Research1 мин
New language model will help decipher ancient Greek texts
Новая языковая модель поможет расшифровать древнегреческие тексты.
SMNTCN (Semanticon) — глобальные новости ИИ
Publication Catalog
All stories
All published intelligence, sovereign stack research, ecosystem news, and AI foundation model reviews.
6040
Stories
Industry AI1 мин
Boston Dynamics has begun preparing Atlas humanoids for real work in automobile factories
Boston Dynamics начала готовить гуманоидов Atlas к реальной работе на автомобильных заводах.
Telegram — GPT Time | Нейросети | ИИ
General1 мин
Patti Harrison Had Dreams of a Tech Utopia. Silicon Valley Smashed Them
The comedian sat down with WIRED to talk about social media, AI, and getting laughs for impersonating Boston Dynamics’ robot dogs.
Wired — Artificial Intelligence
General1 мин
A New Tool Found Malware That’s Guided by an AI Hive Mind—No Humans in Sight
Cisco Talos researchers created a new framework for identifying malware and hacking tools that rely on AI chatbots—and quickly discovered something unusual.
Wired — Artificial Intelligence
Research1 мин
Jev Just Made AI 200x Faster…But There’s A Catch
A new AI called Jeff is taking the world by storm, but why get excited for an AI system that can't even write text? It properly ran over the internet, so let's try to separate the facts from the hype. Okay, so it does not write text. Instead, it makes decisions. A question and…
YouTube — Two Minute Papers
Research1 мин
A New Chatbot Wants to Unlock the Secrets in Tattered Ancient Greek Records
In the hope of uncovering new details about ancient life, researchers have developed a large language model that fills in the gaps in papyrus fragments.
Wired — Artificial Intelligence
Knowledge base1 мин
Безопасны ли ваши данные в ИИ-экосистеме Armeta?
Будем выстраивать самую безопасную AI нативную экосистему во всём мире. >> Ильдос, привет. Коротко ответь. Чем занимается директор по информационной безопасности? [музыка] А >> мы в компании отвечаем за доступность, конфиденциальность и целостность информации. >> Безопасно ли…
YouTube — Armeta Kazakhstan
Policy & regulation1 мин
Эпоха тотального изобилия. Часть 3: Илон Маск, ИИ и наш мир через 5 лет.
Смотри, мне что кажется, вот на примере, допустим, нашего стартапа, который мы с тобой развиваем, да, Армета, [музыка] мы строим сегодня искусственный интеллект для строительства, для инженерии. А сегодня мы с тобой автоматизируем деятельность [музыка] государственной экспертизы…
YouTube — Armeta Kazakhstan
Research1 мин
Сравнение навыков Claude Code, субагентов и рабочих процессов в 2026 году
Сравнение навыков Claude Code, субагентов и рабочих процессов в 2026 году.
SMNTCN (Semanticon) — глобальные новости ИИ
Research1 мин
Integrating AI into existing business software
Интеграция ИИ в существующее бизнес-программное обеспечение.
SMNTCN (Semanticon) — глобальные новости ИИ
General1 мин
How to Use AI With Your Privacy Intact
Your conversations with AI chatbots are both highly personal and deeply vulnerable to surveillance. Here’s how you can protect yourself.
Wired — Artificial Intelligence
General1 мин
Появлися мод для Claude Code, который экономит токены. 🦀 Вместо загрузки всех навыков в окно контекста они остаются ...
Появлися мод для Claude Code, который экономит токены.
Telegram — Вайб-кодинг
Research1 мин
A model has been released for AI agents that makes decisions tens of times faster than conventional LLMs
Для ИИ-агентов выпустили модель, которая принимает решения в десятки раз быстрее обычных LLM.
Telegram — GPT Time | Нейросети | ИИ
Knowledge base1 мин
How to Make AI Videos with Seedance AI in 2026 (AI Filmmaking Tutorial)
Ваш ИИ-инструмент для видео может выдать вам красивый 5- секундный клип. Но попросите его создать сцену с полноценным началом и концом, и она развалится по десятку мелких причин. Лицо плывет, а реакция запаздывает на 2 секунды. Поэтому вы перезапускаете генерацию и молитесь.…
YouTube — AI Master
General1 мин
Google has open sourced AX, its orchestrator for AI agents.
Google открыла исходный код AX — своего оркестратора для ИИ-агентов..
Telegram — Вайб-кодинг
General1 мин
Grok 4.7 is finally out - the release was delayed by almost a month
Grok 4.7 наконец вышел — релиз задержался почти на месяц.
Telegram — GPT Time | Нейросети | ИИ
General1 мин
Китай снова в игре: Xiaomi ночью выпустила MiMo-V2.6 Pro и Flash и результаты очень сильные.
