Dokumentasie
Veranderingslog
Weergawegeskiedenis van hierdie werf en sy protokolkonsepte. Kompatibiliteit-brekende spesifikasieveranderinge word hier aangeteken.
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 Tale en Inhoud- 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 Tale en Inhoud- Nog vyf tale: Yoruba, Khmer, Mongools, Armeens, en Bulgaars — altesaam 55 tale. Derde lot onder die daaglikse ritme, wat Wes-Afrika, Suidoos-Asië, Sentraal-Asië/die Kaukasus, en die Balkan uitbrei.
- Nog drie /topics-inskrywings (altesaam 28): China se nuwe internasionale aksieplan vir etiese KI-bestuur (bekendgestel by WAIC 2026 in Shanghai), 'n opstel oor of KI bewus sou kon wees en wat dit eties sou beteken, en 'n artikel wat die argument teen die toekenning van regspersoonlikheid aan KI-stelsels ondersoek.
- Die bronwerwingstap vir /topics loop nou deur Google Vertex AI (Gemini met Google Search-grondvesting) in plaas van 'n uitgestuurde soekagent — dieselfde dissipline van ophaal-en-onafhanklik-bevestig-elke-URL as voorheen; grondvesting benodig steeds verifikasie soos enige ander bron ('n paar vroeë kandidaat-URL's van die model het aanneemlik gelyk, maar was nie-bestaande, sodat niks vertrou word sonder 'n eerste oplosbare, inhoud-passende ophaal nie).
v0.6.8
2026-07-19 Tale en Inhoud- Nog vyf tale: Nepalees, Sinhala, Oesbeeks, Hausa, en Azerbeidjaans — altesaam 50 tale. Tweede lot onder die daaglikse ritme, weer gekies op grond van bevolking en geografiese bereik (Suid-Asië, Sentraal-Asië, die Kaukasus, en Wes-Afrika).
- Nog drie /topics-inskrywings (altesaam 25): 'n studie oor waarom kompleksiteit-gebaseerde „bewussynstellings” onbetroubaar is vir KI, 'n opstel wat 'n bevoegdheid-gebaseerde standaard vir masjien se morele status voorstel, en 'n verduideliking van die EU KI-wet se verdeelde nakomingstydlyn na die Digitale Omnibus-wysiging van Julie 2026.
v0.6.7
2026-07-18 Tale en Inhoud- Nog vyf tale bo en behalwe die oorspronklike lys van 40 tale: Punjabi, Telugu, Marathi, Amharies, en Birmaans — altesaam 45 tale. Dit is die begin van 'n voortgesette daaglikse ritme, nie 'n vaste lys hierdie keer nie; tale word nou gekies op grond van bevolking en geografiese bereik, namate die werf na volledige wêreldwye dekking werk.
- Nog drie /topics-inskrywings (altesaam 21), wat dieselfde ophaal-en-bevestig-bronwerwingsdissipline as voorheen voortsit.
v0.6.6
2026-07-17 Foutregstelling- Reggestel: die wissel van bladsye of die item-per-bladsy-instelling op /topics het nie altyd die nuwe kaarte gewys totdat 'n mens self verfris het nie. Kaarte anderkant bladsy 1 begin versteek, sodat die werf se eenmalige rol-onthullingsanimasie nooit die kans gehad het om daarop te loop nie; blaai forseer nou daardie kaarte direk sigbaar in plaas daarvan om te wag op 'n animasie wat sy oomblik reeds gemis het.
v0.6.5
2026-07-17 Bladsy-indeling- Bladsy-indeling op /topics: verstek 9 inskrywings per bladsy, met 'n instelling om na 12 of 15 te wissel (word oor besoeke heen onthou). Blaai werk korrek saam met soek — filtrering herbereken bladsye en spring terug na bladsy 1.
- Nog vier inskrywings om by 'n totaal van 18 uit te kom, wat die nuwe bladsy-indeling iets werkliks gee om deur te blaai. Nuutste-eerste volgens publikasiedatum bly die verstek-sortering; ander sorteeropsies is 'n latere byvoeging.
v0.6.4
2026-07-17 Inhoud- Nog agt /topics-inskrywings, hierdie keer nagevors deur 'n KI-agent eerder as met die hand gekureer — dieselfde reël as voorheen: elke bron word opgehaal en lewend bevestig, opsommings is 'n oorspronklike parafrase, voordat enigiets bygevoeg word. 14 inskrywings in totaal.
