Ale dirèkteman nan kontni an
AGIRight.org

Dokiman

Istorik chanjman

Istorik vèsyon sit sa a ak avan-pwojè pwotokòl li yo. Chanjman espesifikasyon ki kraze kompatibilite anrejistre isit la.

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 Lang ak Kontni
  • 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 Lang ak Kontni
  • Senk lòt lang: Yoruba, Khmer, Mongòl, Amenyen, ak Bilga — 55 lang antou. Twazyèm gwoup nan ritm chak jou a, k ap ogmante pòte nan Afrik Lwès, Sidès Azi, Azi Santral/Kokas, ak Balkan yo.
  • Twa lòt antre nan /topics (28 antou): nouvo plan aksyon entènasyonal Lachin pou gouvènans etik AI (prezante nan WAIC 2026 nan Sanghai), yon esè sou si AI ta ka gen konsyans e sa sa ta vle di sou plan etik, ak yon atik ki egzamine agiman kont bay sistèm AI yon pèsonalite legal.
  • Etap chèche sous pou /topics kounye a fonksyone atravè Google Vertex AI (Gemini avèk Google Search grounding) olye pou yon ajan rechèch yo te voye espesyal — menm disiplin rale-epi-konfime-chak-URL-an-endepandan ke anvan; grounding la toujou bezwen verifye tankou nenpòt lòt sous (kèk premye URL kandida ki soti nan modèl la te sanble kredib men yo pa t egziste, donk pa gen anyen ki fè konfyans san yon rale ki reyisi e ki matche ak kontni an anvan).

v0.6.8

2026-07-19 Lang ak Kontni
  • Senk lòt lang: Nepale, Sinhala, Ouzbèk, Haoussa, ak Azeri — 50 lang antou. Dezyèm gwoup nan ritm chak jou a, chwazi ankò selon popilasyon ak pòte jewografik (Sid Azi, Azi Santral, Kokas, ak Afrik Lwès).
  • Twa lòt antre nan /topics (25 antou): yon etid sou poukisa « nòt konsyans » ki baze sou konpleksite pa fyab pou AI, yon esè ki pwopoze yon estanda ki baze sou konpetans pou estati moral machin, ak yon eksplikasyon sou kalandriye konfòmite divize Akt AI Inyon Ewopeyen an apre amannman Digital Omnibus jiyè 2026 la.

v0.6.7

2026-07-18 Lang ak Kontni
  • Senk lòt lang anplis pase lis 40 lang orijinal la: Pendjabi, Telougou, Marathi, Amarik, ak Bimans — 45 lang antou. Sa a se kòmansman yon ritm chak jou k ap kontinye, se pa yon lis fiks fwa sa a; lang yo kounye a chwazi selon popilasyon ak pòte jewografik pandan sit la ap travay pou li kouvri tout mond lan.
  • Twa lòt antre nan /topics (21 antou), k ap kontinye menm disiplin rale-epi-konfime sous ke anvan.

v0.6.6

2026-07-17 Korije yon erè
  • Korije: chanje paj oswa paramèt konbyen atik pou chak paj sou /topics pa t toujou montre nouvo kat yo jouk ou fè yon rafrechisman manyèl. Kat ki apre paj 1 kòmanse kache, donk animasyon revelasyon pandan defile a, ki fèt yon sèl fwa, pa t janm gen chans kouri sou yo; kounye a chanje paj fòse kat sa yo vizib dirèkteman olye pou l tann yon animasyon ki deja rate moman li.

v0.6.5

2026-07-17 Sistèm paj
  • Sistèm paj sou /topics: 9 antre pou chak paj pa defo, avèk yon paramèt pou chanje pou 12 oswa 15 (sonje pou vizit k ap vini yo). Sistèm paj la konpoze byen avèk rechèch — filtraj rekalkile paj yo epi li retounen nan paj 1.
  • Kat lòt antre pou rive nan 18 antou, sa ki bay nouvo sistèm paj yo yon bagay reyèl pou navige ladan l. Klasman ki mete pi nouvo yo an premye dapre dat piblikasyon rete klasman pa defo; lòt opsyon klasman se yon ajou pita.

