HN kreicer 20d ago

Show HN: Omen – A lightweight Kubernetes chaos operator with manual approval

Lightweight Kubernetes chaos engineering operator with manual approval gates and webhook notifications for safe, transparent testing.

HN emregucerr 20d ago

Show HN: Artificial Intelligence Squared – LLMs Debate Each Other

Benchmark tool for LLM comparison using Oxford-style debate format where models compete to flip votes.

HN BruzWJ 20d ago

TradingGoose-Market: canonical ticker identity across market data providers

Data structure providing canonical ticker identity mapping across financial market data providers.

HN hanwoo 20d ago

Show HN: An API that catches what your LLM confidently got wrong

API providing factual verification for LLMs through semantic news search, evidence ranking, and causal reasoning with structured JSON responses.

HN prmalik 20d ago

How to Add Memory to Your Hermes Agent

Headline only, insufficient content about adding memory capabilities to Hermes agent.

HN namin 20d ago

Show HN: Guardians – Verify tool-using agent workflows before execution

Static verification tool for AI agent workflows using structured planning with symbolic references to prevent prompt injection, based on Guardians of the Agents paper.

HN ramoz 20d ago

Show HN: Agent Skill Based on "Open Source Security at Astral"

AI agent skill that audits code repositories for security issues and generates HTML reports with findings and recommendations.

HN akinalpfdn 20d ago

New version of Claude-ground with newly added skills for indie devs

Rule system for Claude Code that adds structural discipline through phase tracking, decision logging, and language-specific best practices as reusable skills.

HN samagra14 20d ago

Pages of Claude Mythos That Got Zero Headlines

Incomplete stub referencing Claude Mythos headlines without content.

HN danielmateo773 20d ago

Uni-1 AI – Advanced AI Platform for Content Generation

AI image generation tool claiming reasoning capabilities for spatial logic and object relationships vs diffusion-based models.

HN 8dazo 20d ago

Show HN: 8d – Agent-Native Version Control, where Git breaks

8d: agent-native version control system designed to handle workflows where traditional Git breaks, optimized for AI agent collaboration.

HN koteelok 20d ago

Keychron's keyboards are now open source

Keychron released production-grade CAD files for keyboards and mice under source-available license for personal and educational use.

HN da352 20d ago

I built an open-source research lab that reads papers and iterates autonomously

Arcana: open-source browser-based research lab where AI agents autonomously read papers, formulate hypotheses, execute experiments on remote GPUs, and iterate.

HN taubek 20d ago

Think out loud. Your ideas get structure

Headline only, insufficient content about idea structuring tool.

HN mellosouls 20d ago

Hi, This Is Clicky

Open-source AI teacher assistant that appears as buddy next to cursor, can see screen and provide contextual guidance using Claude.

HN ankitg12 20d ago

Process Manager for Autonomous AI Agents

Process manager for persistent AI agents with terminal dashboard, web UI, declarative config, and support for macOS, Linux, Windows.

HN AidanKeogh 20d ago

What Is Lipoless? Complete Guide to Weight Loss Support [pdf]

Weight loss supplement guide. Off-topic.

HN alokDT 20d ago

One Engineer, One AI, One Week: Cloudflare Just Rebuilt Next.js

Headline only claiming Cloudflare rebuilt Next.js with one engineer and AI in one week.

HN lumpa 20d ago

Meta's new model is Muse Spark, and meta.ai chat has some interesting tools

Meta released Muse Spark model via private API preview on meta.ai, claims competitive performance with Opus 4.6, Gemini 3.1 Pro, GPT 5.4.

HN cambone 20d ago

Show HN: Local browser extension, scans ToS with regex, no AI

Browser extension using regex patterns to scan Terms of Service and privacy policies for red flags, no AI or data transmission.

HN radurevutchi 20d ago

Dola – AI Consulting for your tiny firm

White-glove AI consulting agency deploying AI-first products across industries with strategic guidance and technical implementation.

HN gpi 20d ago

Does Anybody Need Me?

Personal essay reflecting on changing role of software engineers amid rise of agentic AI systems and autonomous coding tools.

HN wazHFsRy 20d ago

The Usefulness of AI Agents

Researcher discusses LLM-powered agents, challenges keeping research current with rapid industry development.

