Documentación
Changelog
Versión ymaguare ko tenda ha iprotokolo borrador-kuéra rehegua. Cambio especificación ombyaíva oñemoĩ ápe.
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 Ñe'ẽ ha Contenido- 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 Ñe'ẽ ha Contenido- 5 ñe'ẽ ambue: yoruba, jemer, mongol, armenio, ha búlgaro — 55 ñe'ẽ opavavete. Mbohapyha grupo ritmo ára ha ára-pegua, omyasãi África Oeste, Asia Sudeste, Asia Central/Cáucaso, ha Balcanes.
- Mbohapy jehai pyahu /topics-pe (28 opavave): China akcción plan internacional pyahu sãmbyhy ética IA-gua (oñemyasãi WAIC 2026-pe Shanghai-pe), peteĩ ensayo IA ikatúpa iconciente ha mba'épa upéva he'ise éticamente, ha peteĩ kuatia ojesarekóva argumento IA sistema-pe personalidad legal ome'ẽ'ỹ hag̃ua rehe.
- Etapa fuente jeheka /topics-pegua ko'ág̃a oiko Google Vertex AI rupive (Gemini Google Search grounding reheve), ndaha'éima peteĩ agente jeheka ojehaíva rupive — pe rembiapoukapy peteĩcha: jehupyty ha jejesareko independiente peteĩ-teĩ URL-pe, grounding oikotevẽ gueteri ojejesareko oimeraẽ fuente-icha (mokõi térã mbohapy URL candidato ñepyrũguáva modelo-gui ojehecha porãha ha katu ndaipóri hague, upévare mba'eve ndoñemboroviaietei jehupyty ikatúva ha contenido ojoguáva'ỹre).
v0.6.8
2026-07-19 Ñe'ẽ ha Contenido- 5 ñe'ẽ ambue: nepalí, cingalés, uzbeko, hausa, ha azerbaiyano — 50 ñe'ẽ opavavete. Mokõiha grupo ritmo ára ha ára-pegua, oñeporavo jey población ha extensión geográfico rupi (Asia Sur, Asia Central, Cáucaso, ha África Oeste).
- Mbohapy jehai pyahu /topics-pe (25 opavave): peteĩ jehesa'ỹijo mba'ére «puntaje conciencia» complejidad-pe ojejapóva ndajeroviaporãi IA-pe g̃uarã, peteĩ ensayo oikuaaukáva estándar competencia-pe ojejapo IA reko moral-pe g̃uarã, ha peteĩ explicación EU AI Act calendario cumplimiento oñembojoyke hague Digital Omnibus jasypoteĩ 2026 rire.
v0.6.7
2026-07-18 Ñe'ẽ ha Contenido- 5 ñe'ẽ ambue 40 ñe'ẽ rysýi ijypykuégui: punjabi, telugu, maratí, amárico, ha birmano — 45 ñe'ẽ opavavete. Kóva ha'e peteĩ ritmo ára ha ára pyahu oñepyrũva, ndaha'éi ma peteĩ lista mbojoyke ramo; ñe'ẽ-kuéra ko'ág̃a oñeporavo población ha extensión geográfico rupi, tenda oho aja ohupyty hag̃ua cobertura global opavavete.
- Mbohapy jehai pyahu /topics-pe (21 opavave), osegui pe rembiapoukapy fuente jehupyty ha jejesareko peteĩcha ymaguare.
v0.6.6
2026-07-17 Jejavy mbojoheipy- Oñemyatyrõ: emoambue jave rogue térã ñembohysýi mboyve rogue-pe g̃uarã /topics-pe ndojehechaukái porã umi tarjeta pyahu peteĩ actualización manual peve. Umi tarjeta rogue 1 rire oñepyrũ ñemi ramo, upévare pe animación jehecha peteĩ jey año ndaikatúiva oiko hese-kuéra; ko'ág̃a paginación ombopu'ã umíva tarjeta jahecha hag̃ua tapiaite, ani oha'arõ peteĩ animación ohejaraẽ hague hi'aravo.
v0.6.5
2026-07-17 Paginación- Paginación /topics-pe: 9 jehai peteĩ-teĩ rogue-pe default ramo, oĩ ñemboheko ojembopu'ã hag̃ua 12 térã 15-pe (oñeñongatu jey jeike-jeike). Paginación oñembojoaju hekópe jeheka ndive — filtrado ombojoheipy rogue ha ombojevy rogue 1-pe.
