HN 01-_- 4d ago

Claude AI down: Anthropic users hit with errors as chatbot goes offline

Claude chatbot outage with elevated error rates affecting Sonnet 4.6 model and downstream services.

HN ulfaric 4d ago

Show HN: Bring AI Agents to industrial control via "SDK-style" real-time engine

Python real-time engine with sub-1ms jitter for industrial control, auto-generates REST APIs and MCP for LLM agent integration.

HN rantingdemon 4d ago

Anthropic's latest AI model could let hackers carry out attacks faster

Anthropic provides Mythos model to major tech companies for cybersecurity testing and vulnerability discovery.

HN Davincios 4d ago

Open-source weekly live coding session (Thur 5PM)

Open-source framework for AI SRE agents that integrate 40+ infrastructure tools to autonomously investigate and resolve production incidents.

HN stealthybox 4d ago

Why GitOps still matters in a world of AI agents (FluxCon) [video]

Video presentation on GitOps relevance and practices in systems managed by AI agents, from FluxCon conference.

HN qingant 4d ago

Yu – Sandboxes your Claude Code/Codex with zero credential exposure

Yu is a sandboxing tool that isolates Claude Code and Codex execution to prevent credential exposure from compromised code or dependencies.

HN sorenbs 4d ago

GLM 5.1: Pelican Test

GLM-5.1 is a 754B parameter open-source LLM that demonstrates improved reasoning and multi-modal capabilities like unprompted SVG+CSS generation.

HN saikatsg 4d ago

Your parallel Agent limit

Analysis of cognitive load and limitations when managing multiple parallel AI agents, focusing on human-in-the-loop costs beyond throughput metrics.

HN beardyw 4d ago

Row over 'virtual gated community' AI surveillance plan in Toronto neighbourhood

News article on Toronto neighborhood's debate over AI-powered license plate scanning surveillance system to combat property crime.

HN motakuk 4d ago

Enterprise-Managed Authorization for MCP

Enterprise authorization system for Model Context Protocol (MCP) servers using centralized identity providers. Addresses deployment challenges in large organizations.

HN rs545837 4d ago

Structural and semantic component for improving code reviews with local models

Research on improving code reviews by adding semantic analysis layer to local LLMs, providing contextual function/type information beyond diffs.

HN hunglee2 4d ago

China's AI Ethics Governance

Newsletter promotion about AI ethics governance in China. Mostly self-promotional content with no technical depth or original research.

HN jnord 4d ago

Google launched an AI dictation app that works offline

Google releases offline-first dictation app using Gemma-based ASR models. Open-source LLM application for speech recognition on consumer hardware.

HN gpi 4d ago

Two Years of Valkey

Retrospective on Valkey, the open-source Redis fork created two years ago after Redis license change to source-available model.

HN nta25297 4d ago

Optinum – finds the blind spots AI coding agents systematically miss in PR tests

Tool that detects blind spots in AI coding agent pull request reviews by analyzing API and database boundary changes. Addresses integration testing gaps.

HN elliptic1 4d ago

Show HN: Voiceplan.it – The New Planning Mode

Voice-first AI planning tool with MCP integration. Conversational AI agent for strategic planning that generates structured documents in real time.

HN psychip 4d ago

GPU-resident vector database under 300kb

GPU-resident vector database (~300KB executable) supporting 12M vectors with ~10ms query latency, TCP interface, no dependencies.

HN moodiverse 4d ago

Show HN: I'm trying to get 100 users in 24 hours with this simple idea

Buildfeed is a simple social platform for sharing projects without launch pressure, targeting 100 users in 24 hours.

HN MrBuddyCasino 4d ago

"I started to lose my ability to code"

Incomplete article about losing coding ability. Truncated content without substantive information. Likely newsletter signup page.

BL 4d ago

Introducing the Child Safety Blueprint

OpenAI announces Child Safety Blueprint framework for combating AI-enabled child sexual exploitation, developed with NCMEC and law enforcement partners.

