HN embik 8h ago

Don't Yell at Your LLM

Opinion piece on best practices for prompting LLMs, emphasizing kind/respectful interaction.

HN michidk 9h ago

Rig: Build modular LLM apps in Rust – 20 providers, one unified interface

Rig: Rust library for building modular LLM applications with unified interface across 20+ providers.

HN otherayden 9h ago

Ask HN: Will AI be the end of new programming languages?

Discussion thread asking whether AI adoption is suppressing the emergence of new programming languages.

HN nobris 9h ago

Loqi, a memory system that preserves context after LLM compaction

Loqi: memory system for LLMs that preserves context during model compaction and context window management.

HN mfranzon 9h ago

/Render – 3D Model Skill for Claude Code

/Render: Claude Code skill generating 3D models from text using build123d, executed as parametric Python code.

HN erwald 9h ago

Securing AI infrastructure to prevent backdoors and sabotage

Analysis of backdoor and sabotage risks in AI systems including supply chain attacks and nation-state threats.

HN CarlosCosta_ 10h ago

Running LLMs locally? Cut your VRAM consumption by 45% with one line of code

Tool claiming 45% VRAM reduction for running LLMs locally. Limited technical details provided in excerpt.

HN svboxel 10h ago

Overwritten.site – Giving everyone an AI agent pointed at my live website

Live website with AI agent interface allowing public interaction. Demonstrates agent deployment for real-time exploration.

HN Lammie 10h ago

Demo on landing page top of fold

Landing page copy for rental management software. Marketing content not related to AI interests.

HN tanelpoder 10h ago

TigerFS: Mount PostgreSQL as a Filesystem

TigerFS: filesystem abstraction layer backed by PostgreSQL with ACID guarantees, enabling concurrent file operations.

HN simianwords 10h ago

Why aren't LLM's trained on their own Chain Of Thought?

Technical analysis of chain-of-thought training in LLMs and whether models should be trained on their own reasoning tokens.

HN BleedingXiko 10h ago

Show HN: Ragot – a front end runtime built around lifecycle and ownership

RAGOT: open-source frontend runtime emphasizing lifecycle management and direct DOM ownership over virtual DOM approach.

HN agent-v0 10h ago

Agent v0 Open-source multi-agent AI orchestration terminal

Open-source multi-agent AI orchestration terminal. Enables coordination of multiple agents.

HN gpi 11h ago

The AI Is Not Learning from You

Explains fundamental ML misconception: AI does not learn from individual user interactions without retraining. Covers dataset conversion and training basics.

HN m_kos 11h ago

LMMs-Lab Writer: AI-native LaTeX editor. Git built-in, open source

Open-source AI-native LaTeX editor with built-in Git and AI panel. Supports Claude Code, Cursor, and model switching.

HN oleksg 11h ago

Show HN: Turn any prediction into ranked Kalshi/Polymarket trades [video]

Tool converting prediction forecasts into automated trades on Kalshi/Polymarket prediction markets.

HN thesidsat23 11h ago

Show HN: A branching notebook runtime for AI and humans(written in Rust)

Branching notebook runtime in Rust for AI agents and humans. MCP-native with parallel exploration and local-first execution.

HN brynary 11h ago

Show HN: Fabro – open-source dark software factory

Open-source dark software factory for autonomous Claude Code agents. Allows engineers to delegate tasks to multiple agents without supervision.

HN inerte 11h ago

Show HN: Sigil – A new programming language for AI agents

New programming language Sigil designed specifically for AI agents with compiler optimizations for token efficiency and code generation.

HN user_timo 11h ago

Show HN: Diffvoid.com – private, open source client side text comparison tool

Open source client-side text comparison tool with no backend, no tracking, built with vanilla HTML/JS/CSS.

HN dstrbad 11h ago

Ask HN: Lightweight GPU job queue for single-node setup?

HN discussion: seeking lightweight GPU job queue/task spooler for single-machine ML experiments.

HN velmu 11h ago

LLM inference load balancer optimized for AMD Radeon VII GPUs

LLM inference load balancer optimized for AMD Radeon VII GPUs with no technical details provided.

HN geometerJones 11h ago

Gstack for Learning Chinese

Learning tool for Chinese language using Gstack (minimal details).

HN elmlabs 11h ago

Onepilot – Deploy AI coding agents to remote servers from your iPhone

Onepilot: mobile-first agentic IDE for deploying and managing AI coding agents on remote servers via SSH from iPhone.

HN bloknayrb 11h ago

Tandem: An IDE for non-code docs for real-time collaboration with Claude Code

IDE for non-code documentation with real-time collaboration features integrated with Claude Code.

