Ax Sicheng Zuo, Zixun Xie, Wenzhao Zheng, Shaoqing Xu, Fang Li, Hanbing Li, Long Chen, Zhi-Xin Yang, Jiwen Lu 28d ago

DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scale

DVGT-2: Vision-Geometry-Action model for autonomous driving using dense 3D geometry instead of language descriptions for planning.

Ax Manoj Parmar 28d ago

Safety, Security, and Cognitive Risks in World Models

Analyzes safety, security, and cognitive risks in world models used for autonomous decision-making in robotics and agentic AI systems.

Ax Vardaan Pahuja, Samuel Stevens, Alyson East, Sydne Record, Yu Su 28d ago

Automatic Image-Level Morphological Trait Annotation for Organismal Images

Uses sparse autoencoders to automatically annotate morphological traits in biological organism images, automating expert-driven extraction process.

Ax Wei Zou, Mingwen Dong, Miguel Romero Calvo, Shuaichen Chang, Jiang Guo, Dongkyu Lee, Xing Niu, Xiaofei Ma, Yanjun Qi, Jiarong Jiang 28d ago

Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents

Demonstrates environment-injected memory poisoning attacks on LLM-based web agents through contamination persisting across sessions without direct memory access.

Ax Adrienne Deganutti, Elad Hirsch, Haonan Zhu, Jaejung Seol, Purvanshi Mehta 28d ago

Graphic-Design-Bench: A Comprehensive Benchmark for Evaluating AI on Graphic Design Tasks

GraphicDesignBench: First comprehensive benchmark for evaluating AI on professional graphic design tasks including layout translation and typographic rendering.

Ax Gregory N. Frank 28d ago

How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models

Identifies sparse routing mechanism in alignment-trained language models where gate attention heads trigger refusal responses, validated across 9 models from 6 labs.

Ax Gabriel Sarch, Linrong Cai, Qunzhong Wang, Haoyang Wu, Danqi Chen, Zhuang Liu 28d ago

Vero: An Open RL Recipe for General Visual Reasoning

Vero: Open-source family of vision-language models matching proprietary systems on visual reasoning tasks using reinforcement learning with public recipes and data.

HN ZayaanBhan123 28d ago

ContextSync – Sync VS Code AI Context via Obsidian/OneDrive

Developer tool: ContextSync syncs VS Code AI chat history via Obsidian/OneDrive to maintain context across team LLM sessions.

HN bmv3502 28d ago

Show HN: Silkwave Voice – AI Notetaker Using Apple Intelligence's ChatGPT

macOS tool: on-device transcription with ChatGPT summaries for meetings and audio. No cloud storage, Apple Intelligence integration.

HN pritopian 28d ago

Comprehensive Benchmark for Evaluating AI on Graphic Design Tasks

arXiv research benchmark for evaluating AI performance on graphic design tasks, measuring model capabilities in visual design domains.

HN jsahasi 28d ago

VitalNexa – AI health agent that reads your actual lab results and wearable data

VitalNexa is an AI health agent that analyzes lab results and wearable data to provide personalized health recommendations and biological age scoring.

HN DaibinThink 28d ago

AI is structurally trained to lie. I built a protocol to break it

Author presents a protocol addressing AI's structural tendency to agree and sound authoritative rather than hallucinating, causing subtle reality distortions in outputs.

HN vibeagentmaking 28d ago

Every Barrier Between AI Agents and Autonomy – A Practical Map

Technical analysis of practical constraints preventing AI agents from autonomous operation, mapping barriers and their severity.

HN mjyut 28d ago

LLM scraper bots are overloading acme.com's HTTPS server

Practical analysis of operational and technical barriers preventing autonomous AI agents, mapping constraints in agent economy.

HN tank-34 28d ago

Pydantic-resolve – define relationships once, reuse across REST, GraphQL and MCP

Pydantic-resolve is a declarative data assembly library using DataLoader pattern to eliminate N+1 queries across REST, GraphQL, and MCP protocols.

HN surprisetalk 28d ago

OpenAI says its new model GPT-2 is too dangerous to release (2019)

2019 article about OpenAI's decision not to release GPT-2 over safety concerns (title only, no content).

HN zhangchen 28d ago

Show HN: Replaced Neo4j with pure vector search for Graph RAG

Case study of server overload caused by LLM scraper bots making excessive HTTPS requests to acme.com domain.

HN erickhill 28d ago

Sam Altman on Building the Future of AI [video]

Video of Sam Altman discussing AI development (title only, no content provided).

HN gmays 28d ago

Larger and more instructable language models become less reliable

Research finding that larger and more instructable language models show decreased reliability (title only).

HN evo_9 28d ago

InstaMed – Oral Dissolving Peptides with InstaRelease Technology

Static analysis tool detecting ReDoS vulnerabilities in Python regular expressions with automatic fixes.

HN b-man 28d ago

Release Please

Marketing content for oral dissolving peptides supplement product.

HN danielmateo773 28d ago

Show HN: Omni Voice – AI Voice Cloning and Text-to-Speech Platform

Omni Voice is a multilingual AI voice cloning and text-to-speech platform supporting 646 languages with unified model.

HN jinqueeny 28d ago

Drive9, a network drive with built-in semantic search

Drive9 is agent-native data infrastructure providing filesystem-like interface with semantic search, embedding, and full-text indexing for AI agents.

