Docs
Changelog
Version history an site in im protocol draft ko an. Oktak ko breaking ilo spec kar record ijin.
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 Kajin ko im Kontent- 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 Kajin ko im Kontent- Ḷalem kajin bar juon: Yoruba, Khmer, Mongolian, Armenian, im Bulgarian — 55 kajin aolep. Kein ka-jilu batch iuṃwin cadence in raan otemjej, ej kalaplọk ñan West Africa, Southeast Asia, Central Asia/Caucasus, im Balkans.
- Jilu entry bar juon ilo /topics (28 aolep): action plan ekāāl an China kōn international AI ethics governance (kar kwaḷọk ilo WAIC 2026 ilo Shanghai), juon essay kōn eḷaññe AI emaroñ conscious im ta eo enaaj meḷeḷein ilo ethics, im juon paper ej review case eo ṇae lewōj legal personhood ñan AI systems.
- Sourcing step eo an /topics kiiō ej ilọk ilujen Google Vertex AI (Gemini kōn Google Search grounding) jab juon search agent kar dispatch — ejja wōt discipline in fetch-and-independently-confirm-every-URL āinwōt ṃokta; grounding ej aikuj wōt verification āinwōt jabdewōt source jet (jet URL ṃokta jān model eo raar āinwōt ren ṃool ak ejjeḷọk aer, kōnke ejjeḷọk men eṇ trust ṃokta jān juon fetch e resolvable im content-matching).
v0.6.8
2026-07-19 Kajin ko im Kontent- Ḷalem kajin bar juon: Nepali, Sinhala, Uzbek, Hausa, im Azerbaijani — 50 kajin aolep. Kein ka-ruo batch iuṃwin cadence in raan otemjej, kar bar kāālōt kōn population im geographic reach (South Asia, Central Asia, Caucasus, im West Africa).
- Jilu entry bar juon ilo /topics (25 aolep): juon study kōn etke “consciousness score” ko complexity-based re jab lōke ñan AI, juon essay ej kwaḷọk juon competence-based standard ñan machine moral status, im juon explainer kōn split compliance timeline an EU AI Act ālikin amendment eo Digital Omnibus ilo July 2026.
v0.6.7
2026-07-18 Kajin ko im Kontent- Ḷalem kajin bar juon jān list eo ṃokta an 40-kajin: Punjabi, Telugu, Marathi, Amharic, im Burmese — 45 kajin aolep. Men in ej jinoin juon cadence in raan otemjej, jab juon list e pen ilo iien in; kajin ko kiiō rej kāālōt kōn population im geographic reach ke site in ej jerbal ñan tōpar aolepān laḷ.
- Jilu entry bar juon ilo /topics (21 aolep), ej wōnṃaanḷọk kōn ejja discipline in fetch-and-confirm sourcing āinwōt ṃokta.
v0.6.6
2026-07-17 Kōkāāl bug- Kar kōkāāl: oktak page ko ak setting in per-page ioon /topics ear jab aolep iien kwaḷọk card ko ekāāl ṃae juon refresh kōn pā. Card ko ālikin page 1 rej jino ettino, kōnke animation in scroll-reveal an site eo juon wōt alen ear jab wor an iien ñan jerbal ioer; kiiō paging ej kōttōpar card ko bwe ren alikkar directly jab kōttar animation eo ear jako an iien.
v0.6.5
2026-07-17 Pagination- Pagination ioon /topics: 9 entry kōn page āinwōt default, ewor setting ñan oktak ñan 12 ak 15 (ej keememej ilo visit ko). Paging ej jerbal jiṃwe ippān search — filtering ej bar watōk page ko im jepḷaak ñan page 1.
- Emān entry bar juon ñan tōpar 18 aolep, im lewōj ñan pagination ekāāl juon men e ṃool ñan page ie. Kāāl-ṃokta kōn ran in publication ej pād wōt āinwōt default sort; sort option ko jet renaaj kobaik tokālik.
v0.6.4
2026-07-17 Kontent- Ruwalitōk entry bar juon ilo /topics, ilo iien in AI agent ear kōṃṃan research jab armej kōn pā — ejja kien wōt āinwōt ṃokta: source otemjej kar bōk im kaṃool e mour, summary ko rej paraphrase e kāāl, ṃokta jān jabdewōt kobaik. 14 entry aolep.
