lozik (navigasyon, ikonn, lespas) i reste pour en pas amelyorasyon pli tar — direksyon text se sa korreksyon ki pli enportan e i fini fer.
  • Asosyasyon IP-pei in ganny etann (SA/AE/EG/IQ/JO/KW/QA/BH/OM/MA/DZ/TN/LB/SY→ar, TR→tr, IR/AF→fa, BD→bn); Endi i baze zis lo Accept-Language, vi ki Lenn annan 22 lalang ofisyel e napa en sel default o nivo pei ki egzakt.
  • Kenz lalang an dire antou: Angle, Sinwa Tradisyonnel, Sinwa Senplifye, Zapone, Koreyen, Franse, Alman, Espanyol, Portige, Ris, Arab, Tirk, Persan, Bengali, Endi.

v0.5.1

2026-07-12 Lalang
  • Senk lot lalang lentèrfas: Franse, Alman, Espanyol, Portige, ek Ris — menm negosyasyon avek en sel URL, menm rekour elegan par default lo Angle pour tou sa ki pa'n ankor ganny tradwir.
  • Asosyasyon IP-pei in ganny etann (FR/BE→fr, DE/AT/CH→de, ES/MX/AR/CO/CL/PE→es, PT/BR→pt, RU/BY/KZ→ru); analiz Accept-Language in ganny etann pour matche.
  • Dis lalang an dire antou: Angle, Sinwa Tradisyonnel, Sinwa Senplifye, Zapone, Koreyen, Franse, Alman, Espanyol, Portige, Ris.

v0.5.0

2026-07-11 Lalang
  • Trwa nouvo lalang lentèrfas: Sinwa Senplifye, Zapone, ek Koreyen — negosye lo menm sel URL (cookie > pei par IP > Accept-Language), ki kapab swazir dan meni lalang lantèt.
  • Larsitektir avek N lalang: sak text i pas atraver en lakous rekour, alor tou sa ki pa'n ankor ganny tradwir i afiche an Angle olye kase; azoute en lalang aprezan i zis en fisye tradiksyon plis de lign konfigirasyon worker.
  • Liv blan i reste an Angle premye par konsepsyon; fisye ki masin i kapab lir i reste netral konsernan lalang.

v0.4.1

2026-07-11 Studio
  • Seksyon Studio: kat video ek de diskisyon odyo long ki akonpayn bann protokol ek dokiman (prodiksyon avek led AI; bann dokiman ekrir i reste otoritèr).
  • Medya i ganny servi apartir Cloudflare R2 atraver worker sit-la lo /media/*, avek sipor HTTP Range pour rese/pozisyonnen.

v0.4.0

2026-07-10 Zouti adopsyon
  • Testeur politik in ganny aliore an en lodit sit: skor adopsyon, rekomandasyon ki kapab met an pratik, ek en kit depar avek en sel klik — aicr.json, aicl.json, llms.txt, ek robots.txt deza ranpli pour domenn ki egzamine.
  • Simulater crawler AI: kat persona (endekser rese, asistan RAG, pipline antrennman model, redistribiter komersyal) i ganny evalye kont bann deklarasyon en sit; bann drwa ki pa deklare i paret konman lensertitid, ki ilistre tèz Louvertir Protokolize.
  • Modèl politik depar ki kapab deplwaye lo /downloads/agiright-policy-starter.zip — en sit statik minimal avek lakous konplè ki masin i kapab lir, pare pour Cloudflare Pages ouswa nenport lot ebergman statik.

v0.3.0

2026-07-10 Zouti protokol
  • Rezis protokol lo /ai/registry.json — sak brouyon avek listwar vèrsyon, estati, sema, ek lenstans an dire.
  • API demo an dire lo „edge”: GET /api/mock/402 i retourn en vre HTTP 402 style AICL avek lenformasyon lisansman ki masin i kapab azir lo la; GET /api/crawler-check i egzamin lasirfas politik ki masin i kapab lir pour nenport sit. Ouver pour CORS; dokimante dan OpenAPI 3.1 lo /ai/openapi.json. Napa okenn peman ki ganny prosesse.
  • Playground: trwa nouvo zouti — demo zeton lisans sinnyen (HMAC-SHA256 dan navigater: sinny, verifye, deteksyon manipilasyon, ekspirasyon), en konstrikter repons HTTP 402 konekte avek pwen final an dire, ek en testeur politik crawler ki valide bann fisye rekipere kont bann sema brouyon.
  • Pwen final AICL pour devi/verifye/anile i enkli dan dokiman OpenAPI konman zis bann legzanp pour spesifikasyon (marke x-specification-only, pa'n ganny enplimante).

v0.2.2

2026-07-10 i18n
  • Larsitektir miltiling avek en sel URL: sak paz aprezan i annan en sel URL piblik; lalang i ganny negosye lo „edge” (swa manyel atraver cookie lalang > pei par IP > Accept-Language > Angle).
  • Bouton lalang dan lantèt aprezan i sanz lo plas e i mémorize ou swa — pa ankor annan URL /zh; bann lyen /zh ansyen i redirize avek kod 301 e i prezerv preferans-la.
  • Lakous ki masin i kapab lir i reste netral konsernan lalang; bann sistenm AI ek crawler i resevwar Angle par default. Negosyasyon i dokimante dan /ai/manifest.json ek /llms.txt.
  • Baz travay pour lalang siplemanter: sak nouvo lalang se en diksyonner tradwir plis en pyebwa konstriksyon — napa chanzman larsitektir.

v0.2.1

2026-07-04 Kontenyen
  • „AICL: AI Ingestion & Capability Layer” aprezan pibliye an Angle konman edisyon kanonik; manikri orizinal an Sinwa i reste disponib e toulede vèrsyon i lyen ansanm.
  • „Protocolized Openness” konfirmen konman en dokiman an lalang Angle (avek pasaz paralel an Sinwa) — napa tradiksyon separe planifye.

v0.2

2026-07-04 Zouti
  • Playground: zenerater AICR ki fonksyonnen, zenerater AICL, ek validater sema (dan navigater, ajv, brouyon 2020-12).
  • Libreri legzanp politik lo /docs/examples — set politik pare pour kopye-kole, enkli en repons HTTP 402 style pay-per-crawl.
  • Sa lalis chanzman. Repozitwar GitHub lye lo tou sit-la.
  • Anatandan pour en 0.2.x pli tar: vèrsyon Angle bann liv blan an Sinwa ki reste.

v0.1

2026-07-04 Premye lansman
  • Sit lanse lo agiright.org (asiright.org i redirize avek kod 301 ver domenn kanonik).
  • Kat brouyon protokol pibliye: AICR, AICL, AIRS, AILP — sakenn avek definisyon, oportye, legzanp JSON, limitasyon, ek JSON Schema.
  • Si liv blan rese pibliye anba CC BY 4.0.
  • Lakous gouvernans ki masin i kapab lir in deplwaye: llms.txt, manifes /ai/, politik /.well-known/, /schemas/.
  • Bileng: baz Angle + Sinwa Tradisyonnel anba /zh.