Китай снова в игре: Xiaomi ночью выпустила MiMo-V2.6 Pro и Flash и результаты очень сильные. Xiaomi потратила 130 часов, 75 млрд токенов и $2,6 млн на RL, чтобы вывести MiMo-V2.6 Pro на первое место среди открытых моделей. И у них получилось. AA Intelligence Index — 46,32, выше…
Telegram — Вайб-кодинг
Research1 мин
OpenAI researcher Alice Liu completed 57 interviews before joining the company, and then publicly published...
Исследователь OpenAI Алиса Лю прошла 57 собеседований перед тем, как попасть в компанию, а затем открыто опубликовала....
Telegram — Вайб-кодинг
Research1 мин
RBS-Attention: Radius-Bounded Sparse Prefill for Long-Context Large Language Models
Long-context large language model inference is increasingly limited by prefill, where dense self-attention processes the entire prompt before generation begins. Sparse block selection can reduce this cost, but a block centroid may hide a highly relevant token among many…
arXiv — cs.AI
Research1 мин
Attention-Aware Routing: Coupling Routing and Attention in MoEs
In Mixture-of-Experts language models, the router typically selects and weights experts based on the token's hidden state, utilizing limited contextual information. We propose Attention-Aware Routing (AAR), which augments the router with temporal and spectral features extracted…
arXiv — cs.AI
Research1 мин
CaLR: Causal Latent Revision for Robust Diffusion Reasoning
Autoregressive (AR) models suffer from local greediness, while diffusion language models (DLMs) often lack the strict causal structure required for reasoning. To combine the advantages and overcome the drawbacks of the dual, we propose Causal Latent Revision (CaLR), a framework…
arXiv — cs.AI
Research1 мин
LoRA Enhanced Contrastive Learning with SAS Vision Transformers
Automatic target recognition (ATR) with synthetic aperture sonar (SAS) supports advanced naval capabilities, but deep learning is constrained by scarce target imagery, background clutter, and human-in-the-loop assessment. We adapt DINOv3 Vision Transformer (ViT) models to…
arXiv — cs.AI
Research1 мин
Detecting Hallucination in LLMs: Tracing the Topological Signatures of Impaired Context Sharing
In this work, we examine the topology of information flow patterns within attention graphs to effectively distinguish hallucinated from non-hallucinated responses. We analyze the Forman-Ricci curvature to identify structural patterns indicating information bottlenecks in…
arXiv — cs.AI
Research1 мин
Decoupling Internal Representational Changes and Causal Importance in Fine-Tuned Large Language Models
Fine-tuning has emerged as a widely adopted approach for adapting LLMs to a variety of downstream tasks. However, how it reshapes their internal mechanisms remains poorly understood. To address this, we investigate how fine-tuning alters internal representations in LLMs,…
arXiv — cs.AI
Research1 мин
TinyCeNN-LM: Quality-Gated Conversion of Pretrained Attention with CeNN-Inspired Cellular-Recurrent Layers
Replacing attention in a pretrained language model is a compatibility problem: a plausible substitute may alter representations expected by later layers. TinyCeNN-LM introduces a \emph{quality-gated post-training conversion} framework using CeNN-inspired cellular-recurrent…
arXiv — cs.AI
Research1 мин
Clinician-Grounded Quality Assurance for AI-Assisted Psychiatric Intake
Before patients can use AI-assisted psychiatric intake systems, health systems need practical ways to routinely evaluate these tools against their clinical standards for quality assurance. Because clinicians may use different intake styles, evaluation for this task must (1)…
arXiv — cs.AI
Research1 мин
Can Agents Design Better Chips with a Higher Level Abstraction?
Large Language Model (LLM) agents are increasingly being explored for chip design, but most existing approaches operate directly at RTL. We ask whether agents can design better chips by leveraging higher-level abstractions. We compare Direct RTL Design, Agent-based HLS Design,…
arXiv — cs.AI
Research1 мин
Information-Gain Rewards over Diversity-Pruned Tests: GT-Anchored Verifier Co-Training for Reliable Code Generation
Self-play methods that co-train a single language model as both coder and test author promise to move code-generation RL beyond fixed test suites, but they suffer from two coupled pathologies: permissiveness collapse, where pass-rate rewards are maximised by trivial,…
arXiv — cs.AI
Research1 мин
SpecOpt: Contact-Diff Reasoning for Agentic Molecule Optimization Toward Binding Specificity
Off-target protein binding is a major source of adverse effects for small-molecule drugs, yet most structure-based molecular design methods focus on generating selective compounds de novo rather than improving the selectivity of existing, well- characterized drugs. We introduce…
arXiv — cs.AI
Research1 мин
Implicit Rule Induction with Test-Time Task Embeddings in ARC-like Tasks
The Abstraction and Reasoning Corpus and related benchmarks evaluate whether AI models can solve novel reasoning tasks, but often leave unclear whether success reflects inference of the intended underlying rule or reliance on shortcuts. We address this gap by studying test-time…
arXiv — cs.AI