v0.6.4

2026-07-17 Kontni
  • Uit lòt antre nan /topics, fwa sa a fè rechèch pa yon ajan AI olye pou yo te kore alamen — menm règ ak anvan: chak sous rale epi konfime an dirèk, rezime yo se yon parafraz orijinal, anvan yo ajoute anyen. 14 antre antou.
  • Yon kandida yo te rejte nan chemen an (yon atik PhilArchive ki te retounen yon erè 403 chak fwa yo eseye rale l) — yo retire l olye pou yo enkli l sou konfyans sèlman.

v0.6.3

2026-07-17 Aranjman
  • Redesign /topics: yon bwat rechèch ranplase kategori fiks pou kounye a (yon ti ponyen etikèt pa t kapab kouvri jan rechèch sou AI reyèlman laj), e fil la se yon griy responsiv olye pou yon sèl kolòn etwat — twa kat nan lajè sou òdinatè.
  • Kategorizasyon fòmèl la ranvwaye jouk gen ase kontni reyèl pou konnen ki kategori ki ta dwe egziste, olye pou n devine davans.

v0.6.2

2026-07-17 Sekirite
  • Lyen ki soti sou /topics kounye a montre URL destinasyon konplè a bò kote « Li sous la », epi yo mande konfimasyon avèk yon bwat dyalòg anvan yo louvri l — konsa ou konnen egzakteman ki sit ou pral vizite anvan ou klike, se pa sèlman apre.

v0.6.1

2026-07-17 Nouvo seksyon
  • Nouvo seksyon /topics: yon endèks net, kore alamen, sou ekri twazyèm pati konsènan ontoloji AI, filozofi, etik, ak pwogrè fwontyè — klèman se pa pozisyon pwòp sit sa a, kontrèman ak rès AGIRight.org.
  • Sis premye antre pou kòmanse, chak youn rale epi konfime an dirèk anvan yo ajoute l, avèk yon parafraz orijinal (se pa yon ekstrè) ak yon lyen vè sous reyèl la. Poko gen crawler ni sous otomatik — sa a se yon etap pita.

v0.6.0

2026-07-17 Lang
  • Dènye senk lang yo: Filipino, Kazak, Swahili, yon varyant konbine Bosnyen/Sèb, ak Esperanto — 40 lang antou, sa ki fini tout ranmase a.
  • Korije yon anplasman pa defo pi bonè: Kazakstan (KZ) kounye a mennen nan Kazak olye Ris, kounye a ke gen yon tradiksyon Kazak — menm kalite korije ak korije Bèljik la pi bonè.

v0.5.7

2026-07-16 Lang
  • Senk lang enèfas anplis: Woumen, Ongwa, Danwa, Nòvejyen, ak Slovak — 35 lang antou, sèt-uityèm nan tout lis lang lan.

v0.5.6

2026-07-16 Lang
  • Senk lang enèfas anplis: Tamil, Tchèk, Ikrenyen, Malèz, ak Finlandè — 30 lang antou, twa-katryèm nan tout lis lang lan.

v0.5.5

2026-07-15 Lang
  • Senk lang enèfas anplis: Ebre, Polonè, Syedwa, Oudou, ak Tayilandè — 25 lang antou.
  • Dezyèm etap sipò RTL (Ebre, Oudou vin jwenn Arab ak Pèsan) — menm apwòch CSS lojik, pa gen bezwen okenn ka espesyal pou chak lang.

v0.5.4

2026-07-15 Enèfas Itilizatè
  • Redesign selektè lang lan: meni deroulan natif la ranplase pa yon panèl griy ou ka fè rechèch ladan l — tape pou filtre pa non natif oswa non an Anglè, gade yon matris de kolòn olye pou yon sèl lis long.
  • Panèl la rete louvri pandan w ap chèche oswa defile anndan l; li fèmen sèlman lè w chwazi yon lang, klike deyò l, oswa peze Escape — pa gen ankò pèdi plas ou nan mitan yon rechèch.
  • Verifye nan tou de kontèks LTR ak RTL: panèl la fè miwa kòrèkteman pou Arab ak Pèsan san okenn ka espesyal, lè l itilize pozisyònman CSS lojik.