Ax Xingrui Zhuo, Jiapu Wang, Gongqing Wu, Zhongyuan Wang, Jichen Zhang, Shirui Pan, Xindong Wu 4d ago

Knowledge Reasoning Language Model: Unifying Knowledge and Language for Inductive Knowledge Graph Reasoning

Knowledge Reasoning Language Model unifies language models with knowledge graphs for inductive reasoning over unknown entities and relations.

Ax Qing Yang, Zhenghao Liu, Yangfan Du, Pengcheng Huang, Tong Xiao 4d ago

RLAIF-SPA: Structured AI Feedback for Semantic-Prosodic Alignment in Speech Synthesis

RLAIF-SPA uses structured AI feedback to improve emotional expressiveness and semantic-prosodic alignment in text-to-speech synthesis.

Ax Afrozah Nadeem, Mark Dras, Usman Naseem 4d ago

Fairness Evaluation and Inference Level Mitigation in LLMs

Methods for evaluating and mitigating fairness issues in LLMs at inference time to reduce harmful behaviors and drift.

Ax Youngjun Choi, Joonseong Kang, Sungjun Lim, Kyungwoo Song 4d ago

Eigen-Value: Efficient Domain-Robust Data Valuation via Eigenvalue-Based Approach

Eigen-Value method for efficient data valuation using eigenvalue-based approach, focusing on out-of-distribution robustness.

Ax Hao Huang, Geeta Chandra Raju Bethala, Shuaihang Yuan, Congcong Wen, Mengyu Wang, Anthony Tzes, Yi Fang 4d ago

One-shot Adaptation of Humanoid Whole-body Motion with Walking Priors

Data-efficient approach for adapting humanoid robot whole-body motion control from single motion examples using walking priors.

Ax Jay Mohta, Kenan Emir Ak, Gwang Lee, Dimitrios Dimitriadis, Yan Xu, Mingwei Shen 4d ago

Routing-Based Continual Learning for Multimodal Large Language Models

Routing-based architecture for multimodal LLMs enabling continual learning across sequential tasks while preventing catastrophic forgetting.

Ax Pawe{\l} Liskowski, Benjamin Han, Paritosh Aggarwal, Bowei Chen, Boxin Jiang, Nitish Jindal, Zihan Li, Aaron Lin, Kyle Schmaus, Jay Tayade, Weicheng Zhao, Anupam Datta, Nathan Wiegand, Dimitris Tsirogiannis 4d ago

Cortex AISQL: A Production SQL Engine for Unstructured Data

Snowflake's Cortex AISQL production engine integrates semantic operations into SQL for querying structured and unstructured data.

Ax Holger Maus, Paul Tschisgale, Fabian Kieser, Stefan Petersen, Peter Wulff 4d ago

Developing and Evaluating a Large Language Model-Based Automated Feedback System Grounded in Evidence-Centered Design for Supporting Physics Problem Solving

LLM-based automated feedback system for physics problem solving using evidence-centered design methodology.

Ax Changeun Kim, Younwoo Jeong, Bong-Gyu Jang 4d ago

Interpretable Deep Learning for Stock Returns: A Consensus-Bottleneck Asset Pricing Model

CB-APM applies deep learning with interpretability-by-design to stock market prediction using analyst consensus data.

Ax Oleksii Proniakin, Diego Fajardo, Ruslan Nazarenko, Razvan Marinescu 4d ago

Automatic Replication of LLM Mistakes in Medical Conversations

MedMistake pipeline automatically extracts and replicates LLM errors in medical conversations to create evaluation benchmarks.