- Irundy jehai ambue oĩ hag̃ua 18 opavavete, ome'ẽ pe paginación pyahu-pe mba'e teete oñemyasãi hag̃ua. Pyahuvéva raẽ fecha publicación rupi opyta orden default ramo; ambue orden opción ojembojoapy upe rire.
v0.6.4
2026-07-17 Contenido- Poapy jehai pyahu /topics-pe, ko'ág̃a peteĩ agente IA ojehesa'ỹijóva ndive, ndaha'éi po rupive oñemboheko hague — pe rembiapoukapy peteĩcha: opa fuente ojehupyty ha ojejesareko oiko hína hag̃ua, resumen ha'e paráfrasis original, mba'eve oñembojoapy mboyve. 14 jehai opavave.
- Peteĩ candidato oñembotovéva tape rupi (peteĩ kuatia PhilArchive-gua ome'ẽva 403 opa vez ojehupyty haguã) — oñembopo'i, ani oñembojoapy jerovia año-pe.
v0.6.3
2026-07-17 Ñemohenda- Oñemyatyrõ jey /topics: peteĩ caja jeheka-gua omyengovia ko'ág̃aite categoría mbojoyke-kuéra (michĩmi tag ndaikatúiva ohupyty mboýpa IA jehesa'ỹijo oipyso añetehápe), ha pe feed ha'e peteĩ grilla responsiva, ndaha'éi peteĩ columna michĩ año — mbohapy tarjeta ipupu computadora-pe.
- Categorización formal oñembohasa upe peve oĩ contenido tee heta, oikuaa hag̃ua mba'éichapa umi categoría vaerã oĩ, ani ojehecha raẽ nomás.
v0.6.2
2026-07-17 Seguridad- Enlace osẽva /topics-pe ko'ág̃a ohechauka URL destino opavavete «Emoñe'ẽ pe fuente» ykére, ha ojerure confirmación peteĩ diálogo rupive omyasãi mboyve — reikuaa hag̃ua mávapa tenda-pe reho mboyve eclic, ani upe rire año.
v0.6.1
2026-07-17 Sección Pyahu- Sección pyahu /topics: peteĩ índice neutral, po rupive oñemboheko, ambue tapicha ohaíva IA ontología, filosofía, ética, ha jeporeka frontera rehegua — claramente ndaha'éi ko tenda ñembohuguáiva, opa mba'e AGIRight.org-pegua ambue ári.
- Poteĩ jehai ñepyrũha, peteĩ-teĩ ojehupyty ha ojejesareko oiko hína hag̃ua oñembojoapy mboyve, peteĩ paráfrasis original reheve (ndaha'éi peteĩ extracto) ha peteĩ enlace fuente añetegua-pe. Ndaipóri crawler térã fuente automático gueteri — upéva ha'e peteĩ etapa upe rire g̃uarã.
v0.6.0
2026-07-17 Ñe'ẽ-kuéra- Umi 5 ñe'ẽ paha: filipino, kazajo, suajili, peteĩ variante bosnio/serbio ojoajúva, ha esperanto — 40 ñe'ẽ opavavete, omohu'ãva pe rollout completo.
