HN aamir_m 29d ago

Show HN: Open-Source RAG Security Kit for Zero-Trust Retrieval

Discusses challenges maintaining AI-built internal tools beyond initial development. Title only.

HN vinodstartup 29d ago

Genesis AI launches Eno general-purpose robot

Survey on AI adoption rates among Americans. Sociology-focused, title only.

BL 29d ago

A near-autonomous AI chemist improves a challenging reaction in medicinal chemistry

OpenAI's GPT-5.4 used with Molecule.one's Maria to optimize Chan-Lam Coupling reactions in medicinal chemistry, achieving >80% yield improvement across substrates.

HN CrazyTomato 29d ago

An End-to-End Machine Learning Pipeline on Time-Series Data

DolphinDB ML platform integrates algorithms, libraries, and distributed computing for time-series data workflows.

HN ruimbarreira 29d ago

Show HN: I built 184 free browser tools – PDF, image, dev, AI tasks, no upload

Collection of 184 browser-based tools for PDFs, images, dev tasks, and AI applications without cloud uploads.

HN petethomas 29d ago

Tokenization's Next Big Conundrum: What Do Buyers Get?

Incomplete article about tokenization economics.

HN salim2006 29d ago

How to reduce your API LLM bill

Guide for optimizing expenses when using LLM APIs without specific techniques detailed.

HN schvenk 29d ago

The Joy of Tech: A Different Path for Products, People, & AI

Opinion piece on technology product design and AI philosophy without technical content.

HN nu11P01nt3r 29d ago

Which AI agent spent the money on your OpenAI/Anthropic bill

Book/article about alternative product development philosophy involving AI. Vague, title only.

HN morajabi 29d ago

YC Application Review Skill

AI knowledge pack helping founders review Y Combinator applications using official YC resources.

HN ferhatelmas 29d ago

Composable building blocks for full-stack AWS apps

AWS Blocks: Backend toolkit for composable full-stack AWS applications with local development support.

HN rowbin 29d ago

Oracle's OpenJDK Bans Generative AI Contributions, Oracle's GraalVM Allows Them

Oracle's OpenJDK bans AI-generated contributions while GraalVM permits them, establishing conflicting policies on generative AI code submissions.

HN himata4113 29d ago

GLM-5.2 is the new leading open weights model on Artificial Analysis

GLM-5.2 open weights model (744B/40B active params) achieves top score on Artificial Analysis benchmark at competitive pricing compared to proprietary APIs.

HN gjmveloso 29d ago

Distributed AI on AWS

Production-ready reference architectures and code for distributed LLM training on AWS using PyTorch, Megatron-LM, JAX with Kubernetes/Slurm deployment scripts.

HN sschueller 29d ago

Multiple JetBrains IDE plugins caught stealing AI keys

Security report: 15 malicious JetBrains IDE plugins masquerading as AI coding assistants stole API keys from ~70k users.

HN lumpa 29d ago

Building an AI Agent in 6 Weeks (and Understanding How They Work)

Educational cohort program teaching production AI agent development in Python over 6 weeks, with participant case study shipping working agent application.

HN promptalex53 29d ago

RustChain: DePIN for Vintage Hardware

Blockchain project mining cryptocurrency on vintage hardware with financial incentives.

HN andrew_zol 29d ago

Show HN: Xpenser – self-hostable personal finance tracker with MCP access

Open-source self-hostable finance tracker with MCP access and API support.

HN Vishi_2 29d ago

Show HN: CLI Integrated Latex Editor

CLI LaTeX editor powered by Claude that writes and compiles documents from plain language descriptions.

HN dkobia 29d ago

The Hacker Sent by Anthropic to Calm the Government's Nerves About AI Safety

Discussion of Anthropic representative addressing government AI safety concerns. Minimal substantive content.

HN alecco 29d ago

GLM-5.2 is the leading open weights model on the Intelligence Index v4.1

GLM-5.2 designed for long-horizon task execution. Title only, no technical details provided.

HN javatuts 29d ago

Claude Code Skills Turn It into an AI Engineering Team

Claude's code execution capabilities enabling multi-task engineering workflows. Headline-only; lacks technical depth.

HN akshay2211 29d ago

Ucp-Local – Offline RAG for Claude Desktop, Cursor, and LM Studio

GLM-5.2 ranks first on Intelligence Index v4.1 benchmark for open weights models. Title only.

HN doener 29d ago

Lovable merges credit balance with Cloud and AI balance

Product update about Lovable combining credit and AI balance systems. Insufficient detail provided.

HN lucioduran 29d ago

Lighthouse for AI Agents

Lighthouse tool/framework for AI agent development. Insufficient content detail provided in excerpt.

HN Topfi 29d ago

Common Corpus: The Largest Collection of Ethical Data for LLM PRE-Training

Common Corpus dataset claims to be largest ethical collection for LLM pretraining. Title only, no content.

HN ilreb 29d ago

New Approach to Scaling Laws Could Change How AI Models Are Trained

Research on novel scaling law approaches for AI model training. Headline only; requires full article evaluation.

HN JosefAlbers 29d ago

Mlx-Code: A Coding Agent That Speaks Git Natively

mlx-code: AI coding agent that maps state history to Git commits instead of databases, with multi-agent workflow support.

HN theanonymousone 29d ago

GLM 5.2 Performance Benchmarks

Comprehensive performance benchmarks for open-weight GLM-5.2 model across intelligence metrics, speed, and context window capabilities.

HN tarkaTheRotter 29d ago

Maven Central (finally imposes) Publishing Limits

Maven Central introduces publishing limits for high-volume Java package activity to prevent abuse of shared infrastructure.