- Juon candidate kar jolọk ilo iaḷ eo (juon PhilArchive paper ear jepḷaak kōn 403 ilo aolep alen ear kajjioñ fetch) — kar jolọk jab kobaik kōn trust wōt.
v0.6.3
2026-07-17 Layout- Kar bar design /topics: juon search box ej pinej jenkwan category ko re pen ilo iien in (jibubu tag re ban kobaik aolepān AI research), im feed eo ej juon grid responsive jab juon column wōt e aidik — jilu card depakpak ioon desktop.
- Categorization eo formal ej kōttar ṃae eḷap kontent e ṃool bwe jen jeḷā ta ko category ren ṃool, jab watwat ṃokta.
v0.6.2
2026-07-17 Safety- Link ko outbound ioon /topics kiiō rej kwaḷọk aolepān destination URL eo iturin “Read the source,” im rej kajjitōk kaṃool kōn juon dialog ṃokta jān an peḷḷọk — bwe kwōn jeḷā alikkar ta site eo kwōnaaj lo ṃokta jān aṃ click, jab ālikin wōt.
v0.6.1
2026-07-17 Section Ekāāl- Section ekāāl /topics: juon index e neutral, kar kāālōt kōn pā, kōn men ko armej ro jet raar je kōn AI ontology, philosophy, ethics, im frontier progress — alikkar jab ḷōmṇak eo an site in make, oktak jān bar ijoko jet an AGIRight.org.
- Jiljino seed entry ñan jino kake, kajjojo kar fetch im kaṃool e mour ṃokta jān an kobaik, kōn juon paraphrase ekāāl (jab juon excerpt) im juon link ñan source eo e ṃool. Ejjañin wor crawler ak automated sourcing — men eo enaaj itok ilo phase tokālik.
v0.6.0
2026-07-17 Kajin ko- Ḷalem kajin āliktata: Filipino, Kazakh, Swahili, juon variant Bosnian/Serbian eṃōj kobaik, im Esperanto — 40 kajin aolep, ej kajeṃḷọke rollout eo weeppān.
- Kar kōkāāl juon default ṃokta: Kazakhstan (KZ) kiiō ej map ñan Kazakh jab Russian, kiiō ke ewor translation ilo Kazakh — ejja wōt kain kōkāāl āinwōt eo ṃokta ñan Belgium.
v0.5.7
2026-07-16 Kajin ko- Ḷalem kajin bar juon ñan interface: Romanian, Hungarian, Danish, Norwegian, im Slovak — 35 kajin aolep, jiljilimjuon ṃōttan ruwalitōk in aolepān list in kajin.
v0.5.6
2026-07-16 Kajin ko- Ḷalem kajin bar juon ñan interface: Tamil, Czech, Ukrainian, Malay, im Finnish — 30 kajin aolep, jilu ṃōttan emān in aolepān list in kajin.
v0.5.5
2026-07-15 Kajin ko- Ḷalem kajin bar juon ñan interface: Hebrew, Polish, Swedish, Urdu, im Thai — 25 kajin aolep.
- Kein ka-ruo alen an RTL support (Hebrew, Urdu rej deḷọñ ippān Arabic im Persian) — ejja wōt logical-CSS approach, ejjeḷọk special-casing kōn kajjojo kajin ej aikuj.
v0.5.4
2026-07-15 UI- Kar bar design language picker eo: native dropdown eo kar pinej jenkwan kōn juon grid panel emaroñ search kake — je bwe en filter kōn etan native ak English, lale juon matrix ruo column jab juon list eaetok.
- Panel eo ej pād open ke kwōj search ak scroll ilowaan; ej kilōk wōt ñe kwōj kāālōt juon kajin, click ilikin, ak push Escape — ejjeḷọk bar jako an jikin eo aṃ ilo lukwōn juon search.
- Kar verify ilo LTR im RTL context otemjej: panel eo ej mirror jiṃwe ñan Arabic im Persian ejjeḷọk special-casing, kōn logical CSS positioning.
v0.5.3
2026-07-15 Kajin ko- Ḷalem kajin bar juon ñan interface: Indonesian, Vietnamese, Greek, Italian, im Dutch — ejja wōt negotiation kōn juon URL, ejja wōt English āinwōt fallback.
