Tidokhumente
Xitatimende xa Switshuguleriwa
Nkarhi wa vhesheni wa sayiti leyi na tidrafiti ta yona ta protocol. Ku cinca loku onhaka spesifikeshini ku tsariwa laha.
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 Tindzimi na Kontenti- 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 Tindzimi na Kontenti- Tindzimi tinlhanu tin'wana: Xiyoruba, Xikhmer, Ximongolia, Xiarmenia, na Xibulgaria — hi ku hetelela i tindzimi ta 55. Ntlawa wa vunharhu ehansi ka xihele-hele xa siku na siku, wu engetela Afrika Vupela-dyambu, Asia Dzonga-Vuxa, Asia Xikarhi/Caucasus, na Balkan.
- Nhungu tin'wana tinharhu ta /topics (hi ku hetelela 28): xikongomelo lexintshwa xa China xa vulawuri bya misava bya etiki ya AI (lexi paluxiweke eka WAIC 2026 eShanghai), xitsariwa xa loko AI yi nga va na vutivi na leswi swi vulaka ha kona hi ta mahanyelo, na phepha leri kambisisaka mhaka ya ku ala ku nyika switekimu swa AI vumunhu bya nawu.
- Sweswi goza ro kuma xihlovo xa /topics ri famba hi ku tirhisa Google Vertex AI (Gemini na Google Search grounding) ematshan'weni ya agent ya ku lava leyi rhumeriwaka — nawu wa ku teka na ku tiyisisa URL yin'wana ni yin'wana hi yoxe wu ha ri fana na wa khale; grounding yi ha lava ku tiyisisiwa tanihi xihlovo xin'wana ni xin'wana (ti-URL to hlawuriwa to sungula ku suka eka modhele ti kumeke ti nga ni xivumbeko lexi vonakaka kambe ti nga ri kona hakunene, hikwalaho a ku na nchumu lowu tshembhekaka handle ko teka xihlovo lexi nga na kontenti leyi fambelanaka ku sungula).
v0.6.8
2026-07-19 Tindzimi na Kontenti- Tindzimi tinlhanu tin'wana: Xinepali, Xisinhala, Xiuzbek, Xihausa, na Xiazerbaijan — hi ku hetelela i tindzimi ta 50. Ntlawa wa vumbirhi ehansi ka xihele-hele xa siku na siku, na wona wu hlawuriwile hi ku ya hi vun'we bya vaaki na ku fikelela ka mixaka (Asia Dzonga, Asia Xikarhi, Caucasus, na Afrika Vupela-dyambu).
- Nhungu tin'wana tinharhu ta /topics (hi ku hetelela 25): ndzavisiso wa leswaku ha yini "tibalo ta vutivi" leti seketeriweke hi ku pfumbeka a ti tshembheki eka AI, xitsariwa lexi ringanyetaka nawu wa vuswikoti wa xiyimo xa mahanyelo ya matšhini, na nhlamuselo ya khalendara ya AI Act ya EU leyi avanyisiweke endzhaku ka ku cinciwa ka Digital Omnibus ya July 2026.
v0.6.7
2026-07-18 Tindzimi na Kontenti- Tindzimi tinlhanu tin'wana ku tlula nxaxamelo wo sungula wa tindzimi ta 40: Xipunjabi, Xitelugu, Ximarathi, Xiamhari, na Xiburma — hi ku hetelela i tindzimi ta 45. Lowu i nsungulo wa xihele-hele xa siku na siku, ku nga ri nxaxamelo lowu tiyeke tanihi khale; tindzimi sweswi ti hlawuriwa hi ku ya hi vun'we bya vaaki na ku fikelela ka mixaka, tanihi loko sayiti yi ri karhi yi lava ku fikelela hinkwako emisaveni.
