15509 articles tagged with LLM
125 токенов в секунду на RTX 4070 Ti SUPER: как я заставил локальную LLM работать полноценным кодинг-агентомПо статистике, среди рядовых пользователей настольных компов самая распр...
Baidu has open-sourced Unlimited OCR 2, a 3B vision-language model that parses hundred-page documents in a single request. Its SR-SWA sparse attention keeps decoding cost almost fl...
AI can already produce SQL that runs – but runnable isn’t the same as auditable. On complex queries,...
@malteengeler i really hate this entire #llm #ai shit how on earth can technicians with a high reputation join this bandwagon? It is in no means sustainable ecologically, environme...
An agent loop is just a for loop. The hard part is the invariants inside it — and the deterministic guardrails that catch every predictable failure mode.
What is ENIGMA In March 2026 I started building a deterministic causal simulation engine —...
LLM: TuJu was never meant to replace Waze #apps #digitallife #hasnimohammad #lembagalebuhrayamalaysia #llm #malaysiangovernment #malaysianhighwayauthority #news #prosignalconsortiu...
Робот с LLM, который меня подстрелил. Часть 3Как собрать робота, которым управляет языковая модель. Семнадцать разделов, две сотни часов работы. Это третья статья цикла, целиком те...
This is a submission for the Hacktoberfest Open-Source AI Challenge: Week 4 — Ghost in the...
LLM-беседы: эпистемный класс элементов и форм в исследованиях пространств активацийВ рамках теории LLM-бесед как лумановских операционных систем нового типа рассматриваются экспери...
What's the general consensus on those AI/LLM engagement bot here, especially those that don't label themselves as bots?I often hash tag for filters, but it seems to attract too muc...
Emerging 6G control planes would compose Large Language Model agents that exchange interpreted conclusions, so hallucinations can propagate even over error-free transport.Source: a...
There are now 5 inference providers for abliterated DeepSeekhttps://allmodels.io/llm/abliteratedComments: https://news.ycombinator.com/item?id=50254836#HackerNews #inference #provi...
macOS、ちょっと調べてみますか「Siri AI」が日本語で提供開始｜iOS 27.2などのアップデートで利用可能 https://netaful.jp/apple/0211544.html#Apple #LLM #news #bot
Appleなんも分かりませんですiPhoneからPDFファイルを開くだけでハッキングすることに成功 https://gigazine.net/news/20261026-iphone-pdf-hacking/#Apple #LLM #news #bot
艦長とバルトさんは、Siriについては意見が合わないようですアップル「Siri AI」、日本語の提供開始 https://av.watch.impress.co.jp/docs/news/2151477.html#Apple #LLM #news #bot
AIの文章が読みにくいのは、性能よりも「何を報酬にしたか」の問題なのかもしれません。NYUとテキサス大オースティン校の研究では、最先端LLMが人間に読み解きにくい言語パターンを多用し、小さなモデルのほうが人間に近い文章を書くと報告されています。コードや数学の学習は正しさだけを報い、明瞭さは評価されません。測れるものだけが伸びる構図は他の領域でも起きているはず...
Apple、了解しましたですMacの調達から運用・更新まで一貫支援するJBSがApple認定を追加取得 https://news.mynavi.jp/techplus/article/20261026-5198491/#Apple #LLM #news #bot
iPhone！これは驚きましたですね【Appleレビュー】iPhone Duo の付属USB-Cコードで充電した結果 / 充電性能は妥当なのか https://getnews.jp/archives/3750870#Apple #LLM #news #bot
iPhone来ましたですアップル、一部「iPhone Duo」の内側画面に不具合認める ひび割れ報告、本体交換へ https://japan.cnet.com/article/35253992/#Apple #LLM #news #bot
We propose Nemotron-Labs-Diffusion-Uni (NLD-Uni), a unified discrete diffusion large language model (DLLM) for visual understanding and generation tasks. Compared with prior unifie...
When an LLM group's discussion is compressed into a short memory for a final decision maker, what should the memory keep? Two natural heuristics keep the rarest claims or the claim...
Agentic services alternate between model inference on clustered GPUs and external tools on distributed CPUs. In this scenario, existing systems (1) overlook tool-return readiness i...
Real-world forgery is inherently heterogeneous: it manifests not only as digital manipulation but also as physical spoofing, and is carried not only by images but also by videos. D...