Telegram — Вайб-кодинг
Publication Catalog
所有文章
All published intelligence, sovereign stack research, ecosystem news, and AI foundation model reviews.
2220
Stories
Исследования1 мин
看起来 Jev 有一个开放的本地替代方案 - Laya。
看起来 Jev 有一个开放的本地替代方案 - Laya。 Laya是一个本地开放决策模型，拥有4.21亿个参数。它适用于结构化决策（快速是/否答案、评估或从选项中进行选择）。 > 适用于小于 1 GB 的内存 >...
Telegram — Вайб-кодинг
Исследования1 мин
不要被今年夏天的人工智能炒作所愚弄
对于人工智能的炒作来说，这几个月是忙碌的。 4 月底，Anthropic 声称其模型 Claude Mythos 比大多数安全专家更擅长发现软件漏洞。然后我们发生了 OpenAI – Hugging Face 黑客事件，之后 Anthropic（自豪地）和 Meta…
MIT Technology Review
Исследования1 мин
New language model will help decipher ancient Greek texts
Новая языковая модель поможет расшифровать древнегреческие тексты.
SMNTCN (Semanticon) — глобальные новости ИИ
Исследования1 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
Исследования1 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
Исследования1 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
SMNTCN (Semanticon) — глобальные новости ИИ
Исследования1 мин
人工智能代理模型已经发布，其决策速度比传统法学硕士快数十倍
Для ИИ-агентов выпустили модель, которая принимает решения в десятки раз быстрее обычных LLM.
Telegram — GPT Time | Нейросети | ИИ
Исследования1 мин
OpenAI研究员Alice Liu在加入公司之前完成了57次面试，然后公开发表...
Исследователь OpenAI Алиса Лю прошла 57 собеседований перед тем, как попасть в компанию, а затем открыто опубликовала....
Telegram — Вайб-кодинг
Исследования1 мин
CogGym: Towards Large-Scale Comparative Evaluation of Human and Machine Cognition
Understanding and modeling human intelligence are parallel goals shared by artificial intelligence (AI) and cognitive science. As AI systems grow increasingly capable, in what ways do model responses resemble human responses, and where do they systematically diverge? The sheer…
arXiv — cs.AI
Исследования1 мин
DENSE: Distilling Agent Trajectories into Evidence-Grounded Shortcut Trees for Self-Refinement
Online agent deployments produce abundant execution traces, while task-specific verification and expert annotation are costly to scale. We study how to distill these traces into reusable feedback without post-hoc outcome labels, drawing on their evidence of local progress,…
arXiv — cs.AI
Исследования1 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
Исследования1 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
Исследования1 мин
Efficient Benchmarking in Production: A Study of an Evolving LLM Agent
Production LLM agents are evaluated repeatedly as they evolve, but full agent benchmarks are costly to rerun. We study efficient recurring evaluation for a production analytics agent serving tens of thousands of monthly active users and report first-hand deployment experience.…
arXiv — cs.AI
Исследования1 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
Исследования1 мин
GVPO++: Group Variance Policy Optimization for LLM Post-Training and On-Policy Distillation
Post-training plays a pivotal role in enhancing the reasoning capabilities and task-specific expertise of large language models (LLMs). Despite recent advances in post-training methods, such as Group Relative Policy Optimization (GRPO), their practical deployment remains impeded…
arXiv — cs.AI
Исследования1 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
Исследования1 мин
A Fully Differentiable Neuro-Soft-Symbolic Framework for Perceptual Task Planning
Perceptual planning tasks require two key capabilities: accurately perceiving uncertain scenes and planning valid action sequences following logical rules. Conventional methods convert perception into discrete symbolic facts and then plan, discarding perceptual uncertainty and…
arXiv — cs.AI
Исследования1 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
Исследования1 мин
PlaceReasoner-Beta: Reasoning-Driven Macro Placement and Benchmarking
Automated macro placement remains a fundamental challenge in VLSI physical design. Despite decades of research, existing approaches predominantly optimize hand-crafted proxy objectives, such as estimated wirelength, and typically produce placements through one-shot numerical…
arXiv — cs.AI
Исследования1 мин
LEGIT: Credentialing Protocol for Trustworthy AI Agent Marketplaces
Agentic marketplaces are emerging where AI agents with varying capabilities autonomously complete specialized tasks for buyers. A major challenge of such marketplaces is that buyers cannot easily determine which agent will perform best on their tasks. Reported benchmark scores…
arXiv — cs.AI
Исследования1 мин
GameASG-Bench: Benchmarking Autonomous Software Generation for Game Development
Autonomous software generation (ASG) aims to turn human requirements into executable applications, but delivering these applications does not necessarily establish that their interacting components satisfy the specified behavioral requirements. We introduce GameASG-Bench, a…
arXiv — cs.AI
Исследования1 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
Исследования1 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
Исследования1 мин
AI-GRACE: A Use-Case Operationalization Framework for Agentic AI: From Organizational Objectives and Obligations to Deployment Capabilities and Architecture
Organizations deploying agentic artificial intelligence must determine more than whether a model is trustworthy; they must establish what to validate, control, and observe for a use case to deliver its intended outcome while meeting applicable obligations. This paper proposes…
arXiv — cs.AI
Исследования1 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
Исследования1 мин
Driving on Registers, Reasoning on Risk: Risk-Aware Occupancy for Register-Based End-to-End Autonomous Driving
Multimodal trajectory prediction improves behavioral coverage in end-to-end autonomous driving, but existing methods remain limited by sparse scene representations. Incomplete evidence leads to low-quality candidate generation and unreliable ranking among geometrically similar…
arXiv — cs.AI
Исследования1 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
Исследования1 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