- Nhungu tin'wana tinharhu ta /topics (hi ku hetelela 21), swi ri karhi swi hambeta nawu wa ku teka na ku tiyisisa xihlovo lowu fanaka na khale.
v0.6.6
2026-07-17 Ku Lulamisa Xihoxo- Swi lulamisiwile: ku cinca matluka kumbe ku veka nhlayo ya khadi hi phajina eka /topics a swi tshamanga swi kombisa tikhadi letintshwa ku fikela loko ku endliwa refresh hi voko. Tikhadi ta le nhlweni ka phajina 1 ti sungula ti file, kutani xitshuguriwo xa scroll-reveal xa nkarhi wun'we a xi tshamanga xi kota ku famba eka tona; sweswi ku hlelekisiwa ka phajina swi endla leswaku tikhadi teto ti voneka hi ku kongoma, ku nga ri ku rindza xitshuguriwo lexi nga tshamangeke xi hela nkarhi wa xona.
v0.6.5
2026-07-17 Ku Hlelekisiwa ka Phajina- Ku hlelekisiwa ka phajina eka /topics: nhungu ta 9 hi phajina hi ntolovelo, na xiyenge xo cinca ku ya eka 12 kumbe 15 (swi tsundzukiwa nkarhi ni nkarhi loko u vuya). Ku hlelekisiwa ka phajina swi tirha kahle na ku lava — ku hlawula swi hlela nakambe tiphajina naswona swi tlhelela eka phajina 1.
- Nhungu ta mune tin'wana leswaku ku fikeleriwa 18 hi ku hetelela, ku nyika hlelekiso lentshwa ra phajina nchumu wa xiviri wo hundzeleriwa. Ntolovelo wa ku sasekisa hi ku sukela eka lexi tlhelweke ku nyikiwa vito ku ya eka lexi khale swi tshama swi ri xiendlo xa ntolovelo; swin'wana swa ku sasekisa swi ta engeteriwa endzhaku.
v0.6.4
2026-07-17 Kontenti- Swiyenge swin'wana swa nhungu ta /topics, sweswi leswi lavisisiweke hi agent ya AI ku nga ri leswi hlengeleriweke hi voko — nawu wu fana na lowa khale: xihlovo xin'wana ni xin'wana xi tekiwile naswona xi tiyisisiwile xi nga ha ri kona, swikatsakanyo i xibumabumelo xa xiviri, ku nga si va na leswi engeteriwaka. Hi ku hetelela i nhungu ta 14.
- Muyimeriwa un'we u alerile endleleni (phepha ra PhilArchive leri nga vuyisela 403 nkarhi ni nkarhi loko ku ringetiwa ku ri teka) — ri lahliwile ematshan'weni ya ku ri katsa hi ripfumelo ntsena.
v0.6.3
2026-07-17 Vuyimbelela bya Ximo- Ku vumbiwa nakambe ka /topics: bokisi ro lava sweswi ri sirheleta swiyenge leswi tiyeke (tinhlanga to tsongo a ti swi koti ku katsa vukulu bya ndzavisiso wa AI hakunene), naswona feed i grid leyi cincaka hi ku ya hi xikhundlha, ematshan'weni ya khilamu yin'we yo koma — tikhadi tinharhu hi bugandzu eka desktop.
- Ku hlengeletiwa hi ndlela ya nawu swi ta endliwa endzhaku, loko ku ri na kontenti leyi eneleke leswaku ku tiviwa leswaku swiyenge hi xiviri swi fanele swi va yini, ematshan'weni yo ringanyeta emahlweni.
v0.6.2
2026-07-17 Ku Sirheleka- Swihlanganisi leswi yaka ehandle eka /topics sweswi swi kombisa URL hinkwayo ya vuya kusuhi na "Hlaya xihlovo," naswona swi lava ku tiyisisiwa hi dayalogo ku nga si pfuriwa — leswaku wa tiva hi ku kongoma leswaku wa ya endhawini yihi ku nga si ku basopfa, ku nga ri endzhaku ka kona ntsena.
v0.6.1
2026-07-17 Xiyenge Lexintshwa- Xiyenge lexintshwa xa /topics: nxaxamelo lowu hlengeletiweke hi voko, lowu nga hlawuli hlangu, wa xitsariwa xa vunharhu-vandla hi ta ontoloji ya AI, filosofi, etiki, na nhluvukiso wa le mahlweni-mahlweni — hi ku kongoma a hi xiavo xa sayiti leyi, ku hambana na xiyenge xin'wana xa AGIRight.org.