- Een verworpe kandidaat op pad ('n PhilArchive-artikel wat by elke ophaalpoging 'n 403 teruggegee het) — laat vaar eerder as om op vertroue ingesluit te word.
v0.6.3
2026-07-17 Uitleg- /topics herontwerp: 'n soekkassie vervang vir eers vaste kategorieë ('n handjievol etikette kon nie dek hoeveel KI-navorsing werklik strek nie), en die voer is 'n responsiewe rooster in plaas van een smal kolom — drie kaarte breed op 'n rekenaarskerm.
- Formele kategorisering word uitgestel totdat daar genoeg werklike inhoud is om te weet wat die kategorieë eintlik behoort te wees, eerder as om vooraf te raai.
v0.6.2
2026-07-17 Veiligheid- Uitgaande skakels op /topics wys nou die volledige bestemmings-URL langs „Lees die bron”, en bevestig met 'n dialoogvenster voordat dit oopgemaak word — sodat u presies weet watter werf u op die punt staan om te besoek voordat u klik, nie eers daarna nie.
v0.6.1
2026-07-17 Nuwe afdeling- Nuwe /topics-afdeling: 'n met die hand gekureerde, neutrale indeks van derdeparty-geskrifte oor KI-ontologie, filosofie, etiek, en voorpunt-vooruitgang — uitdruklik nie hierdie werf se eie standpunt nie, anders as die res van AGIRight.org.
- Ses beginskrywings om mee te begin, elkeen opgehaal en lewend bevestig voordat dit bygevoeg is, met 'n oorspronklike parafrase (nie 'n uittreksel nie) en 'n skakel na die werklike bron. Nog geen crawler of outomatiese bronwerwing nie — dit is 'n latere fase.
v0.6.0
2026-07-17 Tale- Die laaste vyf tale: Filippyns, Kasak, Swahili, 'n gekombineerde Bosnies/Serwiese variant, en Esperanto — altesaam 40 tale, wat die volledige uitrol voltooi.
- 'n Vroeëre verstekwaarde reggestel: Kasakstan (KZ) skakel nou na Kasak in plaas van Russies, noudat 'n Kasak-vertaling bestaan — dieselfde soort regstelling as die vroeëre België-korreksie.
v0.5.7
2026-07-16 Tale- Nog vyf koppelvlaktale: Roemeens, Hongaars, Deens, Noorweegs, en Slowaaks — altesaam 35 tale, sewe-agtstes van die pad deur die volledige taallys.
v0.5.6
2026-07-16 Tale- Nog vyf koppelvlaktale: Tamil, Tsjeggies, Oekraïens, Maleis, en Fins — altesaam 30 tale, drie-kwart van die pad deur die volledige taallys.
v0.5.5
2026-07-15 Tale- Nog vyf koppelvlaktale: Hebreeus, Pools, Sweeds, Oerdoe, en Thai — altesaam 25 tale.
- Tweede rondte van RTL-ondersteuning (Hebreeus en Oerdoe sluit by Arabies en Persies aan) — dieselfde logiese-CSS-benadering, geen taal-spesifieke spesiale gevalle nodig nie.
v0.5.4
2026-07-15 Gebruikerskoppelvlak- Die taalkieser herontwerp: die inheemse afrolkieser is vervang met 'n deursoekbare rooster-paneel — tik om volgens inheemse of Engelse naam te filter, blaai deur 'n twee-kolom-matriks in plaas van een lang lys.
- Die paneel bly oop terwyl u daarin soek of rol; dit sluit slegs wanneer u 'n taal kies, buite kliek, of Escape druk — u verloor nie meer u plek midde-in 'n soektog nie.
- Bevestig in beide LTR- en RTL-kontekste: die paneel spieël korrek vir Arabies en Persies sonder enige spesiale gevalle, deur logiese CSS-posisionering te gebruik.
v0.5.3
2026-07-15 Tale- Nog vyf koppelvlaktale: Indonesies, Viëtnamees, Grieks, Italiaans, en Nederlands — dieselfde eenvormige-URL-onderhandeling, dieselfde grasieuse Engelse terugvalopsie.
