Mikanda
Lisi ya Mbongwana
Lisolo ya ba-version ya site oyo na mikanda na yango ya ebandeli ya protokolo. Mbongwana ya monene ya spesifikasyo ekomami awa.
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 Minoko mpe Contenu- 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 Minoko mpe Contenu- Minoko mitano mosusu: Yoruba, Khmer, Mongol, Arménien, na Bulgare — minoko nyonso 55. Etuluku ya misato na se ya momesano ya mokolo na mokolo, ekómisi Afrika ya Wɛst, Asie ya Sud-Est, Asie ya Kati/Caucase, na Balkans.
- Makomi misato mosusu ya /topics (nyonso 28): mokano ya sika ya Chine ya bokambami ya etika ya AI ya mokili mobimba (oyo elakisamaki na WAIC 2026 na Shanghai), lisolo na tina ya soki AI ekoki kozala na bososoli mpe nini yango elingaki koloba na etika, mpe mokanda oyo etali likanisi ya kotelemela kopesa bomoto na miso ya mibeko na bibongiseli ya AI.
- Litambwisi ya liziba ya /topics sikoyo elekaka na Google Vertex AI (Gemini elongo na Google Search grounding) na esika ya ajan ya boluki oyo etindamaka — momesano kaka moko ya kozwa mpe kondima na bonsomi URL moko na moko lokola liboso; grounding esengeli kaka lisusu kotalama lokola liziba nyonso mosusu (ba-URL mwa moko ya ebandeli oyo modèle epesaki emonanaki malamu kasi ezalaki na solo te, boye eloko moko te endimami kozanga kozwa yango na solo, na contenu oyo ekokani, liboso).
v0.6.8
2026-07-19 Minoko mpe Contenu- Minoko mitano mosusu: Népalais, Cingalais, Ouzbek, Haoussa, na Azerbaïdjanais — minoko nyonso 50. Etuluku ya mibale na se ya momesano ya mokolo na mokolo, eponami lisusu mpo na motángo ya bato mpe bonene ya mabele (Asie ya Sud, Asie ya Kati, Caucase, na Afrika ya Wɛst).
- Makomi misato mosusu ya /topics (nyonso 25): bolukiluki na tina ya nini "point ya bososoli" oyo etyami na bosangani ezali te na botyeli motema mpo na AI, lisolo oyo epesi likanisi ya norme oyo etyami na bokoki mpo na bomoni ya etika ya masini, mpe elimboli ya calendrier ya botosi ya AI Act ya EU oyo ekabwani nsima ya mbongwana ya Digital Omnibus ya juillet 2026.
v0.6.7
2026-07-18 Minoko mpe Contenu- Minoko mitano mosusu koleka molɔngɔ ya ebandeli ya minoko 40: Pendjabi, Télougou, Marathi, Amharique, na Birman — minoko nyonso 45. Oyo ezali ebandeli ya momesano ya mokolo na mokolo, ezali te molɔngɔ oyo ekangami lokola liboso; minoko sikoyo eponami mpo na motángo ya bato mpe bonene ya mabele, ntango site ezali koluka kozwa bato ya mokili mobimba.
- Makomi misato mosusu ya /topics (nyonso 21), kokoba na momesano kaka moko ya kozwa mpe kondima liziba lokola liboso.
v0.6.6
2026-07-17 Kobongisa libunga- Ebongisami: kobongola bankasa to bandelo ya eteni na eteni na /topics ezalaki komonisa te ba-carte ya sika tii na kozongisa na maboko. Ba-carte oyo eleki nkasa 1 ebandaka ebombami, yango wana animation ya site ya mbala moko ya kolakisa na ko-scroll ezwaka nzela te ya kosalema likolo na yango; sikoyo kokabola bankasa etindisi ba-carte wana komonana mbala moko, na esika ya kozela animation oyo elekisaki tango na yango.
v0.6.5
2026-07-17 Kokabola na Bankasa- Kokabola na bankasa na /topics: makomi 9 na lokasa moko na momesano, elongo na maponami ya kobongola na 12 to 15 (ekundolamaka na mbala na mbala oyo okoya). Kokabola esalaka malamu elongo na boluki — kolongola makambo ebongolaka bankasa mpe ezongisaka na lokasa 1.
- Makomi minei mosusu mpo na kokoma nyonso 18, mpo na kopesa pagination ya sika eloko ya solo ya kokabola. Molɔngɔ ya sika-liboso na kolanda mokolo ya kobima etikalaka momesano; ba-lolenge mosusu ya kolɔngɔnya ekoya na nsima.
v0.6.4
2026-07-17 Contenu- Makomi mosusu mwambe ya /topics, mbala oyo elukamaki na ajan ya AI na esika ya kopona na maboko — mobeko kaka moko lokola liboso: liziba nyonso ezwami mpe endimami ete ezali sikoyo, ba-rezime ezali maloba na biso moko, liboso ya kobakisa eloko. Makomi nyonso 14.