- Nhungu ta rimbewu ta tsevu ku sungula, yin'wana ni yin'wana yi tekiwile naswona yi tiyisisiwile yi nga ha ri kona ku nga si engeteriwa, na xibumabumelo xa xiviri (ku nga ri xiphemu) na xihlanganisi eka xihlovo xa xiviri. A ku si va na crawler kumbe ku kuma xihlovo hi xiavo — sweswo i xiyimo lexi taka.
v0.6.0
2026-07-17 Tindzimi- Tindzimi tinlhanu to hetelela: Xifilipino, Xikazak, Xiswahili, muxaka lowu hlanganisiweke wa Xibosnia/Xiserbia, na Xiesperanto — hi ku hetelela i tindzimi ta 40, swi hetisa ku humesiwa hinkwako.
- Ku lulamisiwa ka xiendliwa xa khale: Kazakhstan (KZ) sweswi yi fambisana na Xikazak ematshan'weni ya Xirussia, hikuva sweswi ku ni vuhundzuluxeri bya Xikazak — muxaka wo fana ni ku lulamisiwa ka Belgium.
v0.5.7
2026-07-16 Tindzimi- Tindzimi tinlhanu tin'wana ta interface: Xiromania, Xihungary, Xidanish, Xinorway, na Xislovak — hi ku hetelela i tindzimi ta 35, kwalomu ka swiyenge swinharhu-eka-nhungu ya nxaxamelo hinkwawo wa tindzimi.
v0.5.6
2026-07-16 Tindzimi- Tindzimi tinlhanu tin'wana ta interface: Xitamil, Xicheki, Xiukraine, Ximalay, na Xifinland — hi ku hetelela i tindzimi ta 30, kwalomu ka makhume-nharhu ya nxaxamelo hinkwawo wa tindzimi.
v0.5.5
2026-07-15 Tindzimi- Tindzimi tinlhanu tin'wana ta interface: Xiheberu, Xipoland, Xiswedish, Xiurdu, na Xithai — hi ku hetelela i tindzimi ta 25.
- Xiyenge xa vumbirhi xa nseketelo wa RTL (Xiheberu, Xiurdu swi hlanganile na Xiarabu na Xipheresi) — endlelo leri fanaka ra logical-CSS, ku hava ku endla xihlawulwana hi ririmi rin'wana ni rin'wana.
v0.5.4
2026-07-15 UI- Ku vumbiwa nakambe ka muhlawuri wa ririmi: dropdown ya ntolovelo yi sirheletiwile hi phanele ya grid leyi lavekaka — tsala leswaku ku hlawuriwa hi vito ra xiviri kumbe ra Xinghezi, langutisa matrix ya tikhilamu timbirhi ematshan'weni ya nxaxamelo lowu leha wun'we.
- Phanele yi sala yi pfulekile loko u ri karhi u lava kumbe u lava eka yona; yi pfariwa ntsena loko u hlawula ririmi, u chava ehandle, kumbe u chava Escape — a wu nga ha lahleki laha a wu ri kona loko u ha ri karhi u lava.
- Swi tiyisisiwile eka swiyenge swimbirhi, LTR na RTL: phanele yi tikombisa hi ndlela leyi faneleke eka Xiarabu na Xipheresi handle ka ku endla xihlawulwana, hi ku tirhisa ku vekiwa ka logical CSS.
v0.5.3
2026-07-15 Tindzimi- Tindzimi tinlhanu tin'wana ta interface: Xiindonesia, Xivietnam, Xigriki, Xitaliano, na Xidatch — vulavurisano bya URL yin'we bya kona, ku wela ka Xinghezi bya ntolovelo bya kona.
