Buy A Modem

High Five Best Friends GIF by Diary of a Wimpy Kid

Show HN: Musefs – organize and tag music without touching the original files

musefs is a virtual filesystem for organizing and tagging your music without altering or duplicating the backing audio files. It scans your library to build up a SQLite db with all the original tags and embedded art and makes note of exactly where in the file the actual audio is. That db becomes the source of truth for the FUSE filesystem. At playback it generates new metadata for the files on the fly from the tags in the db and splices it onto the original backing audio.I have a music collectio

Ask HN: What happens when AI-voice becomes good enough?

I fell into the rabbit hole of TTS models lately. Tried all major paid tools (ElevenLabs/InWorld/etc.), and all the newest open-source models.I started asking myself: what happens when the voice is "solved"? E.g. it gets impossible to distinguish it from a human. Wanted to hear your opinions!Sketched some of my own thoughts, and I see two futures:Future 1: the nuanced versionAudiobooks: I think established authors will still prefer human narrators. If you can afford a $3k–$4k

I indexed 669 GB of my GoPro videos using my M1 Max computer and local ML models

TLDR: I had 2,207 GoPro videos, and I need to rewatch them to find interesting moments from my cycling journey. I built a project to index them locally on my M1 Max using open-source ML models, search for those moments, and send the best clips straight to my DaVinci Resolve timeline. I indexed 628 videos (668.68 GB, 15h 13m 18s of footage duration), more details in the metrics table in the last section of this article.Full article: https://iliashaddad.com/blog/i-indexed-669-

Launch HN: Adam (YC W25) – Open-Source AI CAD

Hey HN! I'm Zach from Adam (https://adam.new/). We're building AI agents for mechanical CAD software. We’ve built the company on two fundamental beliefs:- AI will be the primary medium for creating mechanical designs just like it is in software today.- The best paradigm for CAD generation is to generate CAD as code (text -> code -> CAD).We’re building CADAM, an open source Text to CAD platform. It's a React app (TanStack Start) with a Supabase backend for auth

Ask HN: What has been bothering you lately?

Vent out. Maybe one of us will find a fix.<p>I'm mad that economic policies in France aren't based on what models say is best next action but on elections. Democracy really sucks.<p>I'm also very annoyed that models are censoring stuff without even clarifying what's wrong with the prompt.<p>I don't like that content distribution is still mostly owned by a few platforms. Something is deeply odd with that.

Ask HN: Whats the best and small open source model?

I'm building a project for my company and they want to use a local model (100b max size).<p>I think i tried all the models, the problem is that do not give a good answer even tho i gave them everything they need in terms of context to tackle any question.

Show HN: We cut >60% of tokens from agentic tasks by removing repeated context

Every agentic system I see has the same hidden tax: the model keeps rereading the same context.Tickets, Slack threads, docs, customer history, database notes, runbooks, logs, prior decisions. You can cache static prefixes, route to cheaper models, or set team budgets, but none of those fixes the underlying behavior: agents start most tasks trying to re-explore everything.We built Parcle as a shared memory layer for AI agents. It ingests operational context, indexes what happened, and lets agents

Show HN: Attagram, a tiny printer that gives kids a magical daily digest

I’m building Attagram: a small printer that lives in the kitchen and prints a daily paper digest for kids.The idea came from an emerging family dynamic I kept noticing. My daughters (A, 9 and J, 8) are becoming increasingly independent, but as parents, we hold an enormous amount of invisible state in our heads and phones: what day a project is due, who needs cleats, what's for lunch, which kid has library day, what chores need to happen before screens, how many days until the camping trip,

Ask HN: How much do you trust LLMs with your health questions?

As software engineers, we've definitely seen the best use case for LLMs so far. Coding agents have shown us what these models can do in an area we can actually verify. But lately I've found myself comparing my doctor's notes against LLM answers more and more. Curious how others are using LLMs, and relying on them, for non-engineering stuff.

Launch HN: Drafted (YC P26) – Models for residential architecture

I’m Nick, founder of Drafted (https://www.drafted.ai). We’re training models that generate residential architecture from structured design constraints.Product demo: https://www.youtube.com/watch?v=8QkJ7jNU9y4Residential architecture is still one of the most expensive, slow, and inaccessible creative processes in the world. Designing a custom home typically costs $10,000–$50,000 or more, takes months, and requires making major decisions before most people can even visuali

Show HN: HashMeterAi – Private AI Token Real Usage Meter for All Models

The honest, local-first usage meter for AI coding tools. Claude Code, Codex, Kimi, Qwen CLI, HashCortx, HashCerebrum — unified into one clean dashboard with usage based trophies :)

Show HN: Ghostty in-browser with real client-side back end

A real work in progress I've got here. Our good friend Ghostty is now haunting the browser.Ghostty Playground is an experimental project based on ghostty-web. It includes the full Ghostty terminal with configs, like themes and keybinds (config panel is based on zerebos' ghostty-config).It runs a real Linux-like backend directly in the browser via BrowserPod with a dedicated filesystem, port-listening, bash, git, node.js, npm etc.It includes the ability to download small AI models via H

How Qualcomm Cashes In On The $600 Billion AI Binge

Qualcomm (QCOM) is one of the most important companies in mobile computing. Its processors and cellular modems power billions of smartphones worldwide, while its licensing business generates high-margin royalty revenue from essential wireless patents. The company has also expanded its tech into automobiles, virtual reality headsets, and AI PCs.