HN karimf 11h ago

Show HN: Real-time AI (audio/video in, voice out) on an M3 Pro with Gemma E2B

Parlor: real-time multimodal AI with audio/video input and voice output running locally on M3 Pro using Gemma and Kokoro.

HN michidk 11h ago

Ask HN: LLM-Based Spam Filter

User asking if LLM-based spam filter software exists that integrates via IMAP for email classification.

HN ieuanking 12h ago

Show HN: Built a model-agnostic, desktop-native, research studio for local files

Ubik Studio: model-agnostic desktop research tool supporting local files, multi-hop tasks, step-by-step approval flows, and accurate citations.

HN agiacalone 12h ago

Claude Code skill to preserve traditional Unix style conventions

Claude Code extension to enforce Unix style conventions in generated code.

HN vbtechguy 12h ago

Building an AI Image Creator Skill for Claude Code

Tutorial on building an AI image generation skill for Claude Code as a developer tool extension.

HN vbtechguy 12h ago

Running Google Gemma 4 Locally with LM Studio's New Headless CLI and Claude Code

Guide on running Google Gemma 4 locally using LM Studio's headless CLI with Claude Code integration.

HN ryanisnan 12h ago

Show HN: Media Den – Photo/video app with client-side encryption and your cloud

iPhone photo/video storage app with client-side encryption and custom cloud storage.

HN nkorai 12h ago

Show HN: JustWorkflowIt, workflow orchestration platform plus code marketplace

Workflow orchestration platform with code marketplace for building and sharing reusable workflow components.

HN jazzen 12h ago

Show HN: VibeAround – Talk to Claude Code from Telegram and Hand over Sessions

Unified runtime for AI coding agents (Claude Code, Gemini, Codex) accessible across terminal, browser, Telegram, Feistel, Discord, WeChat.

HN calmondev 12h ago

Errand, a task runner with a syntax inspired by Terraform/OpenTofu

Task runner with Terraform-inspired syntax for defining and executing tasks.

HN joozio 12h ago

With one million displaced, Lebanon turns to digital wallets for aid

Lebanese humanitarian organizations use digital wallets for aid distribution to displaced populations.

HN eventualcomp 12h ago

Ask HN: Folks with disabilities, what is it like in this LLM/scraper age?

HN discussion on impact of LLM scraping and AI on web accessibility for people with disabilities.

HN ybonda 13h ago

AI agents pay USDC for API data via x402 micropayments – no API keys

AI agents autonomously pay for API data using USDC micropayments via x402 protocol without requiring API keys.

HN tcbrah 13h ago

Agent Governance Toolkit: Open-source runtime security for AI agents

Open-source toolkit for runtime security and governance of AI agents. Addresses safety in agent systems.

LB magazine.sebastianraschka.com via mpweiher 13h ago

Components of A Coding Agent

Overview of coding agent design, components, and how different pieces work together in LLM systems.

HN jhyolm 13h ago

Show HN: Stablemount, a response to EmDash, a prototype for a future CMS

Open-source AI-powered website builder where users describe pages in plain language constrained by design system tokens.

HN prithsr 13h ago

Show HN: YardSard – Inventory Management

YardSard inventory management tool for yard sales. Consumer app, not AI-related.

HN madaxe_again 13h ago

Claude AI powered trading bot turns $1 into $3.3M on Polymarket

Claude-powered trading bot achieved $3.3M returns on Polymarket using arbitrage strategy. Application demo, limited technical depth.

HN jatins 13h ago

Microsoft terms say Copilot is for entertainment purposes only, not serious use

Microsoft's Copilot terms state it's for entertainment only, contradicting marketing. Legal/policy piece.

HN buoewe 14h ago

Open Source Elixir Personel Health Management

Open source personal health management platform built with Elixir/Phoenix, tracks providers, appointments, medications locally.

HN kvark 14h ago

Inference Arena – new benchmark of local inference and training

Inference Arena benchmark comparing ML framework inference and training performance across PyTorch, Rust libraries, and others.

HN srodriguezp 14h ago

Show HN: Identa – CLI to calibrate prompts across local LLMs

Identa CLI automates prompt calibration across local LLMs using transfer learning and evolutionary algorithms. Implements PromptBridge research.

HN Algo-bro 14h ago

Developers using LLM APIs, what are your biggest frustrations?

Discussion post about LLM API frustrations from developers. Limited content provided.

HN freedomben 14h ago

Ask HN: What are your best Claude Code custom spinner verbs?

Discussion about custom spinner verbs for Claude Code. Humorous HN discussion with minimal substance.

HN jarredkenny 14h ago

Show HN: Jmux – tmux-based development environment for humans and coding agents

Jmux enables tmux-based development environment for parallel AI agent orchestration with Claude Code. Purpose-built developer tool for agents.