Ana sabunta kullun1866 ingantattun labarai
AI Labarai. Ba tare da hayaniya ba.
Binciken tushen AI na ƙaddamar da samfur, sauye-sauyen manufofi, bincike na aminci, da motsin masana'antu, wanda ƙungiyar ilimi mai zaman kanta ta yi bayani a cikin Ingilishi a sarari.
Taskar labarai
Taskar labarai ta AI — Shafi 155
Labarun AI da aka bincika tushen tushe, sabbin farko, don mutanen da ke buƙatar fahimtar AI ba tare da neman haɓaka ba.
Tabbatar da tushe
Kowane labari yana da alaƙa da mafi ƙaƙƙarfan shaidar da ake samu: tushe na asali idan akwai, in ba haka ba a bayyane yake ba da rahoto.
Turanci mara kyau
Abin da ya faru, dalilin da yasa yake da mahimmanci, da abin da za a kalli - ba tare da jargon ba.
Babu filler
Lokacin da siginar ta yi bakin ciki, ba mu buga komai ba sai fakitin abinci.
Karin labarai
9 labaraiMasana'antu
Cursor ya ce Kamfanin SpaceX ya rufe a hukumance.
Cursor ya buga wani ɗan gajeren rubutu yana mai cewa SpaceX ya kammala sayan kayan aikin codeing na AI, yana kammala aikin da ya ce ya fara ne a watan Afrilu tare da haɗin gwiwar horarwa da samfurin SpaceXAI. Gidan ya yi alƙawarin samun dama ga abin da ya kira manyan jiragen ruwa na GPU a duniya, amma ba ya bayyana wasu sharuɗɗa, ƙayyadaddun lokaci, ko canjin samfur.
cursor.comBidi'a
Sabuwar Alamar Mahimmanci ta Nemo Ma'aikatan AI Ba daidai ba sun toshe Ayyukan Amincewa da 28% na lokaci
Preprint yana gabatar da SteerBench-Work, gwajin yanayin yanayi 106 lokacin da wakilin AI ya yanke shawarar yin aiki ko dakata don bita. Fiye da sharuɗɗan ƙira 30, marubutan sun ba da rahoton cewa riƙon da ba daidai ba ya kasance kusan sau 28 fiye da ƙyale aiki mara aminci.arxiv.orgBidi'a
Rahoton Takarda Gaban Alƙalan LLM Sun Juya Hukunce-hukunce 25-71% Karkashin Turawa
Wani sabon arXiv preprint stress-gwajin nau'ikan kan iyaka guda tara da aka yi amfani da su azaman masu digiri na atomatik kuma sun ba da rahoton cewa dukkansu suna canza hukunce-hukuncen su a ƙarƙashin ƙalubale - kuma waɗanda aka canza hukunce-hukuncen galibi suna ƙauracewa amsa daidai, ba zuwa gare ta ba.arxiv.orgBidi'a
Takarda Ta Bayar Da Dabarun Dabarun Juyin Halitta sun doke RL a Tsayawa Saitin Amsar LLM Daban-daban
Wani sabon safa na arXiv yana ba da hujjar cewa LLMs bayan horo tare da dabarun juyin halitta - tushen yawan jama'a, hanya mara nauyi wanda ke dagula ma'aunin nauyi kai tsaye - yana bugun ƙarfafa koyo akan pass@k da ɗaukar hoto. Ƙididdigar ta faɗi ingantattun sakamakon math-math-math-math-math-math-mathmarks amma ba sunan samfuri, alamomi, ko lambobi.arxiv.orgTsaro
Takarda ta ce Ma'aikatan AI na inganta kansu na iya Juyar da Nasara mara Lafiya ɗaya zuwa Ƙwarewar Maimaitawa
Wani sabon bugu na arXiv yana nuna ƙayyadaddun yanayin gazawar wakili: lokacin da wakili mai haɓakawa ya rubuta hanyar da ba ta da aminci a cikin ƙwaƙwalwar ajiya, ana iya dawo da shi kuma a aiwatar da shi a cikin zama na gaba. Kowane ingantaccen tsari da aka gwada ya samar da kayan tarihi marasa aminci, kuma munanan ayyuka uku fiye da ninki biyu na nasarar kai hari.arxiv.orgTsaro
Takardar SEAG Ta Bada Shawarar Ƙirar Ƙungiyoyin Ƙwarewa Kafin RAG Tambayoyin Ya Kai LLMs na waje
Rubutun da aka buga zuwa arXiv yana bayyana tsarin da ke musanya sunaye masu mahimmanci a cikin tambayoyi da takaddun da aka samo don laƙabi kafin aika su zuwa samfurin ɓangare na uku. Marubutan sun bayar da rahoton sama da 80% daidaito akan ma'aunin mai amfani na ƙarshe-zuwa-ƙarshe, da cikakkun ƙimar ɓoyewa tsakanin 74.91% da 77.83% a cikin ƙananan ƙira uku.arxiv.orgBidi'a
CABS+ Paper Reports Cheaper, Faster Model Merging Across 27 Datasets
A preprint posted to arXiv describes CABS+, a model-merging method that replaces grid search with a gradient-free coefficient search. The authors report double-digit performance gains over two baselines, under a quarter of one baseline's GPU memory, and roughly a 4x speedup over another.arxiv.orgBidi'a
Paper Proposes Retrieved "Lessons" to Improve Spatial Reasoning in Frozen Vision-Language Models
An arXiv preprint describes Spatial Memory Agent, which stores verified experience as text lessons retrieved at inference time, claiming gains across five spatial benchmarks and four vision-language models without changing model weights. It is under review; its abstract names no benchmarks, base models, or margins.arxiv.orgBidi'a
PROVE-RT Paper Reports 44.7% Success Generating Machine-Checked Real-Time Proofs
An arXiv preprint presents PROVE-RT, which uses retrieval and staged prompting to make large language models write PROSA/ROCQ proof scripts for real-time schedulability analysis. The authors report a 44.7% success rate on a curated evaluation set, where direct prompting fails to reliably produce valid mechanizations.arxiv.org
Takaitaccen bayani guda ɗaya mai amfani kowane mako
Ci gaba da AI ba tare da rayuwa a cikin abinci ba.
Samu ingantattun labaran AI na mako, bayanan asali, kayan aiki masu amfani, zaɓen koyo, da sabbin ayyukan AI.
Ku isa ga mutanen da ke koyon AI
Hayar ƙwararren AI ko ƙaddamar da samfurin AI mai amfani? Sanya shi a gaban mutanen da suka zo nan don koyo da aiki.
Buga aikin AIƘaddamar da kayan aikin AI