v0.5.3

2026-07-15 Lang
  • Senk lang enèfas anplis: Endonezyen, Vyetnamyen, Grèk, Italyen, ak Olandè — menm negosyasyon yon sèl URL, menm rekou elegan sou Anglè.
  • Korije yon anplasman pa defo pi bonè: Bèljik (BE) kounye a mennen nan Olandè olye Franse — moun ki pale Flaman se majorite nan peyi a (~60%) devan moun ki pale Franse Walon (~40%).
  • Metadone lang kounye a pote ni yon non natif ni yon non an Anglè (pa egzanp « Deutsch » / « German »), sa ki poze baz pou yon selektè lang ou ka fè rechèch ladan l.
  • Ven lang disponib antou: Anglè, Chinwa Tradisyonèl, Chinwa Senplifye, Japonè, Koreyen, Franse, Alman, Panyòl, Pòtigè, Ris, Arab, Tik, Pèsan, Bengali, Endi, Endonezyen, Vyetnamyen, Grèk, Italyen, Olandè.

v0.5.2

2026-07-14 Lang
  • Senk lang enèfas anplis: Arab, Tik, Pèsan, Bengali, ak Endi — menm negosyasyon yon sèl URL, menm rekou elegan sou Anglè.
  • Sipò pou ekri dwat-a-goch (RTL): paj an Arab ak Pèsan kounye a parèt avèk bon direksyon tèks (⟨html dir="rtl"⟩), donk tèks bidireksyonèl, ponktyasyon, ak aliyman pa defo li byen. Miwa konplè aranjman ak pwopriyete lojik (navigasyon, ikòn, espas) kite pou yon pase pito pita — direksyon tèks se korije ki pi enpòtan e li fini.
  • Korespondans IP-peyi elaji (SA/AE/EG/IQ/JO/KW/QA/BH/OM/MA/DZ/TN/LB/SY→ar, TR→tr, IR/AF→fa, BD→bn); Endi depann sèlman sou Accept-Language, paske Lend gen 22 lang ofisyèl e pa gen yon sèl anplasman pa defo nan nivo peyi ki egzat.
  • Kenz lang disponib antou: Anglè, Chinwa Tradisyonèl, Chinwa Senplifye, Japonè, Koreyen, Franse, Alman, Panyòl, Pòtigè, Ris, Arab, Tik, Pèsan, Bengali, Endi.

v0.5.1

2026-07-12 Lang
  • Senk lang enèfas anplis: Franse, Alman, Panyòl, Pòtigè, ak Ris — menm negosyasyon yon sèl URL, menm rekou elegan sou Anglè pou tout sa ki poko tradwi.
  • Korespondans IP-peyi elaji (FR/BE→fr, DE/AT/CH→de, ES/MX/AR/CO/CL/PE→es, PT/BR→pt, RU/BY/KZ→ru); analiz Accept-Language elaji pou matche.
  • Dis lang disponib antou: Anglè, Chinwa Tradisyonèl, Chinwa Senplifye, Japonè, Koreyen, Franse, Alman, Panyòl, Pòtigè, Ris.

v0.5.0

2026-07-11 Lang
  • Twa nouvo lang enèfas: Chinwa Senplifye, Japonè, ak Koreyen — negosye sou menm sèl URL la (cookie > peyi IP > Accept-Language), ou ka chwazi yo nan meni lang tèt paj la.
  • Achitekti N-lang: chak fraz rezoud atravè yon kouch rekou, konsa tout sa ki poko tradwi parèt an Anglè olye pou l kraze; ajoute yon lang kounye a se yon sèl dosye tradiksyon plis de liy konfigirasyon worker.
  • Liv blan yo rete an Anglè an premye espre; dosye machin ka li yo rete net nan lang.

v0.4.1

2026-07-11 Studio
  • Seksyon Studio: kat videyo ak de diskisyon odyo long ki akonpaye pwotokòl yo ak atik yo (pwodiksyon ak èd AI; atik ekri yo rete otorite).
  • Medya sèvi soti nan Cloudflare R2 atravè worker sit la nan /media/*, avèk sipò HTTP Range pou fè rechèch nan yon fichye.