- 'n Vroeëre verstekwaarde reggestel: België (BE) skakel nou na Nederlands in plaas van Frans — Vlaamssprekendes is die land se meerderheid (~60%) teenoor Waalse Franssprekendes (~40%).
- Taal-metadata dra nou beide 'n inheemse naam en 'n Engelse naam (bv. „Deutsch” / „German”), wat die grondwerk lê vir 'n deursoekbare taalkieser.
- In totaal is twintig tale regstreeks beskikbaar: Engels, Tradisionele Chinees, Vereenvoudigde Chinees, Japannees, Koreaans, Frans, Duits, Spaans, Portugees, Russies, Arabies, Turks, Persies, Bengaals, Hindi, Indonesies, Viëtnamees, Grieks, Italiaans, Nederlands.
v0.5.2
2026-07-14 Tale- Nog vyf koppelvlaktale: Arabies, Turks, Persies, Bengaals, en Hindi — dieselfde eenvormige-URL-onderhandeling, dieselfde grasieuse Engelse terugvalopsie.
- Ondersteuning vir regs-na-links (RTL): Arabiese en Persiese bladsye word nou met die korrekte teksrigting weergegee (⟨html dir="rtl"⟩), sodat tweerigting-teks, punktuasie, en verstek-belyning korrek lees. Volledige spieëling van uitleg deur logiese eienskappe (navigasie, ikone, spasiëring) word vir 'n latere verfyningsrondte gelaat — teksrigting is die regstelling wat die meeste saak maak, en dit is voltooi.
- IP-land-koppeling uitgebrei (SA/AE/EG/IQ/JO/KW/QA/BH/OM/MA/DZ/TN/LB/SY→ar, TR→tr, IR/AF→fa, BD→bn); Hindi steun slegs op Accept-Language, aangesien Indië 22 amptelike tale het en geen enkele land-vlak-verstek akkuraat is nie.
- In totaal is vyftien tale regstreeks beskikbaar: Engels, Tradisionele Chinees, Vereenvoudigde Chinees, Japannees, Koreaans, Frans, Duits, Spaans, Portugees, Russies, Arabies, Turks, Persies, Bengaals, Hindi.
v0.5.1
2026-07-12 Tale- Nog vyf koppelvlaktale: Frans, Duits, Spaans, Portugees, en Russies — dieselfde eenvormige-URL-onderhandeling, dieselfde grasieuse Engelse terugvalopsie vir enigiets wat nog nie vertaal is nie.
- IP-land-koppeling uitgebrei (FR/BE→fr, DE/AT/CH→de, ES/MX/AR/CO/CL/PE→es, PT/BR→pt, RU/BY/KZ→ru); Accept-Language-ontleding ooreenstemmend uitgebrei.
- In totaal is tien tale regstreeks beskikbaar: Engels, Tradisionele Chinees, Vereenvoudigde Chinees, Japannees, Koreaans, Frans, Duits, Spaans, Portugees, Russies.
v0.5.0
2026-07-11 Tale- Drie nuwe koppelvlaktale: Vereenvoudigde Chinees, Japannees, en Koreaans — onderhandel by dieselfde enkele URL (koekie > IP-land > Accept-Language), kiesbaar vanuit die taalkieslys in die kop.
- N-taal-argitektuur: elke string word deur 'n terugvallaag opgelos, sodat enigiets wat nog nie vertaal is nie in Engels vertoon word in plaas daarvan om te breek; die byvoeging van 'n taal is nou een vertaallêer plus twee reëls worker-konfigurasie.
- Witskrifte bly doelbewus eerste in Engels; masjienleesbare lêers bly taal-neutraal.
v0.4.1
2026-07-11 Studio- Studio-afdeling: vier video's en twee uitgebreide oudiogesprekke wat die protokolle en artikels vergesel (KI-ondersteunde produksie; die geskrewe artikels bly gesaghebbend).
- Media word vanaf Cloudflare R2 bedien deur die werf se worker by /media/*, met HTTP Range-ondersteuning vir soek.
v0.4.0
2026-07-10 Aannemingsgereedskap- Beleidstoetser opgegradeer tot 'n werf-oudit: aannemingstelling, uitvoerbare aanbevelings, en 'n eenklap-beginkomplet — aicr.json, aicl.json, llms.txt, en robots.txt vooraf ingevul vir die ondersoekte domein.