- Mokandidat moko oyo eboyamaki na nzela — mokanda ya PhilArchive oyo ezongisaki 403 na komeka nyonso ya kozwa yango — elongolamaki na esika ya kokɔtisa yango na kondima kaka.
v0.6.3
2026-07-17 Bosali- Etongami lisusu /topics: boîte ya boluki ezali sikoyo na esika ya ba-catégorie oyo ekangamaki liboso (mwa ba-tag ekokaki te kozipa ndenge bolukiluki ya AI ezali monene mpenza), mpe feed ezali sikoyo grille oyo ebongolaka na esika ya colonne moko ya moke — ba-carte misato na mokuse na ordinatele.
- Bokaboli ya makambo na ba-molɔngɔ etyami sima tii ntango contenu ya solo ekozala mingi mpo na koyeba ba-molɔngɔ ya solo, na esika ya kokanisa liboso.
v0.6.2
2026-07-17 Bokengeli- Ba-lien oyo ekei libanda na /topics sikoyo elakisaka URL mobimba ya esika ekokende, pembeni ya "Tángá liziba," mpe esengaka kondima na dialogue liboso ya kofungola yango — mpo oyeba malamu site nini okei kotala liboso ya kofinela, ezali te kaka na nsima.
v0.6.1
2026-07-17 Eteni ya Sika- Eteni ya sika /topics: molɔngɔ ya bosembo, eponami na maboko, ya makomi ya bato mosusu na tina ya ontologie ya AI, filozofi, etika, mpe bokoli ya suka — ezali polele te likanisi ya site oyo yango moko, ekeseni na eteni mosusu ya AGIRight.org.
- Makomi motoba ya ebandeli mpo na kobanda, moko na moko ezwami mpe endimami ete ezali sikoyo liboso ya kobakisama, na maloba na biso moko (ezali te eteni oyo elongolami) mpe lien na liziba ya solo. Crawler to boluki oyo esalemaka na yango moko ezali nanu te — yango ekoya na eteni ya nsima.
v0.6.0
2026-07-17 Minoko- Minoko mitano ya suka: Filipino, Kazakh, Swahili, lolenge oyo esangisi Bosniaque/Serbe, na Espéranto — minoko nyonso 40, esilisi kobima mobimba.
- Ebongisami libunga ya kala: Kazakhstan (KZ) sikoyo ekei na Kazakh na esika ya Russe, sikoyo ete traduction ya Kazakh ezali — ndenge kaka moko ya libongisi ya kala ya Belgique.
v0.5.7
2026-07-16 Minoko- Minoko mitano mosusu ya interface: Roumain, Hongrois, Danois, Norvégien, na Slovaque — minoko nyonso 35, ndambo nsambo na mwambe ya molɔngɔ mobimba ya minoko.
v0.5.6
2026-07-16 Minoko- Minoko mitano mosusu ya interface: Tamoul, Tchèque, Ukrainien, Malais, na Finnois — minoko nyonso 30, ndambo misato na minei ya molɔngɔ mobimba ya minoko.
v0.5.5
2026-07-15 Minoko- Minoko mitano mosusu ya interface: Hébreu, Polonais, Suédois, Ourdou, na Thaï — minoko nyonso 25.
- Etuluku ya mibale ya bosungi ya RTL (Hébreu, Ourdou ekangani na Arabe na Persan) — momesano kaka moko ya CSS logique, esengeli te kosala eloko na ndenge ekeseni mpo na monoko na monoko.
v0.5.4
2026-07-15 UI- Etongami lisusu esaleli ya kopona monoko: liste ya kala ebongolami na panel ya grille oyo bakoki koluka — koma mpo na kopona na nkombo ya ebandeli to na Lingelesi, tambolá na matrice ya colonne mibale na esika ya liste molai moko.
- Panel etikalaka polele ntango ozali koluka to ko-scroller kati na yango; ekangamaka kaka ntango oponi monoko, ofinelaka libanda, to onyati Escape — okobungisa lisusu esika na yo te na katikati ya boluki.
- Etalelami na contexte LTR na RTL nyonso mibale: panel emonanaka malamu na kotalana mpo na Arabe na Persan kozanga kosala eloko ekeseni, na kosalela esika ya CSS logique.
v0.5.3
2026-07-15 Minoko- Minoko mitano mosusu ya interface: Indonésien, Vietnamien, Grec, Italien, na Néerlandais — momesano kaka moko ya URL moko, kozonga kaka moko na Lingelesi.