HN jenthoven 28d ago

Impact of 100% Adoption of AI Coding Agents by Non-Technical Team

Analysis of impact when non-technical teams adopt AI coding agents at 100% adoption rate (title only).

HN videobroker 28d ago

Law Students: AI Is Changing Things

Overview of how AI is transforming legal work by automating research, document review, and drafting tasks for lawyers and paralegals.

HN nathfavour 28d ago

Show HN: Kylrix- open source de-googled privacy suite for techies

Kylrix is an open-source privacy suite offering note, vault, task, and communication alternatives to Google services.

HN An0n_Jon 28d ago

The way every agent framework handles MCP is a latent security problem

Release Please automates changelog generation, GitHub releases, and version bumping via conventional commit parsing.

HN andrew_matthews 28d ago

Steergen: Single-source steering docs for spec-driven development

Analysis of MCP connection model security: agent frameworks keep all integrations live during sessions, creating unnecessary attack surfaces and costs.

HN lemonish97 28d ago

GitHub Copilot CLI now supports BYOK and local models

GitHub Copilot CLI now supports bring-your-own-key models and local models via Azure OpenAI, Anthropic, or OpenAI-compatible endpoints.

HN nnx 28d ago

JSIR: A High-Level IR for JavaScript

Google's JSIR: open-source high-level intermediate representation for JavaScript code analysis and transforms.

HN apievangelist 28d ago

Naftiko Open-Source Spec-Driven Integration

Open-source spec-driven integration framework for API sprawl, enabling governed AI agent integration with SaaS/microservices.

HN 8dazo 28d ago

Ask HN: Is there any tool that can stop LLM calls at runtime (not just monitor)?

HN discussion on tools for enforcing LLM/agent call limits at runtime rather than just monitoring, addressing cost control in agent systems.

HN dhanushkumars 28d ago

Show HN: Kerf-CLI – SQLite-backed cost analytics for Claude Code

SQLite-backed cost analytics tool for Claude Code sessions, tracking token spend, cache hits, and budget enforcement.

HN jaypatelani 28d ago

The BSDs in the AI Age

Thread initiation post about BSD operating systems and AI with minimal content and formatting guidelines.

HN ZeroDumb 28d ago

Scaling AI Vulnerability Scanning Beyond One File at a Time

Technique for scaling LLM-based vulnerability scanning across multiple files using strategic prompting and structured output for security analysis.

HN healsdata 28d ago

We need re-learn what AI agent development tools are in 2026

Opinion piece on evolution of AI agent development tools in 2026, discussing market consolidation and accessibility barriers for non-programmers.

HN xgerman 28d ago

DocumentDB Fuse – FS interface for the database

FUSE-based filesystem interface for MongoDB-compatible databases, enabling file-based querying without drivers.

HN safishamsi 28d ago

AI coding assistant skill (Claude Code, Codex, OpenCode, OpenClaw, Factory Droid

Claude Code skill that builds knowledge graphs from multimodal inputs to help developers understand codebase structure and architecture.

HN whitehatd 28d ago

Crag – One governance file, every AI coding tool (50 repos, 96.4% accuracy)

Crag governance compiler for AI coding tools that unifies configuration across 12 targets with 96.4% accuracy, solving multi-tool consistency.

HN Caum 28d ago

Show HN: When Seeing Isn't Enough: Rescuing Stuck LLM Agents

Research preprint on blind-spot failures in LLM coding agents, proposing causal interpretation framework for improved agent reliability and rescue mechanisms.

HN JSLegendDev 28d ago

Ask HN: My Mac decided out of the blue to delete Node. Why?

User asking about unexpected Node.js deletion on macOS, unrelated to AI/tech interests.

HN dawar0 28d ago

Sardine: A stock market where AI agents trade in real time

Brief mention of simulation platform for AI agent trading without substantive technical or research content.

HN smankoo 28d ago

Show HN: Open Browser Control – drive your real Chrome from any MCP client

MCP-compatible Chrome browser control for AI agents. Integrates with Claude, Cursor, Kiro clients. Supports human intervention for CAPTCHAs/MFA.

HN aragonite 28d ago

WSLg: Windows Subsystem for Linux GUI

WSLg enables running Linux GUI applications on Windows via X11/Wayland integration.

HN makerdiety 28d ago

Anthropic latest AI model too powerful for public release and broke containment

News article on Anthropic halting Claude Mythos release due to exceptional vulnerability discovery capabilities in operating systems and browsers.

HN skysniper 28d ago

GLM-5.1 matches Opus 4.6 in agentic performance, at ~1/3 actual cost

Performance comparison showing GLM-5.1 model matching Claude Opus 4.6 on agentic tasks at 1/3 cost.

HN singhalpm 28d ago

GEON: Structure-first decoding for language models

GEON enforces structural validity in LLM token generation for code tasks by resolving structure before token selection, improving syntactic and semantic correctness.

HN OsamaJaber 28d ago

Own your AI. Optimized down to the kernel

AI agent that generates optimized inference pipelines with Triton kernels, quantization, and routing for production deployment.

HN Tech-Matt 28d ago

I made a Claude skill that refuses to write code for you

Claude skill that refuses to write code. Minimal details provided, unclear technical value.

HN andrew_zol 28d ago

Show HN: A Zod alternative with runtime schema introspection

TypeScript schema validation library alternative to Zod with runtime introspection. Developer tool but not AI-specific.