- Kar kōkāāl juon default ṃokta: Belgium (BE) kiiō ej map ñan Dutch jab French — ri-kōnono Flemish rej eḷap iaan ro ilo aelōñ eo (~60%) jān ri-kōnono French Walloon (~40%).
- Metadata in kajin kiiō ej bōkḷọk ruo etan — etan native im etan English (āinwōt “Deutsch” / “German”), im ej kōṃṃan groundwork ñan juon language picker emaroñ search kake.
- Roñoul kajin rej mour aolep: English, Traditional Chinese, Simplified Chinese, Japanese, Korean, French, German, Spanish, Portuguese, Russian, Arabic, Turkish, Persian, Bengali, Hindi, Indonesian, Vietnamese, Greek, Italian, Dutch.
v0.5.2
2026-07-14 Kajin ko- Ḷalem kajin bar juon ñan interface: Arabic, Turkish, Persian, Bengali, im Hindi — ejja wōt negotiation kōn juon URL, ejja wōt English āinwōt fallback.
- RTL support: page ko Arabic im Persian kiiō rej render kōn text direction eo jiṃwe (⟨html dir="rtl"⟩), kōnke bidi text, punctuation, im default alignment rej riit jiṃwe. Layout mirroring e weeppān (nav, icon ko, spacing) ej pād ñan tokālik — text direction eo ej kein kōkāāl eḷap tata tokjān im eṃōj e.
- IP-country mapping kar kalaplọk (SA/AE/EG/IQ/JO/KW/QA/BH/OM/MA/DZ/TN/LB/SY→ar, TR→tr, IR/AF→fa, BD→bn); Hindi ej lōke Accept-Language wōt, kōnke India ewor 22 official kajin im ejjeḷọk juon default ilo country-level ej jiṃwe.
- Joñoul ḷalem kajin rej mour aolep: English, Traditional Chinese, Simplified Chinese, Japanese, Korean, French, German, Spanish, Portuguese, Russian, Arabic, Turkish, Persian, Bengali, Hindi.
v0.5.1
2026-07-12 Kajin ko- Ḷalem kajin bar juon ñan interface: French, German, Spanish, Portuguese, im Russian — ejja wōt negotiation kōn juon URL, ejja wōt English āinwōt fallback ñan jabdewōt ejjañin translate.
- IP-country mapping kar kalaplọk (FR/BE→fr, DE/AT/CH→de, ES/MX/AR/CO/CL/PE→es, PT/BR→pt, RU/BY/KZ→ru); Accept-Language parsing kar kalaplọk bwe en ekkar.
- Joñoul kajin rej mour aolep: English, Traditional Chinese, Simplified Chinese, Japanese, Korean, French, German, Spanish, Portuguese, Russian.
v0.5.0
2026-07-11 Kajin ko- Jilu kajin ekāāl ñan interface: Simplified Chinese, Japanese, im Korean — kar negotiate ilo ejja URL wōt (cookie > IP country > Accept-Language), emaroñ kāālōt jān menu in kajin ilo header.
- N-language architecture: string otemjej ej ilọk ilujen juon fallback layer, kōnke jabdewōt ejjañin translate ej waḷọk ilo English jab kọkkure page eo; kobaik juon kajin kiiō ej juon file in translation kobaik ippān ruo laain ilo worker config.
- Whitepaper ko rej pād English-first kōn design; file ko machine-readable rej pād language-neutral.
v0.4.1
2026-07-11 Studio- Studio section: emān video im ruo audio discussion eaetok rej ipae protocol ko im paper ko (AI-assisted production; paper ko kar je rej pād wōt āinwōt eo ṃool tata).
- Media ej itok jān Cloudflare R2 ilujen site worker eo ilo /media/*, ewor an HTTP Range support ñan seeking.
v0.4.0
2026-07-10 Kein Jerbal ñan Adoption- Policy tester kar upgrade ñan juon site audit: adoption score, recommendation ko emaroñ kōṃṃani, im juon starter kit kōn juon click — aicr.json, aicl.json, llms.txt, im robots.txt kar prefill ñan domain eo kar inspect.