- Oñemyatyrõ peteĩ default ymaguare: Kazajistán (KZ) ko'ág̃a ojoaju kazajo-pe, ruso rangue, oĩ ma haguére traducción kazajo — kóva ha'e pe jejavy oñemyatyrõ hague Bélgica-pe ojejapo haguéicha.
v0.5.7
2026-07-16 Ñe'ẽ-kuéra- 5 ñe'ẽ interfaz pyahu: rumano, húngaro, danés, noruego, ha eslovaco — 35 ñe'ẽ opavavete, pokõi óctavo rape guasu ñe'ẽ rysýi tuichakue rupi.
v0.5.6
2026-07-16 Ñe'ẽ-kuéra- 5 ñe'ẽ interfaz pyahu: tamil, checo, ucraniano, malayo, ha finlandés — 30 ñe'ẽ opavavete, mbohapy cuarto rape guasu ñe'ẽ rysýi tuichakue rupi.
v0.5.5
2026-07-15 Ñe'ẽ-kuéra- 5 ñe'ẽ interfaz pyahu: hebreo, polaco, sueco, urdu, ha tailandés — 25 ñe'ẽ opavavete.
- Mokõiha jeporu RTL (hebreo, urdu oike árabe ha persa ndive) — pe enfoque CSS lógico peteĩcha, ndaipóri caso especial ñe'ẽ-pe g̃uarã oipotáva.
v0.5.4
2026-07-15 Interfaz- Oñemyatyrõ jey ñe'ẽ picker: dropdown ijypykuégua oñemyengovia peteĩ panel grilla ikatúva ojejeheka — ehai efiltra hag̃ua téra ijypykuégua térã inglés-gua rupi, ejesareko peteĩ matriz mokõi columna-gua, peteĩ lista puku año rangue.
- Pe panel opyta ijurujáva eheka térã eguata aja hi'ári; oñembotýnte eiporavo jave peteĩ ñe'ẽ, eclic ambue tenda-pe, térã eipichy Escape — ndaipóri ma ne lugar rejora jeheka mbytépe.
- Oñemyesakã mokõive contexto-pe, LTR ha RTL: pe panel oñeespeja hekópe árabe ha persa-pe g̃uarã caso especial'ỹre, oiporu posicionamiento CSS lógico.
v0.5.3
2026-07-15 Ñe'ẽ-kuéra- 5 ñe'ẽ interfaz pyahu: indonesio, vietnamita, griego, italiano, ha holandés — peteĩ negociación URL peteĩ año-gua, peteĩ fallback inglés-pe g̃uarã.
- Oñemyatyrõ peteĩ default ymaguare: Bélgica (BE) ko'ág̃a ojoaju holandés-pe, francés rangue — flamenco ñe'ẽhára ha'e tetã apytépe hetavéva (~60%) valón francés ñe'ẽhára ári (~40%).
- Ñe'ẽ metadato ko'ág̃a orekóma téra ijypykuégua ha téra inglés-gua (techapyrãrõ «Deutsch» / «German»), omopyenda peteĩ picker ñe'ẽ-gua ikatúva ojejeheka.
- 20 ñe'ẽ oiko opavavete: inglés, chino tradicional, chino simplificádo, japonés, coreano, francés, alemán, español, portugués, ruso, árabe, turco, persa, bengalí, hindi, indonesio, vietnamita, griego, italiano, holandés.
v0.5.2
2026-07-14 Ñe'ẽ-kuéra- 5 ñe'ẽ interfaz pyahu: árabe, turco, persa, bengalí, ha hindi — peteĩ negociación URL peteĩ año-gua, peteĩ fallback inglés-pe g̃uarã.
- Jeporu RTL (asy ho'a katupyry): rogue árabe ha persa ko'ág̃a ojehecha dirección texto hekópe (⟨html dir="rtl"⟩), upévare texto bidi, puntuación, ha alineación default ojehecha hekópe. Espejo layout completo propiedad lógico-gua (nav, ícono, espacio) opyta peteĩ pulido paha-pe g̃uarã — dirección texto ha'e pe corrección importantevéva ha ojejapo ma.
- IP-tetã ñemoĩ ojembopu'ãve (SA/AE/EG/IQ/JO/KW/QA/BH/OM/MA/DZ/TN/LB/SY→ar, TR→tr, IR/AF→fa, BD→bn); Hindi oñembopyenda Accept-Language año-pe, India orekóva haguére 22 ñe'ẽ oficiál ha ndaipóri peteĩ default tetã-pegua iporãva año.
