HN themaxdavitt 4d ago

Let-Fate-Decide

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

HN kevinlu 4d 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 4d ago

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

Minimal stub post about photo storage without AI.

HN ashmil 4d 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 4d 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 4d 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 4d 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 4d 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 4d 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 4d ago

Show HN: I Created an LLM Harness for Language Learning

Incomplete snippet about creating an LLM harness for language learning.

HN taubek 4d 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 4d 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 4d ago

WordPress AI Theme Builder

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

HN angarrido 4d 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 4d 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 4d 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 4d 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 4d 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 4d 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 4d 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 4d 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 4d 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 4d 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 4d 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 4d 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 4d 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 4d ago

Sol-RL: FP4 Explore, BF16 Train

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

HN mvac 4d ago

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

Open-source macOS launcher supporting Raycast-compatible extensions.

HN simonenespolo 4d 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 4d 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 4d 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 4d ago

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

Opinion video on Suno AI music generation and societal implications.

HN kuberwastaken 4d 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 4d ago

Claude Code Checkpoints

Stub entry with minimal information.

HN binyu 4d ago

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

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

HN markhan-nping 4d ago

Show HN: NeZha – An Open-Source Agentic Development Environment (ADE)

NeZha: Open-source agentic development environment for running multiple AI coding agents in parallel across projects using Claude, Codex, Git.

HN btables 4d ago

LLMs don't want pixels, they want tools

Brief title-only post discussing LLM preference for tool interfaces over pixel-based inputs.

HN willm 4d ago

A full-featured terminal user interface for hledger plain-text accounting

Terminal UI for hledger accounting software.

HN Imustaskforhelp 4d ago

Ask HN: What are all the bad things that AI companies have done which we forgot

Hackernews thread proposing website documenting AI companies' negative actions and failures.

HN devinabox 4d ago

Ask HN: Is Zero Trust Architecture Overkill?

Discussion of Zero Trust Architecture security for Dev In A Box, an AI-powered debugging/security vulnerability detection tool (~70% accuracy).

HN yamafaktory 4d ago

Show HN: Formal – Formal verification for AI-generated code using Lean 4

Formal: Tool for mathematically verifying AI-generated code correctness using Lean 4 theorem proving, works with any LLM backend.

HN Mohd_Umar 4d ago

Ask HN: What is the best way to get your first users?

Generic discussion thread about user acquisition strategies with minimal content.

HN cathy246 4d ago

HappyHorse AI Video Generator

HappyHorse: Cinematic AI video generator with improved motion quality, prompt adherence, and scene consistency.

HN arthur-G 4d ago

LRTS – Regression testing for LLM prompts (open source, local-first)

LRTS is an open-source, local-first tool for regression testing of LLM prompts to ensure consistent behavior across model updates.

HN kev_earth 4d ago

AI builds anything. I Claude-coded tasteID so every AI tool just knows

tasteID: Open-source tool capturing personal design fingerprint across 23 dimensions, portable to any AI tool, privacy-focused.

HN darccio 4d ago

World Socialist Web Site to Launch Socialism AI (2025)

World Socialist Web Site announces Socialism AI project in 2025.

HN Brajeshwar 4d ago

Over 4,732 Messages, He Fell in Love with an AI Chatbot. Now He's Dead

Clickbait headline about person's relationship with AI chatbot.

HN genphy1976 4d ago

OpenAI's vision for AI economy: public wealth funds, robot taxes, 4-day workweek

OpenAI policy proposals on managing AI economy through public wealth funds, robot taxes, and social safety nets.

HN ayhanfuat 4d ago

Agentsview: A local-first desktop and web app for browsing AI agent sessions

Local-first desktop/web app for browsing and analyzing AI agent coding sessions. Supports Claude Code, Codex, OpenCode and 11 other agents. Open source with GitHub releases.

HN dudleyspence 4d ago

Show HN: Chunk – macOS menu bar time-blocking app with Claude AI integration

Native macOS menu bar app for time-blocking with Claude AI integration, Google Calendar/Outlook sync, and drag-to-create scheduling interface.