- Ebongisami libunga ya kala: Belgique (BE) sikoyo ekei na Néerlandais na esika ya Français — baye balobaka Flamand bazali bato mingi ya mboka (~60%) koleka baye balobaka Français ya Wallonie (~40%).
- Métadonnée ya monoko sikoyo ememi nkombo ya ebandeli mpe nkombo na Lingelesi (ndakisa "Deutsch" / "German"), etyi ebandeli mpo na esaleli ya kolukaka minoko.
- Minoko ntuku mibale ezali sikoyo: Lingelesi, Chinois ya kala, Chinois ya pete, Japonais, Coréen, Français, Allemand, Espagnol, Portugais, Russe, Arabe, Turc, Persan, Bengali, Hindi, Indonésien, Vietnamien, Grec, Italien, Néerlandais.
v0.5.2
2026-07-14 Minoko- Minoko mitano mosusu ya interface: Arabe, Turc, Persan, Bengali, na Hindi — momesano kaka moko ya URL moko, kozonga kaka moko na Lingelesi soki eza nanu na traduction te.
- Bosungi ya nzela-kobanda-na-mobali (RTL): bankasa ya Arabe na Persan sikoyo emonanaka na nzela ya makomi oyo ebongi (⟨html dir="rtl"⟩), boye makomi ya bidi, ba-ponctuation, mpe kotalana ya momesano etángamaka malamu. Kolakisama mobimba ya bosali na proprieté logique (nav, ba-icône, esika) etikali mpo na kobongisa ya nsima — nzela ya makomi ezali libongisi ya ntina mingi mpe esili.
- Bokangisi ya mboka-na-IP ekomisami monene (SA/AE/EG/IQ/JO/KW/QA/BH/OM/MA/DZ/TN/LB/SY→ar, TR→tr, IR/AF→fa, BD→bn); Hindi etyelaka motema kaka na Accept-Language, mpo India ezali na minoko 22 ya official mpe mboka moko te ekoki kolakisa yango na bosikisiki.
- Minoko zomi na mitano ezali sikoyo: Lingelesi, Chinois ya kala, Chinois ya pete, Japonais, Coréen, Français, Allemand, Espagnol, Portugais, Russe, Arabe, Turc, Persan, Bengali, Hindi.
v0.5.1
2026-07-12 Minoko- Minoko mitano mosusu ya interface: Français, Allemand, Espagnol, Portugais, na Russe — momesano kaka moko ya URL moko, kozonga kaka moko na Lingelesi mpo na nyonso oyo eza nanu na traduction te.
- Bokangisi ya mboka-na-IP ekomisami monene (FR/BE→fr, DE/AT/CH→de, ES/MX/AR/CO/CL/PE→es, PT/BR→pt, RU/BY/KZ→ru); kotangwama ya Accept-Language ekomisami monene mpo na koyokana.
- Minoko zomi ezali sikoyo: Lingelesi, Chinois ya kala, Chinois ya pete, Japonais, Coréen, Français, Allemand, Espagnol, Portugais, Russe.
v0.5.0
2026-07-11 Minoko- Minoko misato ya sika ya interface: Chinois ya pete, Japonais, na Coréen — eyokanaki na URL kaka moko (cookie > mboka ya IP > Accept-Language), oyo bakoki kopona na menu ya monoko na tête ya lokasa.
- Architecture ya minoko N: liloba moko na moko elekaka na niveau ya kozonga, boye eloko oyo eza nanu na traduction te emonanaka na Lingelesi na esika ya kobuka; kobakisa monoko sikoyo ezali kaka fichier moko ya traduction elongo na milɔngɔ mibale ya config ya worker.
- Mikanda ya bolukiluki etikalaka na Lingelesi liboso na mokano; ba-fichier oyo masini ekoki kotánga etikalaka na bopimeli ya monoko.
v0.4.1
2026-07-11 Studio- Eteni ya Studio: bavideo minei mpe masolo mibale ya molai na maloba, oyo elandi ba-protokolo na mikanda (bosali oyo AI esungaki; mikanda oyo ekomami etikalaka na ntina mingi).
- Media eutaka na Cloudflare R2 na nzela ya worker ya site na /media/*, elongo na HTTP Range mpo na koluka esika.
v0.4.0
2026-07-10 Bisaleli ya kondima kosalela- Testeur ya politiki ekomisami audit ya site: point ya kondima kosalela, batoli oyo ekoki kosalema, mpe kit ya ebandeli na clic moko — aicr.json, aicl.json, llms.txt, na robots.txt oyo etondisami liboso mpo na domaine oyo etalelami.