HN pavpanchekha 20d ago

Can LLMs accelerate science? An experiment

Experimental analysis of whether LLMs can accelerate scientific research. Tests Opus and Codex on wet lab tasks.

HN paulpauper 20d ago

When AI Day of Reckoning?

Analysis of AI ROI expectations and failure rates. Discusses coding as LLMs' most promising application area.

HN azhenley 20d ago

Keychron has open sourced its hardware

Keychron released production-grade CAD files for keyboards and mice under source-available license for personal and educational use.

HN 1270011 20d ago

I rebuilt Claude Code's removed /buddy companion as a permanent MCP app

Open-source MCP app restoring Claude's removed /buddy companion feature as standalone assistant compatible with any Claude Code version.

HN handfuloflight 20d ago

The Waymo Rule for AI-Generated Code

Article argues AI-generated code only needs to exceed developer capability, discusses formal methods and language design.

HN bobchen1322 20d ago

GPU solver that matches Fujitsu's $1M Digital Annealer on cubic optimization

GPU-based solver for higher-order binary optimization (HUBO) problems with 3+ variable interactions, matching commercial annealer performance.

HN mgh2 20d ago

Apple Will Release iPhone Air 2 No Matter How Badly It May Sell

Apple iPhone Air 2 sales predictions and design rumors from a leaker.

Ax Sotaro Ishii, Tetsuro Tanaka 20d ago

High-Precision Estimation of the State-Space Complexity of Shogi via the Monte Carlo Method

Statistical estimation of Shogi game state-space complexity using Monte Carlo methods, narrowing previous estimates to higher precision.

Ax Cameron Pattison, Lorenzo Manuali, Seth Lazar 20d ago

Blind Refusal: Language Models Refuse to Help Users Evade Unjust, Absurd, and Illegitimate Rules

Research documenting patterns of language model refusal on unjust or absurd rules, arguing for better moral reasoning in AI safety training.

Ax Elena Villalobos (Tecnol\'ogico de Monterrey, Mexico City, Mexico), Adolfo De Un\'anue T. (Tecnol\'ogico de Monterrey, Mexico City, Mexico), Fernanda Sobrino (Tecnol\'ogico de Monterrey, Mexico City, Mexico), David Ak\'e (Tecnol\'ogico de Monterrey, Mexico City, Mexico), Stephany Cisneros (Tecnol\'ogico de Monterrey, Mexico City, Mexico), Jorge Lecona (Container Terminal Operations, Veracruz, Mexico), Alejandra Matadamaz (Container Terminal Operations, Veracruz, Mexico) 20d ago

Toward Reducing Unproductive Container Moves: Predicting Service Requirements and Dwell Times

Data science study using machine learning to predict container service requirements and dwell times at terminals to reduce unproductive moves.

Ax Shoaib Sadiq Salehmohamed, Jinal Prashant Thakkar, Hansika Aredla, Shaik Mohammed Omar, Shalmali Ayachit 20d ago

Weakly Supervised Distillation of Hallucination Signals into Transformer Representations

Research on distilling hallucination detection signals into transformer representations during training, enabling inference-time detection without external verification.

Ax Isaac Henry, Avery Byrne, Christopher Giza, Ron Henry, Shahram Yazdani 20d ago

SymptomWise: A Deterministic Reasoning Layer for Reliable and Efficient AI Systems

Framework combining expert medical knowledge with deterministic reasoning to improve reliability and reduce hallucinations in AI-driven symptom analysis systems.

Ax Satwik Pandey, Suresh Raghu, Shashwat Pandey 20d ago

SELFDOUBT: Uncertainty Quantification for Reasoning LLMs via the Hedge-to-Verify Ratio

Research paper on uncertainty quantification for reasoning LLMs using hedge-to-verify ratio, addressing limitations of sampling and single-pass proxy methods for proprietary APIs.

Ax Varun Pratap Bhardwaj 20d ago

Qualixar OS: A Universal Operating System for AI Agent Orchestration

Application-layer OS for universal AI agent orchestration supporting 10 LLM providers, 8+ frameworks, 12 multi-agent topologies, and heterogeneous systems.

Ax Kranthi Kommuru, Kunal Khanvilkar, Gaurav Parekh 20d ago

ProofSketcher: Hybrid LLM + Lightweight Proof Checker for Reliable Math/Logic Reasoning

Hybrid LLM plus lightweight proof checker for reliable math/logic reasoning, verifying arguments and catching logical missteps in generated proofs.