- KI-crawler-simulator: vier persona's (soekenjin-indekseerder, RAG-assistent, model-afrigtingspyplyn, kommersiële herverspreider) word teen 'n werf se verklarings geëvalueer; onverklaarde regte kom na vore as onsekerheid, wat die tesis van Geprotokolliseerde Openheid illustreer.
- Ontplooibare beleid-beginjabloon by /downloads/agiright-policy-starter.zip — 'n minimale statiese werf met die volledige masjienleesbare laag, gereed vir Cloudflare Pages of enige statiese gasheer.
v0.3.0
2026-07-10 Protokolgereedskap- Protokolregister by /ai/registry.json — elke konsep met weergawegeskiedenis, status, skema, en lewende instansie.
- Lewende demonstrasie-API by die rand: GET /api/mock/402 gee 'n werklike HTTP 402 in AICL-styl terug met masjien-uitvoerbare lisensiëringsinligting; GET /api/crawler-check ondersoek enige werf se masjienleesbare beleidsoppervlak. CORS-oop; gedokumenteer in OpenAPI 3.1 by /ai/openapi.json. Geen betalings word verwerk nie.
- Playground: drie nuwe gereedskapstukke — demonstrasie van ondertekende lisensietokens (HMAC-SHA256 binne die blaaier: teken, verifieer, opsporing van omknoeiing, verstryking), 'n HTTP 402-responsbouer gekoppel aan die lewende eindpunt, en 'n crawler-beleidstoetser wat opgehaalde lêers teen die konsepskemas bevestig.
- AICL kwotasie/verifieer/herroep-eindpunte ingesluit in die OpenAPI-dokument as slegs-spesifikasie-illustrasies (gemerk x-specification-only, nie geïmplementeer nie).
v0.2.2
2026-07-10 i18n- Eenvormige-URL meertalige argitektuur: elke bladsy het nou een openbare URL; die taal word by die rand onderhandel (handmatige keuse via lang-koekie > IP-land > Accept-Language > Engels).
- Die taalknoppie in die kop wissel nou ter plaatse en onthou u keuse — geen /zh-URL's meer nie; verouderde /zh-skakels stuur met 301 om en behou die voorkeur.
- Die masjienleesbare laag bly taal-neutraal; KI-stelsels en crawlers ontvang Engels by verstek. Onderhandeling word gedokumenteer in /ai/manifest.json en /llms.txt.
- Grondwerk vir bykomende tale: elke nuwe taal is 'n vertaalde woordeboek plus 'n bou-boom — geen argitektuurverandering nie.
v0.2.1
2026-07-04 Inhoud- „AICL: AI Ingestion & Capability Layer” is nou in Engels gepubliseer as die kanonieke uitgawe; die oorspronklike Chinese manuskrip bly beskikbaar, en albei weergawes skakel na mekaar.
- „Protocolized Openness” is bevestig as 'n Engelstalige artikel (met parallelle Chinese gedeeltes) — geen aparte vertaling word beplan nie.
v0.2
2026-07-04 Gereedskap- Playground: werkende AICR-generator, AICL-generator, en skemavalideerder (binne die blaaier, ajv, konsep 2020-12).
- Biblioteek van beleidsvoorbeelde by /docs/examples — sewe beleide gereed om te kopieer en te plak, insluitend 'n HTTP 402-respons in betaal-per-crawl-styl.
- Hierdie veranderingslog. GitHub-bewaarplek werfwyd gekoppel.
- Hangende vir 'n latere 0.2.x: Engelse weergawes van die oorblywende Chinese-taal witskrifte.
v0.1
2026-07-04 Aanvanklike vrystelling- Werf bekendgestel by agiright.org (asiright.org stuur met 301 om na die kanonieke domein).
- Vier protokolkonsepte gepubliseer: AICR, AICL, AIRS, AILP — elkeen met definisie, omvang, JSON-voorbeeld, beperkings, en JSON-skema.
- Ses navorsingswitskrifte gepubliseer onder CC BY 4.0.
- Laag van masjienleesbare bestuur ontplooi: llms.txt, /ai/-manifeste, /.well-known/-beleide, /schemas/.
- Tweetalig: Engelse wortelpad + Tradisionele Chinees onder /zh.