HN Olshansky 11h ago

Core views on AI safety (March 2023)

Anthropic's 2023 statement on AI safety risks and impact, discussing concerns about powerful AI development in coming decade.

HN benswerd 11h ago

X for AI Agents

Minimal stub post with no content.

HN ninjagoo 11h ago

The race to train AI robots

Article on training AI robots to understand physical movement through human trainers in India and global industrial settings.

HN AISupportTeam 11h ago

I built a tool that checks if AI recommends your brand when buyers ask questions

Tool testing brand visibility across ChatGPT, Gemini, Claude, and other LLMs when users ask buying questions, with competitive analysis.

HN grimm8000 12h ago

Show HN: The AI agent that can improve itself

GrimmBot: Autonomous AI agent in sandboxed Docker with desktop/browser control, self-improvement capability, and tool building.

HN benmora 12h ago

Show HN:Lumisift – improves data retention in RAG from ~40% to 87%

Lumisift: Open-source tool improving data retention in RAG pipelines from 40% to 87% by fixing retrieval accuracy for scientific documents.

HN idid 12h ago

Generate tool-specific AI config files from shared templates

CLI tool generating AI configuration files for Claude Code, GitHub Copilot, and Cursor from unified templates.

HN xngbuilds 12h ago

LLM-Wiki

LLM-Wiki: Obsidian-based persistent agent memory system with searchable indexed documents, inspired by Andrej Karpathy's concept.

HN ethanwillis 12h ago

Y Combinator lets you cross the line [video]

Minimal stub post with no content.

HN ziyasal 12h ago

Agentjail: Minimal Linux sandbox for running untrusted code/apps/agents

Agentjail: Minimal Linux sandbox for running untrusted AI agent code, with DNS filtering and optional GPU passthrough support.

HN paulpauper 12h ago

Nailing Jell-O to the Wall, Again. Can China Contain LLMs?

Incomplete article fragment on LLM regulation in China.

HN spotlayn 12h ago

Show HN: I built a project board where AI agents join as real teammates

is.team: AI-native project management platform with built-in AI agents as teammates, workflow automation, and external agent integration.

HN aweussom 13h ago

Can you self-host AI on Intel NPU or ARC (iGFX and proper card?

Local LLM server supporting Intel NPU and ARC GPUs with OpenAI/Ollama-compatible APIs, auto-detecting hardware.

HN HemeshCh 13h ago

Show HN: A proactive AI agent on iMessage that texts you before you even ask

Proactive AI agent on iMessage with 135+ tools that anticipates user needs by integrating email, calendar, and other services.

HN bumpa 13h ago

Show HN: Revdiff – TUI diff reviewer with inline annotations for AI agents

TUI diff viewer tool designed for AI agents to review code changes inline with annotations, enabling feedback loops without leaving terminal.

HN themaxdavitt 13h ago

Let-Fate-Decide

Claude Code skill using cryptographic randomness and Tarot cards to resolve ambiguous planning decisions through entropy injection.

HN kevinlu 13h ago

Ask HN: What are your favorite AI agents?

HN discussion thread asking users about their favorite AI agents and reasons for preference.

HN amr_shawky 13h ago

Show HN: PicPocket – Efficient photo storage/sharing without AI

Minimal stub post about photo storage without AI.

HN ashmil 13h ago

Ask HN: We built cloud ops AI 3 years ago. Are managed agents a death sentence?

Startup built cloud ops AI agent 3 years ago enabling plain English queries across AWS, GCP, observability tools; concerns about competition from managed agents.

HN aiola 13h ago

Show HN: Specsight – Living product specs generated from your codebase

Specsight: Tool auto-generating living product documentation from codebase to reduce knowledge gaps and interruptions.

HN fathomlab 13h ago

Styxx – Reads an LLM's cognitive state from token probabilities

Styxx: Python package providing real-time monitoring of LLM agent cognitive states through token probability analysis and reasoning detection.

HN pseudolus 13h ago

Microsoft exec suggests AI agents will need to buy software licenses

Microsoft executive suggests AI agents may need software licenses; discusses industry response to AI threats from Salesforce and others.

HN preyneyv 13h ago

We're Learning Backwards: LLMs build intelligence in reverse

Essay exploring whether LLM failures stem from fundamental architectural issues or insufficient scale, discussing scene completion examples.

HN gsteinacker 13h ago

Kingman's Formula: Why Variability Kills Performance Before Capacity Does

Analysis of how variability in system load affects performance before capacity becomes a bottleneck, using Kingman's Formula.

HN MO-379 13h ago

Show HN: I Created an LLM Harness for Language Learning

Incomplete snippet about creating an LLM harness for language learning.