- 15 ñe'ẽ oiko opavavete: inglés, chino tradicional, chino simplificádo, japonés, coreano, francés, alemán, español, portugués, ruso, árabe, turco, persa, bengalí, hindi.
v0.5.1
2026-07-12 Ñe'ẽ-kuéra- 5 ñe'ẽ interfaz pyahu: francés, alemán, español, portugués, ha ruso — peteĩ negociación URL peteĩ año-gua, peteĩ fallback inglés-pe g̃uarã, umi mba'e ndojetraduci hague-rã.
- IP-tetã ñemoĩ ojembopu'ãve (FR/BE→fr, DE/AT/CH→de, ES/MX/AR/CO/CL/PE→es, PT/BR→pt, RU/BY/KZ→ru); Accept-Language ñemyesakã ojembopu'ãve avei.
- 10 ñe'ẽ oiko opavavete: inglés, chino tradicional, chino simplificádo, japonés, coreano, francés, alemán, español, portugués, ruso.
v0.5.0
2026-07-11 Ñe'ẽ-kuéra- Mbohapy ñe'ẽ interfaz pyahu: chino simplificádo, japonés, ha coreano — oñenegocia peteĩ URL peteĩ año-pe (cookie > tetã IP-gua > Accept-Language), ikatúva ojeporavo menú ñe'ẽ encabezado-gua-pe.
- Arquitectura N-ñe'ẽ-gua: peteĩ-teĩ cadena ñe'ẽ ojehupyty ñuãha fallback rupive, upévare umi mba'e ndojetraduci hague-rã ojehechauka inglés-pe, anive haguã oñembyai; embojoapy peteĩ ñe'ẽ pyahu ha'e ko'ág̃a peteĩ kuatia traducción ha mokõi línea worker configuración-gua.
- Kuatia jehesa'ỹijo opyta inglés-pe raẽ diseño rupive; kuatia oñemoñe'ẽkuaáva máquina rupive opyta ñe'ẽ neutral-icha.
v0.4.1
2026-07-11 Studio- Sección Studio: irundy video ha mokõi ñomongeta audio pukuvéva, oipytyvõva umi protokolo ha kuatia (producción IA ndive ojejapo hague; kuatia ohaipyre opyta mba'e oñemomba'éva).
- Medio oñeme'ẽ Cloudflare R2-gui tenda worker rupive /media/*-pe, HTTP Range reheve ojehecha jey hag̃ua.
v0.4.0
2026-07-10 Herramienta jeporu-gua- Política probador ojembopu'ã tenda auditoría-pe: puntaje jeporu, recomendación ikatúva ojejapo, ha peteĩ kit oñepyrũ hag̃ua peteĩ clic-pe — aicr.json, aicl.json, llms.txt, ha robots.txt oñembopyahu hague dominio ojejesarekóva-pe g̃uarã.
- IA crawler simulador: irundy persona (indexador jeheka-gua, RAG asistente, pipeline entrenamiento modelo-gua, redistribuidor comercial) oñemyesakã tenda declaración-kuéra rovake; derécho ndeclarapyréva ojehecha incertidumbre ramo, ohechauka tesis Jehepyme'ẽ Protokolizádo.
- Plantilla política oñemoĩkuaáva /downloads/agiright-policy-starter.zip-pe — peteĩ tenda estática mínima, ñuãha oñemoñe'ẽkuaáva máquina rupive opavavete reheve, oñemoĩkuaáva Cloudflare Pages térã oimeraẽ host estático-pe.
v0.3.0
2026-07-10 Protokolo Herramienta-kuéra- Protokolo registro /ai/registry.json-pe — peteĩ-teĩ borrador orekóva versión ymaguare, reko, esquema, ha instancia oikóva.
