6h ago
Show HN: Firmion is a DSL for composing firmware images
Firmion is a Rust DSL for composing firmware images, managing memory layouts declaratively.
6h ago
Show HN: Enough, an Agent Harness for Writers
Enough is extensible personal language system with local models and OpenRouter support for planning, writing, and translation tasks.
7h ago
Show HN: Ktx – Open-source executable context layer for data agents
Ktx is open-source executable context layer for reliable data agents, addressing accuracy issues in SQL generation and warehouse interactions.
7h ago
Claude Code hook that plays a random sound on negative feedback
Claude Code hook that plays audio feedback sounds in response to negative user messages.
7h ago
SQLite Agents.md
Guidance documentation for AI agents working with SQLite codebase, covering public domain status and PR policies.
7h ago
Spotify CEO defends AI music, wants you to stop calling it 'slop'
Spotify CEO defends AI-generated music against criticism. Content appears to be malformed with timestamp list only.
7h ago
Show HN: My custom agent skill for commit messages
Custom Claude Code agent skill for enforcing conventional commit message format with validation hooks.
7h ago
Giving LLMs a Formal Reasoning Engine for Code Analysis
Research on enhancing LLM code analysis with formal reasoning engine for transitive code questions and dead code detection.
7h ago
Spread: A simple, fast spreadsheet viewer written in Rust using GPUI
Rust spreadsheet viewer built with GPUI, mostly AI-generated code. No editing support.
7h ago
Why Google's AI can't spell Google (or anything else)
Analysis of failures in Google's AI Overview demonstrating character counting and spelling errors in simple tasks.
7h ago
Wix laying off about 20% of its workforce. CEO cites AI, exchange rates
Wix announces 20% workforce reduction, citing rapid AI capabilities evolution and currency exchange challenges.
7h ago
The enterprise security risks of autonomous AI agents, and how to manage them
Analysis of enterprise security risks from autonomous AI agents with 66% benchmark accuracy increase, discusses control mechanisms.
7h ago
Show HN: Genesis Architect – scans 20 GitHub repos before scaffolding
Genesis Architect scans 15-20 GitHub repos to extract architecture patterns, bug issues, and security patches, then generates project scaffolds based on production data rather than templates.
8h ago
Creating got easier. Meaning got harder
Opinion piece on how AI-generated content proliferation made creation easier but quality assessment harder across media formats.
8h ago
WinMerge 2.16.56.2 – A Windows tool for visual difference display and merging
WinMerge 2.16.56.2 release notes with bugfixes for file diff and merge utility. Off-topic.
8h ago
Malware dev tries to steal Claude users secrets NPM slop, leaks own GitHub token
Analysis of AI-generated malware npm package targeting Claude users that leaked its own GitHub token via security misconfiguration.
8h ago
Show HN: Open-source alternative to Codex Chronicle, using Apple's local OCR
Familiar: open-source screen/clipboard capture tool using Apple's local OCR, providing context for AI agents via markdown output.
8h ago
Never Pay for Claude
rotom: local Rust gateway enabling Codex and Grok OAuth with OpenAI/Anthropic-compatible APIs, allowing use of alternative providers.
8h ago
Vc: SIMD Vector Classes for C++
Vc SIMD vector library for C++ now in maintenance mode, directing users to std::simd alternatives.
8h ago
Getting Agent-Ready with Symfony
Guide for making Symfony applications agent-ready with markdown negotiation, OpenAPI docs, and API exposure for AI agent integration.
8h ago
Show HN: Code Block Selector – select code by structure, not by dragging
VS Code extension for selecting code blocks by syntax structure rather than manual dragging, with AST-aware navigation.
8h ago
Claude Code Skills set for SEO research
SEO automation toolkit using NodeHub API and optional LLM for SERP analysis and cluster naming. Promotional package by Senuto.
9h ago
Deep humanistic context for every engineering decision
jensenify-mcp MCP server injecting literary works into AI-assisted engineering interactions. Promotional/novelty tool with unclear practical value.
13h ago
Taste Skill: An Anti-Slop Front End Framework for AI Agents
Taste Skill is a frontend framework for AI agents that improves UI quality beyond boilerplate. Includes image generation skills for design implementation.
13h ago
Netflix is building an AI animation studio
Netflix is building a generative AI animation studio to produce feature-quality content. Off-topic entertainment industry application.