- Simulateur ya crawler ya AI: ba-persona minei (indexeur ya boluki, assistant ya RAG, chaîne ya formasyo ya modèle, mpe mopanzi ya mombongo) etalelami na kotalana na ba-esakoli ya site; makoki oyo esakolami te emonanaka lokola ntembe, mpe emonisi likanisi ya "Bopolele oyo ezali na Protokolo".
- Modèle ya ebandeli ya politiki oyo bakoki kotia, na /downloads/agiright-policy-starter.zip — site static ya moke oyo ezali na niveau mobimba oyo masini ekoki kotánga, oyo ebongi mpo na Cloudflare Pages to host static nyonso.
v0.3.0
2026-07-10 Bisaleli ya Protokolo- Registre ya protokolo na /ai/registry.json — mokanda ya ebandeli moko na moko elongo na lisolo ya ba-version, status, schema, mpe esika oyo esalaka sikoyo.
- API ya démo oyo esalaka sikoyo na edge: GET /api/mock/402 ezongisaka HTTP 402 ya solo na lolenge ya AICL, na sango ya lisansi oyo masini ekoki kosalela; GET /api/crawler-check etalaka politiki oyo masini ekoki kotánga ya site nyonso. CORS efungwami; ekomami na OpenAPI 3.1 na /ai/openapi.json. Lifuta moko te esalemaka.
- Playground: bisaleli misato ya sika — démo ya jeton ya lisansi oyo esignami (HMAC-SHA256 na navigateur: signer, kotala solo, komona bobebisi, ntango ya kosuka), motongi ya eyano ya HTTP 402 oyo ekangani na esika ya sikoyo, mpe testeur ya politiki ya crawler oyo etalaka ba-fichier oyo ezwami na kotalana na ba-schema ya ebandeli.
- Ba-esika ya kosenga ntalo/kotala solo/kolongola ya AICL ekɔtisami na mokanda ya OpenAPI lokola bandakisa ya spesifikasyo kaka (elakisami na x-specification-only, esalemi nanu te).
v0.2.2
2026-07-10 i18n- Architecture ya minoko ebele na URL moko: lokasa moko na moko ezali sikoyo na URL moko ya bato nyonso; monoko eyokanaka na edge (kopona na maboko na nzela ya cookie ya monoko > mboka ya IP > Accept-Language > Lingelesi).
- Bouton ya monoko na tête ya lokasa sikoyo ebongolaka na esika moko mpe ekundolaka maponi na yo — /zh URL ezali lisusu te; ba-lien ya kala ya /zh ezongisaka na 301 mpe ebateli maponi na yo.
- Niveau oyo masini ekoki kotánga etikalaka na bopimeli ya monoko; bibongiseli ya AI mpe ba-crawler bazwaka Lingelesi na esika ya momesano. Boyokani ekomami na /ai/manifest.json mpe /llms.txt.
- Ebandeli mpo na minoko misusu: monoko ya sika moko na moko ezali dictionnaire oyo ebongolami elongo na arbre ya construction — architecture ebongwani te.
v0.2.1
2026-07-04 Contenu- "AICL: AI Ingestion & Capability Layer" ebimisami sikoyo na Lingelesi lokola édition ya solo; mokanda ya ebandeli na Chinois etikali ezwama, mpe ba-version nyonso mibale ekangani na kati na kati.
- "Protocolized Openness" endimami lokola mokanda na monoko ya Lingelesi (na biteni ya Chinois na mokuse elongo) — traduction ekeseni ezali te na mokano.
v0.2
2026-07-04 Bisaleli- Playground: generateur ya AICR, generateur ya AICL, mpe validateur ya schema oyo esalaka (na navigateur, ajv, draft 2020-12).
- Bibliothèque ya bandakisa ya politiki na /docs/examples — ba-politiki nsambo oyo ebongi na kokopi-kotia, na kati na yango eyano ya HTTP 402 na lolenge ya kofuta-na-crawl.
- Changelog oyo. Repository ya GitHub ekangani na site mobimba.
- Ezali kozela mpo na 0.2.x ya nsima: ba-version na Lingelesi ya mikanda ya bolukiluki oyo etikali na Chinois.
v0.1
2026-07-04 Kobima ya Liboso- Site ebimaki na agiright.org (asiright.org ezongisaka na 301 tii na domaine ya solo).
- Mikanda minei ya ebandeli ya protokolo ebimisami: AICR, AICL, AIRS, AILP — moko na moko ezali na ndimbola, etando, ndakisa ya JSON, bandelo, mpe schema ya JSON.
- Mikanda motoba ya bolukiluki ebimisami na se ya CC BY 4.0.
- Niveau ya bokambami oyo masini ekoki kotánga etyami: llms.txt, ba-manifest ya /ai/, ba-politiki ya /.well-known/, /schemas/.
- Minoko mibale: Lingelesi lokola ebandeli + Chinois ya kala na se ya /zh.