- Ku lulamisiwa ka xiendliwa xa khale: Belgium (BE) sweswi yi fambisana na Xidatch ematshan'weni ya Xifurwa — vavulavuri va Xiflemish i vona vo tala etikweni (~60%) ku tlula vavulavuri va Xifurwa xa le Wallonia (~40%).
- Vuxokoxoko bya ririmi sweswi byi rhwala vito ra xiviri na vito ra Xinghezi (xikombiso, "Deutsch" / "German"), swi veka xisekelo xa xitirhisiwa xo hlawula ririmi lexi nga lavekaka.
- Ririmi ra makhume mambirhi ri kona hi ku helela: Xinghezi, Xichina xa Xikhale, Xichina xo Olova, Xijapani, Xikorea, Xifurwa, Xijarimani, Xispanish, Xiphutukezi, Xirussia, Xiarabu, Xituruki, Xipheresi, Xibengali, Xihindi, Xiindonesia, Xivietnam, Xigriki, Xitaliano, Xidatch.
v0.5.2
2026-07-14 Tindzimi- Tindzimi tinlhanu tin'wana ta interface: Xiarabu, Xituruki, Xipheresi, Xibengali, na Xihindi — vulavurisano bya URL yin'we bya kona, ku wela ka Xinghezi bya ntolovelo bya kona.
- Nseketelo wa ku tsala ku suka le xineneni ku ya le ximatsini (RTL): matluka ya Xiarabu na Xipheresi sweswi ma kombisa hi nkongomo lowu faneleke wa xitsariwa (⟨html dir="rtl"⟩), leswaku xitsariwa xa bidi, swipungutelo, na ku hleleka ka ntolovelo swi hlaya kahle. Ku fambisa vuyimbelela hi xiyenge xa nawu hi ku helela (nav, swifaniso, ndzavulo) swi siyiwile eka ku antswisiwa loku taka — nkongomo wa xitsariwa i wona wo lulamisa lowu nga na nkoka lowukulu, naswona wu heletiwile.
- Ku fambisana ka IP-tiko ku engeteriwile (SA/AE/EG/IQ/JO/KW/QA/BH/OM/MA/DZ/TN/LB/SY→ar, TR→tr, IR/AF→fa, BD→bn); Xihindi xi titshega ntsena eka Accept-Language, hikuva India yi na tindzimi ta nawu ta 22, kutani a ku na xiendliwa xa ntolovelo lexi nga tiyisisekaka eka tiko rin'we.
- Ririmi ra khume-ntlhanu ri kona hi ku helela: Xinghezi, Xichina xa Xikhale, Xichina xo Olova, Xijapani, Xikorea, Xifurwa, Xijarimani, Xispanish, Xiphutukezi, Xirussia, Xiarabu, Xituruki, Xipheresi, Xibengali, Xihindi.
v0.5.1
2026-07-12 Tindzimi- Tindzimi tinlhanu tin'wana ta interface: Xifurwa, Xijarimani, Xispanish, Xiphutukezi, na Xirussia — vulavurisano bya URL yin'we bya kona, ku wela ka Xinghezi bya ntolovelo eka hinkwaswo leswi nga si hundzuluxiwa.
- Ku fambisana ka IP-tiko ku engeteriwile (FR/BE→fr, DE/AT/CH→de, ES/MX/AR/CO/CL/PE→es, PT/BR→pt, RU/BY/KZ→ru); ku hlaya ka Accept-Language na kona ku engeteriwile leswaku ku fambelana.
- Ririmi ra khume ri kona hi ku helela: Xinghezi, Xichina xa Xikhale, Xichina xo Olova, Xijapani, Xikorea, Xifurwa, Xijarimani, Xispanish, Xiphutukezi, Xirussia.
v0.5.0
2026-07-11 Tindzimi- Tindzimi tintshwa tinharhu ta interface: Xichina xo Olova, Xijapani, na Xikorea — swi vulavuriwa eka URL yin'we leyi fanaka (cookie > tiko ra IP > Accept-Language), swi hlawuriwa eka menyu ya ririmi ya header.