Ax Jiaju Lin, Xingjian Du, Qingyun Wu, Ellen Wenting Zou, Jindong Wang 20d ago

On Emotion-Sensitive Decision Making of Small Language Model Agents

Studies emotion-sensitive decision-making in small language model agents using activation steering and game-theoretic evaluation.

Ax Qihan Ren, Peng Wang, Ruikun Cai, Shuai Shao, Dadi Guo, Yuejin Xie, Yafu Li, Quanshi Zhang, Xia Hu, Jing Shao, Dongrui Liu 20d ago

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

Analysis of cross-domain generalization in reasoning SFT with chain-of-thought, showing generalization is conditional on optimization, data, and base model capability.

Ax Monirul Islam Pavel, Siyi Hu, Muhammad Anwar Masum, Mahardhika Pratama, Ryszard Kowalczyk, Zehong Jimmy Cao 20d ago

KD-MARL: Resource-Aware Knowledge Distillation in Multi-Agent Reinforcement Learning

Knowledge distillation framework for multi-agent RL enabling resource-aware deployment on edge devices with smaller models.

Ax Yujun Cheng, Enfang Cui, Hao Qin, Zhiyuan Liang, Qi Xu 20d ago

AgentGate: A Lightweight Structured Routing Engine for the Internet of Agents

Lightweight routing engine for Internet of Agents managing agent discovery and request dispatch across devices, edge, and cloud with latency/privacy constraints.

Ax Samuel Sameer Tanguturi 20d ago

ATANT: An Evaluation Framework for AI Continuity

Open evaluation framework ATANT for measuring continuity in AI systems: persistence, context updating, and reconstruction across time.

Ax Jianhong Pang, Ruoxi Cheng, Ziyi Ye, Xingjun Ma, Zuxuan Wu, Xuanjing Huang, Yu-Gang Jiang 20d ago

Steering the Verifiability of Multimodal AI Hallucinations

Framework for steering verifiability of multimodal LLM hallucinations, distinguishing between obvious and elusive hallucinations to guide mitigation strategies.

Ax Juan Du, Yueteng Wu, Pan Zhao, Yuze Liu, Min Zhang, Xiaobin Xu, Xinglong Zhang 20d ago

TurboAgent: An LLM-Driven Autonomous Multi-Agent Framework for Turbomachinery Aerodynamic Design

LLM-driven autonomous multi-agent framework for end-to-end turbomachinery aerodynamic design, coordinating geometry, prediction, optimization, and validation.

Ax Shivanshu Shekhar, Sagnik Mukherjee, Jia Yi Zhang, Tong Zhang 20d ago

FVD: Inference-Time Alignment of Diffusion Models via Fleming-Viot Resampling

Inference-time alignment method for diffusion models using Fleming-Viot resampling to prevent diversity collapse in SMC sampling.

Ax Suhaas Garre, Erik Knutsen, Sushant Mehta, Edwin Chen 20d ago

Riemann-Bench: A Benchmark for Moonshot Mathematics

Benchmark for mathematical reasoning beyond competition math, testing advanced theoretical knowledge and deep mathematical reasoning.

Ax Zonghuan Xu, Xiang Zheng, Yutao Wu, Xingjun Ma 20d ago

Beyond Surface Judgments: Human-Grounded Risk Evaluation of LLM-Generated Disinformation

Evaluates LLM-generated disinformation risk by comparing LLM judges to human evaluation, addressing limitations of automated assessment.

Ax Daniele Fossem\`o, Filippo Mignosi, Giuseppe Placidi, Luca Raggioli, Matteo Spezialetti, Fabio Aurelio D'Asaro 20d ago

Explaining Neural Networks in Preference Learning: a Post-hoc Inductive Logic Programming Approach

Using inductive logic programming to approximate neural networks for user preference learning with explainability.

Ax Songze Li, Xiaoke Guo, Tianqi Liu, Biao Yi, Zhaoyan Gong, Zhiqiang Liu, Huajun Chen, Wen Zhang 20d ago

What's Missing in Screen-to-Action? Towards a UI-in-the-Loop Paradigm for Multimodal GUI Reasoning

GUI reasoning paradigm called UI-in-the-Loop for improved UI understanding and interaction, enhancing interpretability in screen-to-action tasks.