- API demo oikóva rembe'y-pe: GET /api/mock/402 ome'ẽ peteĩ HTTP 402 AICL-icha añetegua, información licenciamiento máquina ikatúva omba'apo hese reheve; GET /api/crawler-check ojesareko oimeraẽ tenda superficie política oñemoñe'ẽkuaáva máquina rupive. CORS ijurujáva; oñembohai OpenAPI 3.1-pe /ai/openapi.json-pe. Ndaipóri ñemyengovia oñeprocesa hague.
- Playground: mbohapy herramienta pyahu — demo token licencia firmado (HMAC-SHA256 navegador ryepýpe: firma, mbojoja, jehecha manipulación, tiempo límite), constructor mbohovái HTTP 402 ojoajúva endpoint oikóva ndive, ha peteĩ probador política crawler-gua ombojojáva kuatia ojehupytýva esquema borrador-kuéra rovake.
- AICL endpoint oferta/mbojoja/jejora-gua oñemoĩ documento OpenAPI-pe techapyrã especificación año ramo (marcádo x-specification-only, ndaha'éi ojejapo hague).
v0.2.2
2026-07-10 i18n- Arquitectura multilingüe URL peteĩ año-gua: peteĩ-teĩ rogue orekóma peteĩ URL público; ñe'ẽ oñenegocia rembe'y-pe (jeporavo manual lang cookie rupive > tetã IP-gua > Accept-Language > inglés).
- Pe votõ ñe'ẽ encabezado-pe ko'ág̃a oñemoambue ijehegui ha oñeñongatu ne jeporavo — ndaipóri ma URL /zh-gua; enlace /zh ymaguare 301-oñemboguereja ha oñeñongatu preferencia.
- Ñuãha oñemoñe'ẽkuaáva máquina rupive opyta ñe'ẽ neutral-icha; IA sistema-kuéra ha crawler-kuéra ohupyty inglés default ramo. Negociación oñembohai /ai/manifest.json ha /llms.txt-pe.
- Pyenda ñe'ẽ ambue g̃uarã: peteĩ-teĩ ñe'ẽ pyahu ha'e peteĩ diccionario traducido ha peteĩ árbol build — ndaipóri cambio arquitectura-pe.
v0.2.1
2026-07-04 Contenido- «AICL: AI Ingestion & Capability Layer» oñemondo ko'ág̃a inglés-pe edición canónico ramo; manuscrito chino ijypykuégua opyta oĩ, ha mokõive versión ojoaju.
- «Protocolized Openness» oñemomba'e peteĩ kuatia inglés-pe ramo (pasaje paralelo chino-pe reheve) — ndaipóri traducción mbojoyke oñeplania.
v0.2
2026-07-04 Herramienta-kuéra- Playground: generador AICR omba'apóva, generador AICL, ha validador esquema (navegador ryepýpe, ajv, draft 2020-12).
- Biblioteca política techapyrã /docs/examples-pe — pokõi política oñekopiakuaáva pya'e, oĩva peteĩ mbohovái HTTP 402 pay-per-crawl-icha.
- Ko changelog. Repositorio GitHub ojoajúva tenda opavavete-pe.
- Oha'arõva peteĩ 0.2.x g̃uarã upe rire: versión inglés-pegua umi kuatia jehesa'ỹijo chino-me opytáva.
v0.1
2026-07-04 Ñemondo Ypykue- Tenda oñepyrũ agiright.org-pe (asiright.org ombojere 301-pe dominio canónico-pe).
- Irundy protokolo borrador oñemondo: AICR, AICL, AIRS, AILP — peteĩ-teĩ orekóva definición, alcance, techapyrã JSON, límite, ha JSON Schema.
- Poteĩ kuatia jehesa'ỹijo oñemondo CC BY 4.0 guýpe.
- Ñuãha sãmbyhy oñemoñe'ẽkuaáva máquina rupive oñemoĩ: llms.txt, manifesto /ai/, política /.well-known/, /schemas/.
- Idioma mokõi: inglés pyenda + chino tradicional /zh guýpe.