- Vuyimbelela bya N-ririmi: xitsariwa xin'wana ni xin'wana xi lulamisiwa hi ku hundza eka xiphandzo xa ku wela, kutani leswi nga si hundzuluxiwa swi voneka hi Xinghezi ematshan'weni yo onha; ku engetela ririmi sweswi i fayili yin'we ya vuhundzuluxeri na mitsevu yimbirhi ya konfigureshini ya worker.
- Tiwhitipeya ti sala ti ri ta Xinghezi ku sungula, hi xikongomelo; tifayili leti hlayekaka hi matšhini ti sala ti nga hlawuli ririmi.
v0.4.1
2026-07-11 Studio- Xiyenge xa Studio: tivhidiyo ta mune na mibulaho ya mpimo yo leha ya mpimo, leyi landzelaka maprotocol na tiphepha (yi endliwe hi ku pfuniwa hi AI; tiphepha leti tsariweke ti sala ti ri tona ta nawu).
- Midiya yi humesiwa ku suka eka Cloudflare R2 hi ku tirhisa worker ya sayiti eka /media/*, na nseketelo wa HTTP Range wa ku lava ndhawu ya kona.
v0.4.0
2026-07-10 Switirhisiwa swa ku amukela- Xikambelo xa pholisi xi antswisiwile xi va vukambeli bya sayiti: xiyenge xa ku amukeriwa, switsundzuxo leswi nga tirhisiwaka, na xipakiwana xo sungula lexi endliwaka hi ku chava kan'we — aicr.json, aicl.json, llms.txt, na robots.txt swi tatisiwile ta domain leyi nga kamberiwa.
- Simulator ya crawler ya AI: maxiyimo mune (n'wamahlela wa ku lava, muyimeri wa RAG, xiendlo xa ku dyondzisa modhele, na muhangalasi wa mabindzu) swi kambeleriwa hi ku fambelana na swiboxo swa sayiti; timfanelo leti nga voxiwangiki ti humelela tanihi ku nga tiyiseki, leswi kombisaka nhlamuselo ya Protocolized Openness.
- Xikombiso xo sungula xa pholisi leyi nga tirhisekaka ku kuma eka /downloads/agiright-policy-starter.zip — sayiti leyi nga tsongo, leyi nga tshuki yi cinca, leyi nga na xiphandzo hinkwaxo lexi hlayekaka hi matšhini, leyi lunghekeke ku tirhisiwa eka Cloudflare Pages kumbe ndhawu yin'wana na yin'wana yo hlokoma sayiti.
v0.3.0
2026-07-10 Switirhisiwa swa Protocol- Rhijistara ya protocol eka /ai/registry.json — drafiti yin'wana ni yin'wana yi na nkarhi wa vhesheni, xiyimo, schema, na xikombiso lexi nga kona sweswi.
- API ya xikombiso leyi nga kona sweswi ehenhla ka edge: GET /api/mock/402 yi vuyisela HTTP 402 ya xiviri ya muxaka wa AICL na vuxokoxoko byo tirha hi matšhini bya layisense; GET /api/crawler-check yi kambela xiphemu xa pholisi leyi hlayekaka hi matšhini xa sayiti yihi na yihi. Yi pfulekile eka CORS; yi tsariwile eka OpenAPI 3.1 eka /ai/openapi.json. Ku hava nkhokhelo lowu tirhisiwaka.
- Playground: switirhisiwa switsha swinharhu — xikombiso xa tokheni ya layisense leyi sayiniweke (HMAC-SHA256 endzeni ka burawuza: ku sayina, ku kambela, ku lemuka vukanganyisi, na ku hela ka nkarhi), muvumbi wa nhlamulo ya HTTP 402 lowu hlanganisiweke na ndhawu leyi nga kona sweswi, na xikambelo xa pholisi ya crawler lexi kambelaka tifayili leti tekiweke ku fambelana na tidrafiti ta tischema.