- AI crawler simulator: emān persona (search indexer, RAG assistant, model-training pipeline, commercial redistributor) rej kar joñe ekkar ñan kwaḷọk ko an juon site; maroñ ko re jañin kar kwaḷọk rej waḷọk āinwōt uncertainty, im men in ej kwaḷọk thesis eo an Protocolized Openness.
- Template in policy emaroñ deploy ilo /downloads/agiright-policy-starter.zip — juon site static e dik wōt ewor an layer machine-readable weeppān, pojak ñan Cloudflare Pages ak jabdewōt static host.
v0.3.0
2026-07-10 Kein Jerbal an Protocol- Protocol registry ilo /ai/registry.json — draft otemjej ewor an version history, status, schema, im live instance.
- Live demo API ioon edge eo: GET /api/mock/402 ej jepḷaak kōn juon HTTP 402 e ṃool ilo wāween AICL ewor an info in laisin machine-actionable; GET /api/crawler-check ej inspect surface in policy machine-readable an jabdewōt site. CORS-open; kar document ilo OpenAPI 3.1 ilo /ai/openapi.json. Ejjeḷọk kōḷḷā eo ej process.
- Playground: jilu kein jerbal ekāāl — signed license token demo (HMAC-SHA256 ilowaan browser: sign, verify, tamper detection, expiry), HTTP 402 response builder eṃōj kobaik ñan live endpoint eo, im juon crawler policy tester ej validate file ko kar fetch ekkar ñan draft schema ko.
- Endpoint ko an AICL ñan quote/verify/revoke rej pād ilo document OpenAPI āinwōt waanjoñak specification wōt (kar mark e x-specification-only, ejjeḷọk implement e).
v0.2.2
2026-07-10 i18n- Single-URL multilingual architecture: page otemjej kiiō ewor an juon URL rāllep; kajin eo ej negotiate ilo edge eo (kāālōt kōn pā kōn lang cookie > IP country > Accept-Language > English).
- Button in kajin ilo header kiiō ej oktak ilo jikin eo wōt im keememej kāālōt eo aṃ — ejjeḷọk bar /zh URL ko; link ko /zh etto rej 301-redirect im kōjparok preference eo.
- Layer machine-readable ej pād language-neutral wōt; AI systems im crawler ko rej bōk English āinwōt default. Negotiation kar document ilo /ai/manifest.json im /llms.txt.
- Groundwork ñan kajin ko bar jet: kajjojo kajin ekāāl ej juon dictionary eṃōj translate kobaik ippān juon build tree — ejjeḷọk oktak ilo architecture.
v0.2.1
2026-07-04 Kontent- “AICL: AI Ingestion & Capability Layer” kiiō kar publish ilo English āinwōt canonical edition; manuscript eo ṃokta ilo Chinese ej pād wōt im version ko ruo rej cross-link.
- “Protocolized Openness” kar kaṃool āinwōt juon paper ilo kajin English (ippān passage ko parallel ilo Chinese) — ejjeḷọk translation make kar planned.
v0.2
2026-07-04 Kein Jerbal- Playground: AICR generator ej jerbal, AICL generator, im schema validator (ilowaan browser, ajv, draft 2020-12).
- Library in waanjoñak policy ilo /docs/examples — jiljilimjuon policy rej pojak ñan copy-paste, kobaik ippān juon HTTP 402 response ilo wāween pay-per-crawl.
- Changelog in. GitHub repository kar link ilo aolepān site.
- Ej kōttar ñan 0.2.x tokālik: version ko ilo English an whitepaper ko ilo kajin Chinese re jañin translate.
v0.1
2026-07-04 Release Ṃokta Tata- Site eo ear jino ilo agiright.org (asiright.org ej 301-redirect ñan canonical domain eo).
- Emān protocol draft kar publish: AICR, AICL, AIRS, AILP — kajjojo ewor an definition, scope, JSON waanjoñak, limitation ko, im JSON Schema.
- Jiljino research whitepaper kar publish iuṃwin CC BY 4.0.
- Layer in governance machine-readable kar deploy: llms.txt, /ai/ manifest ko, /.well-known/ policy ko, /schemas/.
- Ruo kajin: English āinwōt jabōn eo laḷtata + Chinese eo etto iuṃwin /zh.