Ax Tianxin Xie, Wentao Lei, Kai Jiang, Guanjie Huang, Pengfei Zhang, Chunhui Zhang, Fengji Ma, Haoyu He, Han Zhang, Jiangshan He, Jinting Wang, Linghan Fang, Lufei Gao, Orkesh Ablet, Peihua Zhang, Ruolin Hu, Shengyu Li, Weilin Lin, Xiaoyang Feng, Xinyue Yang, Yan Rong, Yanyun Wang, Zihang Shao, Zelin Zhao, Chenxing Li, Shan Yang, Wenfu Wang, Meng Yu, Dong Yu, Li Liu 4d ago

PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation

PhyAVBench benchmark evaluates physics-plausibility of audio in text-to-audio-video generation models.

Ax Ruikang Zhang, Shuo Wang, Qi Su 4d ago

Mechanistic Knobs in LLMs: Retrieving and Steering High-Order Semantic Features via Sparse Autoencoders

Framework using sparse autoencoders to identify and steer high-order semantic features in LLMs for reliable control of language generation behaviors.

Ax Yankai Jiang, Qiaoru Li, Binlu Xu, Haoran Sun, Chao Ding, Junting Dong, Yuxiang Cai, Xuhong Zhang, Jianwei Yin 4d ago

IBISAgent: Reinforcing Pixel-Level Visual Reasoning in MLLMs for Universal Biomedical Object Referring and Segmentation

IBISAgent improves pixel-level visual reasoning in medical multimodal LLMs for biomedical object segmentation through enhanced training strategies.

Ax Haoming Xu, Ningyuan Zhao, Yunzhi Yao, Weihong Xu, Hongru Wang, Xinle Deng, Shumin Deng, Jeff Z. Pan, Huajun Chen, Ningyu Zhang 4d ago

Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency

Research paper analyzing LLM truthfulness under contextual perturbations, showing self-consistent facts can collapse under mild interference.

Ax Jingsheng Zheng, Jintian Zhang, Yujie Luo, Yuren Mao, Yunjun Gao, Lun Du, Huajun Chen, Ningyu Zhang 4d ago

Can We Predict Before Executing Machine Learning Agents?

Research paper proposing predictive reasoning to replace costly physical execution in ML agent workflows using internalized execution priors.

Ax Hyun Do Jung, Jungwon Choi, Hwiyoung Kim 4d ago

ReaMIL: Reasoning- and Evidence-Aware Multiple Instance Learning for Whole-Slide Histopathology

ReaMIL, a multiple instance learning approach for histopathology with reasoning-aware evidence selection under sparsity constraints.

Ax Xiangchen Li, Jiakun Fan, Qingyuan Wang, Dimitrios Spatharakis, Saeid Ghafouri, Hans Vandierendonck, Deepu John, Bo Ji, Ali R. Butt, Dimitrios S. Nikolopoulos 4d ago

WISP: Waste- and Interference-Suppressed Distributed Speculative LLM Serving at the Edge via Dynamic Drafting and SLO-Aware Batching

WISP system for distributed LLM inference at the edge using dynamic drafting and SLO-aware batching to balance workload across networks.

Ax Naeem Paeedeh, Mahardhika Pratama, Ary Shiddiqi, Zehong Cao, Mukesh Prasad, Wisnu Jatmiko 4d ago

Cross-Domain Few-Shot Learning for Hyperspectral Image Classification Based on Mixup Foundation Model

Cross-domain few-shot learning for hyperspectral image classification using mixup foundation models to reduce overfitting.

Ax Zhuohong Chen, Zhengxian Wu, Zirui Liao, Shenao Jiang, Hangrui Xu, Yang Chen, Chaokui Su, Xiaoyu Liu, Haoqian Wang 4d ago

R3G: A Reasoning--Retrieval--Reranking Framework for Vision-Centric Answer Generation

R3G framework for vision-centric visual question answering using reasoning, retrieval, and reranking to select and integrate relevant images.

Ax Fengxu Yang, Jack D. Evans 4d ago

QUASAR: A Universal Autonomous System for Atomistic Simulation and a Benchmark of Its Capabilities

QUASAR, a universal autonomous system integrating LLMs for atomistic simulation and materials science discovery with flexible tool-calling for production workflows.