HN taubek 13h ago

WordPress 7.0: The Good, the AI, and the Still Missing

Review of WordPress 7.0 release delayed due to real-time collaboration data storage issues, noting underreported useful features.

HN krumboy 13h ago

Kon – A tiny coding harness

Kon is a minimal terminal coding agent with a 270-token core prompt, 6 default tools, and layered project-specific context for extensibility.

HN kemyd 14h ago

WordPress AI Theme Builder

Collection of AI-powered web editors for WordPress theme building, Tailwind CSS, Bootstrap, and design tools.

HN angarrido 14h ago

How HN: AndesCode – local AI coding assistant that runs offline

AndesCode: local offline AI coding assistant running Gemma 4 26B that indexes codebases and answers questions without data leaving machine.

HN jruohonen 14h ago

Introducing Project Glasswing

Project Glasswing: analysis of how advanced AI models discovered in late 2025 excelled at identifying zero-day software vulnerabilities.

HN djyde 14h ago

Show HN: Give your AI agent a preview link for files and diff

Diff4: tool converting AI agent file changes into shareable encrypted web preview links, compatible with OpenClaw and Hermes agents.

HN steveharing1 14h ago

Bouncer: Block "crypto", "rage politics", and more from your X feed using AI

Browser extension using AI to filter Twitter/X feed by user-defined topics like crypto and rage politics with local model caching.

HN nazanki 14h ago

AI Didn't Teach Me to Code but It Changed How I Build

Personal account of how AI coding assistants changed development workflow and pace, shifting from manual linear processes to iterative exploration.

HN 1395291968 15h ago

Show HN: Project Parliament – a multi-model workflow for choosing OSS ideas

Multi-model workflow system for evaluating and selecting open source project ideas.

HN anaspro 15h ago

Mugib – AI agents that work across every channel–chat, voice, web, and live data

Mugib platform for deploying AI agents across multiple communication channels including chat, voice, web, and real-time data sources.

HN BuleBule 15h ago

Show HN: The cutest WhatsApp concierge for dog friendly travel

Pet-travel application using WhatsApp as interface with verified dataset of 58,000 dog-friendly venues across 56 countries.

HN harshdoesdev 15h ago

Show HN: Run AI coding agents in real sandboxes, not Git worktrees

SuperHQ tool for running coding agents in isolated sandbox environments using microVMs, enabling parallel multi-agent execution without system risk.

HN ColinWright 15h ago

Who Uses AI?

Discussion of who uses LLM AIs and personality types associated with adoption, referencing critiques from David Gerard's blog.

HN EvgeniyZh 15h ago

Training LLMs to Predict World Events

Technical deep dive on training LLMs for event forecasting using Tinker, combining multiple approaches to achieve superforecaster-level accuracy on geopolitical predictions.

HN young_mete 15h ago

Show HN: PDF-Proof – Make Claude show where it found each value in a PDF

Tool for Claude to show source locations in PDFs when extracting values, enabling verification.

HN florianleibert 15h ago

Nvidia's moat is not what it used to be

CUDA's dominance eroding as AI models generate low-level code (kernels, bindings) efficiently, reducing lock-in costs and enabling easier hardware switching.

HN gmays 15h ago

Sol-RL: FP4 Explore, BF16 Train

Reinforcement learning approach using FP4 for exploration and BF16 for training.

HN mvac 16h ago

SuperCmd – Open-source launcher for macOS with Raycast-compatible extensions

Open-source macOS launcher supporting Raycast-compatible extensions.

HN simonenespolo 16h ago

Test your CV against any job description – free, open-source, AI-powered

Open-source resume evaluation tool using LLM system prompts to match CVs against job descriptions.

HN cashbackoz 16h ago

Building the first AI Red Team OS – mythosai.cloud – early access open

MythosAI announces early access to red team operating system for AI security testing.

HN kilroy123 16h ago

Show HN: Millions of websites crawled for LLMs to rebuild the pricing pages

Dataset project crawling millions of pricing pages and benchmarking ~50 LLMs on their ability to reconstruct pricing page structure.

HN ptrhvns 16h ago

Suno, AI Music, and the Bad Future [video]

Opinion video on Suno AI music generation and societal implications.

HN kuberwastaken 16h ago

Show HN: Agent-Notifications – Real-Time Alerts for OpenClaw and Hermes Agents

Notification system for AI agents enabling event-driven alerts via cron jobs without token waste.

HN maksyyy 16h ago

Claude Code Checkpoints

Stub entry with minimal information.

HN binyu 16h ago

AI and Psi with Paul Werbos (Inventor of Backpropagation) [video]

Video interview with Paul Werbos (backpropagation inventor) on AI and parapsychology.