Ask HN: LLM-Based Spam Filter
User asking if LLM-based spam filter software exists that integrates via IMAP for email classification.
User asking if LLM-based spam filter software exists that integrates via IMAP for email classification.
Ubik Studio: model-agnostic desktop research tool supporting local files, multi-hop tasks, step-by-step approval flows, and accurate citations.
Claude Code extension to enforce Unix style conventions in generated code.
Tutorial on building an AI image generation skill for Claude Code as a developer tool extension.
Guide on running Google Gemma 4 locally using LM Studio's headless CLI with Claude Code integration.
iPhone photo/video storage app with client-side encryption and custom cloud storage.
Workflow orchestration platform with code marketplace for building and sharing reusable workflow components.
Unified runtime for AI coding agents (Claude Code, Gemini, Codex) accessible across terminal, browser, Telegram, Feistel, Discord, WeChat.
Task runner with Terraform-inspired syntax for defining and executing tasks.
Lebanese humanitarian organizations use digital wallets for aid distribution to displaced populations.
HN discussion on impact of LLM scraping and AI on web accessibility for people with disabilities.
AI agents autonomously pay for API data using USDC micropayments via x402 protocol without requiring API keys.
Open-source toolkit for runtime security and governance of AI agents. Addresses safety in agent systems.
Overview of coding agent design, components, and how different pieces work together in LLM systems.
Open-source AI-powered website builder where users describe pages in plain language constrained by design system tokens.
YardSard inventory management tool for yard sales. Consumer app, not AI-related.
Claude-powered trading bot achieved $3.3M returns on Polymarket using arbitrage strategy. Application demo, limited technical depth.
Microsoft's Copilot terms state it's for entertainment only, contradicting marketing. Legal/policy piece.
Open source personal health management platform built with Elixir/Phoenix, tracks providers, appointments, medications locally.
Inference Arena benchmark comparing ML framework inference and training performance across PyTorch, Rust libraries, and others.
Identa CLI automates prompt calibration across local LLMs using transfer learning and evolutionary algorithms. Implements PromptBridge research.
Discussion post about LLM API frustrations from developers. Limited content provided.
Discussion about custom spinner verbs for Claude Code. Humorous HN discussion with minimal substance.
Jmux enables tmux-based development environment for parallel AI agent orchestration with Claude Code. Purpose-built developer tool for agents.
Autocrit automates UX prototyping and evaluation using AI-generated personas. LLM application for product development.
Guide for building internal AI tools with GPT-4 while meeting compliance requirements like GDPR and data processing agreements.
Investigation into Meta Ray-Ban glasses privacy concerns and data handling practices in Kenya.
Trinity-Large-Thinking: Apache 2.0 open-source frontier reasoning model for multi-turn tool calling and complex agent tasks. Released on Hugging Face.
Analysis of why LLMs are useful despite requiring verification. Discusses generation vs. verification performance delta.
Library for training custom Claude-like code models end-to-end using Constitutional AI approach on TPUs with JAX.
Local-first intelligence terminal with OSINT tools, encrypted communications, and built on local AI without cloud.
Management principle variation on Bezos's disagree-and-commit called raise-and-release.
Technical analysis of batch API design patterns and their drawbacks with practical examples.
Terminal UI performance monitor that consolidates multiple CLI monitoring tools into customizable interface.
Dropbox optimized relevance judgment system for search using DSPy, improving ranking and data generation pipelines.
Analysis of liability and responsibility when AI agents autonomously operate business functions. Feature on risk redistribution.
NPM package publishing tool that requires explicit review of tarball contents before publication.
Cabinet: open-source knowledge base + LLM integration tool supporting PDFs, CSVs, web apps. Runs locally via npm with Claude Code agents.
Claude Code skill that formats code review feedback as Rust compiler errors with severity codes and fixes.
Playful Claude skill that makes the model speak like Rocky. Low substance, mostly broken content.
Multi-agent AI pipeline using Claude to migrate 14K+ RSpec tests to Minitest. Technical case study on LLM-assisted code migration at scale.
Instructions for implementing Claude Pro support in OpenCode via AI agent. Appears to document a legal dispute workaround.
Analysis of why domain-specific LLMs haven't emerged as viable competitors to general models. Technical reasoning on LLM architecture trends.
Tool for bulk product photography and video generation. Minimal description, unclear technical details.
Developer built SQLite devtools in 3 months using AI assistance after 8 years of planning. Technical case study on AI-accelerated developer tool creation.
Andrej Karpathy X post on LLM knowledge bases. Minimal content provided, likely link-only post.
Weather visualization tool using space and color instead of numbers. Open source, unclear AI involvement in current form.
Military news unrelated to AI/tech.
Nvidia plans to use photonic interconnects to scale GPU systems to 1000+ GPUs by 2028, investing in optics companies.
CLI tool for free stock image search across Unsplash/Pexels without API keys. Designed for use by agents. Available via uv tool.