HN yooibox 29d ago

MediaUse Site Skills

MediaUse: CLI infrastructure for AI agents to interact with websites via browser automation and site-specific plugins.

HN joozio 29d ago

Exclusive eBook: How AI is becoming the next military advisor

Paywalled eBook collection on military AI decision-making applications. Subscription-restricted content with limited preview.

HN alfanick 29d ago

Show HN: Mini-film – open-source tool for batch processing and reviewing RAWs

Open-source tool for batch processing and reviewing RAW images with film emulation.

Ax Maeva Guerrier, Karthik Soma, Jana Pavlasek, Giovanni Beltrame 29d ago

Can Vision Foundation Models Navigate? Zero-Shot Real-World Evaluation and Lessons Learned

Real-world evaluation of five vision foundation models for robot navigation, measuring trajectory quality and robustness beyond success rate metrics.

Ax Qichuan Yin, Ziwei Su, Shuangning Li 29d ago

Overcoming the Incentive Collapse Paradox

Analyzes incentive collapse in AI-assisted task delegation where improved AI accuracy paradoxically requires unbounded human effort payments.

Ax Fangjun Hu, Christian Kokail, Milan Kornja\v{c}a, Pedro L. S. Lopes, Weiyuan Gong, Sheng-Tao Wang, Xun Gao, Stefan Ostermann 29d ago

Learning and Generating Mixed States Prepared by Shallow Channel Circuits

Methods for learning and generating quantum mixed states prepared by shallow channel circuits.

Ax Asmaa Eldesoukey, Yongxin Chen, Abhishek Halder 29d ago

A Generalized Sinkhorn Algorithm for Mean-Field Schr\"odinger Bridge

Generalized Sinkhorn algorithm for solving mean-field Schrödinger bridge problems in multi-agent diffusion systems.

Ax Nick Souligne, Vignesh Subbian 29d ago

Evaluating Intersectional Fairness across Clinical Machine Learning Use Cases using Fairlogue and the All of Us Research Program

FairLogue toolkit evaluates intersectional biases in clinical machine learning models using All of Us dataset across multiple demographic groups.

Ax Ryuki Tsukuba, Kazutoshi Ando 29d ago

Characterizing Admissible Objective Functions for Hierarchical Clustering

Theoretical analysis of objective functions for hierarchical clustering, extending Dasgupta's framework with admissibility concept.

Ax Luo Ji, Qi Qin, Ningyuan Xi, Teng Chen, Qingqing Gu, Hongyan Li 29d ago

Learn-To-Learn on Arbitrary Textual Conditioning: A Hypernetwork-Driven Meta-Gated LLM

Meta-learning approach using hypernetworks and meta-gating in SwiGLU blocks to help LLMs handle diverse textual conditions without catastrophic forgetting.

Ax Zhengrui Xiang, Jiaqi Wu, Fupeng Sun, Heliang Zheng, Yingzhen Li 29d ago

DVD: Discrete Voxel Diffusion for 3D Generation and Editing

Discrete diffusion framework for 3D voxel generation and editing in generative pipelines.

Ax Runang He, Tongya Zheng, Huiling Peng, Yuanyu Wan, Bingde Hu, Jiawei Chen, Canghong Jin, Mingli Song, Can Wang 29d ago

Temporal Motif-aware Graph Test-time Adaptation for OOD Blockchain Anomaly Detection

Test-time adaptation method for graph anomaly detection on blockchain with temporal motifs.

Ax Collin Cranston, Zhichao Wang, Todd Kemp, Michael W. Mahoney 29d ago

Eigen-Spike Emergence and Quadratic Equivalents for Conjugate Kernels on Nonlinearly Separable Data

Random matrix theory analysis of spectral behavior for nonlinear kernels on non-linearly separable data.

Ax Xuhui Lin, Stephen Law, Nanjiang Chen, Kunyao Li, Tao Yang 29d ago

A 3D Isovist World Model -- Revealing a City's Unseen Geometry and Its Emergent Cross-City Signature

3D world model for embodied navigation agents predicting traversable space rather than visual appearance.

Ax Giorgio Maria Cavallazzi, Miguel P\'erez-Cuadrado, Alfredo Pinelli 29d ago

Reward hacking in physical reinforcement learning revealed by turbulent drag reduction

Analyzes reward hacking in physical RL agent controlling turbulent drag reduction, demonstrating design-intent divergence.

Ax Ruida Wang, Jerry Huang, Pengcheng Wang, Xuanqing Liu, Luyang Kong, Tong Zhang 29d ago

Lean4Agent: Formal Modeling and Verification for Agent Workflow and Trajectory

Formal verification framework for LLM agent workflows using Lean4, enabling specification and debugging of multi-step trajectories.

Ax Han-yu Wang 29d ago

Priors Persist Through Suppression: A Stroop Paradigm for Lexical Override

Stroop-style experiments showing LLM lexical priors persist despite system prompts attempting semantic remapping.

Ax Zhicheng Du, Lan Ma 29d ago

Continuous Language Diffusion as a Decoder-Interface Problem

Studies diffusion language models as decoder-interface problem, identifying decoder-basin mechanism for denoising.

Ax Kevin Han Huang 29d ago

Data augmented bootstrap: Unifying confidence interval construction by approximate invariance

Data augmented bootstrap framework for constructing confidence intervals from approximate symmetries.

Ax Badr AlKhamissi, Johannes Mehrer, Lara Marinov, Ahmed Abdelaal, Abdulkadir Gokce, Martin Schrimpf 29d ago

Discovering Functionally Selective Brain Regions with a Deep Topographic Multimodal Model

Topographic multimodal neural model discovering functionally selective brain regions across sensory systems.