13h ago
AI orientation before retrieval and action
AIluminode is a tool for AI systems to check contextual posture before retrieval and action. Content is fragmented and unclear about actual functionality.
13h ago
Released reminders-sync, bug fixes for neural web
Neovim plugin for syncing macOS Reminders and neural network utilities.
13h ago
Everyone's building AI agents that remember. I built one that has a body
Brief mention of building embodied AI agent with memory. Limited details provided.
13h ago
Show HN: I made samspov.com to easily track updates
Personal project tracking TikTok content about restaurant updates.
14h ago
When products think: navigating the AI product shift
Article about AI product development shifts. Title-only, no substantive content provided.
14h ago
A useful paper on the case for AI data centres in space [pdf]
Paper discussing AI data centers in space. Title-only submission, no content available.
14h ago
DiffusionBlocks: Training Neural Networks One Block at a Time
DiffusionBlocks proposes training neural networks block-by-block instead of end-to-end, reducing resource requirements for frontier models.
14h ago
Ax language: Compact source, build for agents
Programming language designed for extreme code compression and AI agent inspection. Emphasizes compact semantics for human and agent readability.
14h ago
Show HN: LaunchPact – get upvotes for your ProductHunt launch
Product Hunt launch coordination platform for mutual upvoting.
14h ago
Train 1T parameter LLM with 8 GPUs?
Orbit project enables training 1 trillion parameter LLMs on 8 GPUs. Link-only submission with minimal detail.
14h ago
Show HN: AI agents for UK GDAD PCF roles and their skills
Open source AI agents implementing UK Government Digital and Data Profession Capability Framework roles and skills as markdown specifications.
14h ago
The first framework that can post train DeepSeek V4-pro on a single-node?
Orbit framework enables reinforcement learning post-training of trillion-scale LLMs like DeepSeek V4 on single nodes. Opensourced project.
14h ago
Former Google and Apple Researchers Launch a Startup to Build AI's Missing Feed
Trajectory startup by former Google/Apple/OpenAI researchers builds platform for continuous AI improvement through real-world user interaction data.
15h ago
Optimizing Our ML Feature Store: Cutting Compute Costs
Blog post on optimizing ML feature store infrastructure, mentions 55% compute cost reduction. Redirect page with minimal content.
15h ago
Omniclip: Open-source, powerful video editor right in the browser
Open-source browser-based video editor with no cloud dependencies or accounts required.
15h ago
Halted ARM64 Port Work
Developer halts ARM64 porting work citing project disagreement over AI-assisted development.
16h ago
The fog is alive: bacteria in fog droplets clear toxins from air
Study on bacteria in fog droplets and air toxin removal. Biology research unrelated to AI/tech interests.
16h ago
Show HN: BetterCallClaude – Open Source AI Legal Agents for Italy
Open source AI legal agents for Italian law covering 20 regions. Specialized agents for contract review, legal research, document drafting. Italian privacy-compliant.
16h ago
MTerm
Native macOS terminal emulator, GPU-accelerated, pre-release status. Not an AI tool.
17h ago
NovaGPU – An open-source GPU architecture written in Verilog
Open-source GPU architecture in Verilog targeting FPGA prototyping. Early stage, 34% testbench passing, not yet on physical hardware.
17h ago
Ask HN: How Much a Difference Does an LLM's Corpus Make?
Discussion on how training data composition affects LLM performance on domain-specific tasks like scientific reasoning.
17h ago
Clojure → YAMLScript transpiler: using LLMs for normalization, SCI for execution
Clojure to YAMLScript transpiler using LLMs for code normalization and SCI for deterministic execution. Hybrid compilation approach leveraging LLM strengths.
17h ago
JAL to launch Moon payload service, aims to preserve heritage
Japan Airlines launching Moon payload service for cultural heritage items. Space industry news unrelated to AI/tech interests.
17h ago
Amdahl's law for AI agents
Analysis of multi-agent systems achieving throughput gains. Discusses patterns in autonomous coding agents, concurrent agent orchestration, and practical scaling insights.
18h ago
When pre-training hurts LoRA fine-tuning: a dynamical analysis via single-index models
Mathematical analysis showing excessive pre-training can slow LoRA fine-tuning optimization, studied via single-index models.