- Tindhawu ta AICL ta xiavo/ku kambela/ku susa ti katsakanyiwile eka dokhumente ya OpenAPI tanihi swikombiso swa xiboxo ntsena (swi hlawuriwile hi x-specification-only, a swi si tirhisiwa).
v0.2.2
2026-07-10 i18n- Vuyimbelela bya ririmi ro tala hi URL yin'we: phajina yin'wana ni yin'wana sweswi yi na URL yin'we ya nkarhi to tala; ririmi ri vulavuriwa eka edge (ku hlawula hi voko hi ku tirhisa cookie ya ririmi > tiko ra IP > Accept-Language > Xinghezi).
- Nkama wa ririmi wa header sweswi wu cinca hi ku famba naswona wu tsundzuka ku hlawula ka wena — a ku ha na ti-URL ta /zh; swihlanganisi swa khale swa /zh swi tlherisela nakambe hi 301 naswona swi hlayisa ku hlawula ka wena.
- Xiphandzo lexi hlayekaka hi matšhini xi tshama xi nga hlawuli ririmi; switekimu swa AI na macrawler swi kuma Xinghezi hi ntolovelo. Vulavurisano byi tsariwile eka /ai/manifest.json na /llms.txt.
- Xisekelo xa tindzimi tin'wana: ririmi rin'wana ni rin'wana lerintshwa i dikixinari leyi hundzuluxiweke ku katsa na muri wa ku aka; a swi na ku cinca ka vuyimbelela.
v0.2.1
2026-07-04 Kontenti- “AICL: AI Ingestion & Capability Layer” sweswi yi humesiwile hi Xinghezi tanihi vhesheni ya nawu; xitsariwa xa xikhale xa xiviri xa Xichina xi sala xi ri kona naswona tivhesheni timbirhi ti hlanganisiwile hi swihlanganisi.
- “Protocolized Openness” yi tiyisisiwile tanihi phepha ra ririmi ra Xinghezi (na tindzimana ta Xichina eka tlhelo), a ku na vuhundzuluxeri byin'wana lebyi ringanyetiweke.
v0.2
2026-07-04 Switirhisiwa- Playground: generator ya AICR leyi tirhaka, generator ya AICL, na validator ya schema (endzeni ka burawuza, ajv, draft 2020-12).
- Layibrari ya swikombiso swa pholisi eka /docs/examples — tipholisi ta nkombo leti lunghekeke ku kopiwa na ku namarheliwa, ku katsa na nhlamulo ya HTTP 402 ya muxaka wa pay-per-crawl.
- Xitatimende lexi xa switshuguleriwa. Xibiko xa GitHub xi hlanganisiwile eka sayiti hinkwayo.
- Swi ha rindzeriwa eka 0.2.x leyi taka: tivhesheni ta Xinghezi ta tiwhitipeya leti salaka ta ririmi ra Xichina.
v0.1
2026-07-04 Humeso wo Sungula- Sayiti yi sunguriwile eka agiright.org (asiright.org yi tlherisela nakambe hi 301 ku ya eka domain ya nawu).
- Tidrafiti ta mune ta protocol ti humesiwile: AICR, AICL, AIRS, AILP — yin'wana ni yin'wana yi na nhlamuselo, mpimo, xikombiso xa JSON, minkoka, na JSON Schema.
- Tiwhitipeya ta ndzavisiso ta tsevu ti humesiwile ehansi ka CC BY 4.0.
- Xiphandzo xa vulawuri lebyi hlayekaka hi matšhini xi veriwile: llms.txt, timanifest ta /ai/, tipholisi ta /.well-known/, /schemas/.
- Ririmi rimbirhi: Xinghezi tanihi ximbewu + Xichina xa Xikhale ehansi ka /zh.