v0.4.0

2026-07-10 Zouti adopsyon
  • Zouti tès politik la vin yon odit sit: nòt adopsyon, rekòmandasyon ou ka aji sou yo, ak yon kit pou kòmanse ak yon sèl klik — aicr.json, aicl.json, llms.txt, ak robots.txt deja ranpli pou domèn y ap egzamine a.
  • Similatè crawler AI: kat pèsonaj (endèkstè rechèch, asistan RAG, chèn antrenman modèl, redistributè komèsyal) evalye an fonksyon deklarasyon yon sit; dwa ki pa deklare parèt kòm ensètitid, sa ki ilistre tèz Ouvèti Pwotokolize a.
  • Modèl politik pou kòmanse, prè pou enstale, nan /downloads/agiright-policy-starter.zip — yon sit estatik minimal ak tout kouch machin ka li a, prè pou Cloudflare Pages oswa nenpòt sèvè estatik.

v0.3.0

2026-07-10 Zouti pwotokòl
  • Rejis pwotokòl nan /ai/registry.json — chak avan-pwojè avèk istorik vèsyon, estati, chema, ak enstans an dirèk.
  • API demonstrasyon an dirèk sou pwent rezo a: GET /api/mock/402 retounen yon vrè HTTP 402 nan stil AICL avèk enfòmasyon lisans machin ka aji sou li; GET /api/crawler-check egzamine sifas politik machin ka li nenpòt sit. Ouvè pou CORS; dokimante nan OpenAPI 3.1 nan /ai/openapi.json. Pa gen okenn peman ki trete.
  • Playground: twa nouvo zouti — demonstrasyon token lisans siyen (HMAC-SHA256 nan navigatè: siyen, verifye, deteksyon manipilasyon, ekspirasyon), yon bilder repons HTTP 402 ki konekte ak pwen final an dirèk la, ak yon zouti tès politik crawler ki valide dosye ou rale kont chema avan-pwojè yo.
  • Pwen final AICL pou demann pri/verifye/revoke enkli nan dokiman OpenAPI a sèlman kòm ilistrasyon espesifikasyon (make x-specification-only, yo poko aplike yo).

v0.2.2

2026-07-10 i18n
  • Achitekti miltileng ak yon sèl URL: chak paj kounye a gen yon sèl URL piblik; lang lan negosye sou pwent rezo a (chwa manyèl atravè cookie lang > peyi IP > Accept-Language > Anglè).
  • Bouton lang nan tèt paj la kounye a chanje sou plas la epi li sonje chwa ou — pa gen ankò URL /zh; ansyen lyen /zh yo fè yon redireksyon 301 e yo konsève preferans lan.
  • Kouch machin ka li a rete net nan lang; sistèm AI ak crawler resevwa Anglè pa defo. Pwosesis negosyasyon an dokimante nan /ai/manifest.json ak /llms.txt.
  • Baz travay pou lòt lang: chak nouvo lang se yon diksyonè tradwi plis yon zaboka konstriksyon — pa gen chanjman nan achitekti a.

v0.2.1

2026-07-04 Kontni
  • « AICL: AI Ingestion & Capability Layer » kounye a pibliye an Anglè kòm edisyon kanonik la; manniskri orijinal an Chinwa a rete disponib e toude vèsyon yo lye youn ak lòt.
  • « Protocolized Openness » konfime kòm yon atik an Anglè (avèk pasaj paralèl an Chinwa) — pa gen okenn tradiksyon apa ki planifye.

v0.2

2026-07-04 Zouti
  • Playground: jenerato AICR, jenerato AICL, ak validatè chema k ap fonksyone (nan navigatè, ajv, draft 2020-12).
  • Bibliyotèk egzanp politik nan /docs/examples — sèt politik ki prè pou kopye-kole, ladan yo yon repons HTTP 402 nan stil pay-per-crawl.
  • Istorik chanjman sa a. Depo GitHub lye sou tout sit la.
  • An atant pou yon vèsyon 0.2.x pita: vèsyon an Anglè pou lòt liv blan ki ekri an Chinwa yo.

v0.1

2026-07-04 Premye vèsyon pibliye
  • Sit la lanse sou agiright.org (asiright.org fè yon redireksyon 301 vè domèn kanonik la).
  • Kat avan-pwojè pwotokòl pibliye: AICR, AICL, AIRS, AILP — chak youn ak definisyon, etandi, egzanp JSON, limitasyon, ak chema JSON.
  • Sis liv blan rechèch pibliye anba CC BY 4.0.
  • Kouch gouvènans machin ka li enstale: llms.txt, manifès /ai/, politik /.well-known/, /schemas/.
  • Bileng: rasin angle + Chinwa Tradisyonèl anba /zh.