Ax V\'ictor Yeste, Paolo Rosso 4d ago

Do Schwartz Higher-Order Values Help Sentence-Level Human Value Detection? A Study of Hierarchical Gating and Calibration

Study on hierarchical gating and calibration for human value detection from sentences using Schwartz higher-order categories.

Ax Lixiang Fan, Bohao Li, Tao Zou, Junchen Ye, Bowen Du 4d ago

Incident-Guided Spatiotemporal Traffic Forecasting

Deep learning and GNN methods for traffic forecasting that incorporate incident data as external disturbances to improve predictions.

Ax Mahmud Ashraf Shamim, Md Moshiur Rahman Raj, Mohamed Hibat-Allah, Paulo T Araujo 4d ago

Graph-Theoretic Analysis of Phase Optimization Complexity in Variational Wave Functions for Heisenberg Antiferromagnets

Graph-theoretic analysis of computational complexity in learning ground state phases of Heisenberg antiferromagnets using variational methods.

Ax Ehud Shapiro 4d ago

Implementing Grassroots Logic Programs with Multiagent Transition Systems and AI

Derives deterministic operational semantics for Grassroots Logic Programs (GLP), a multiagent concurrent logic programming language for serverless platforms.

Ax Baorong Shi, Bo Cui, Boyuan Jiang, Deli Yu, Fang Qian, Haihua Yang, Huichao Wang, Jiale Chen, Jianfei Pan, Jieqiong Cao, Jinghao Lin, Kai Wu, Lin Yang, Shengsheng Yao, Tao Chen, Xiaojun Xiao, Xiaozhong Ji, Xu Wang, Yijun He, Zhixiong Yang 4d ago

MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs

MedXIAOHE, a medical multimodal foundation model with entity-aware continual pretraining, achieves state-of-the-art on clinical benchmarks.

Ax David Puertolas Merenciano, Ekaterina Vasyagina, Kevin Zhu, Javier Ferrando, Maheep Chaudhary 4d ago

Weight space Detection of Backdoors in LoRA Adapters

Method to detect backdoor attacks in LoRA adapters without test inputs by analyzing weight space, addressing security vulnerabilities in shared model repositories.

Ax Kihoon Son, Hyewon Lee, DaEun Choi, Yoonsu Kim, Tae Soo Kim, Yoonjoo Lee, John Joon Young Chung, HyunJoon Jung, Juho Kim 4d ago

"When to Hand Off, When to Work Together": Expanding Human-Agent Co-Creative Collaboration through Concurrent Interaction

Study on human-agent co-creative collaboration patterns in shared workspaces, revealing capability gaps for concurrent interaction vs sequential delegation.

Ax Prerna Ravi, Om Gokhale, Suyash Fulay, Eugene Yi, Deb Roy, Michiel Bakker 4d ago

Agora: Teaching the Skill of Consensus-Finding with AI Personas Grounded in Human Voice

Agora platform uses LLMs with AI personas to teach civic competence and consensus-finding skills through deliberative democratic practice.

Ax Anupam Purwar, Aditya Choudhary 4d ago

MM-tau-p$^2$: Persona-Adaptive Prompting for Robust Multi-Modal Agent Evaluation in Dual-Control Settings

MM-tau-p²: Persona-adaptive evaluation framework for multi-modal LLM agents with dual-control settings exposing user personality and behavior adaptation.

Ax Maria Rosaria Briglia, Simone Facchiano, Paolo Cursi, Alessio Sampieri, Emanuele Rodol\`a, Guido Maria D'Amely di Melendugno, Luca Franco, Fabio Galasso, Iacopo Masi 4d ago

Not All Latent Spaces Are Flat: Hyperbolic Concept Control

HyCon: Hyperbolic control mechanism for steering text-to-image models away from unsafe concepts using parallel transport instead of Euclidean adjustments.