1. Right now trades businesses are profitable because of supply and demand. They are profitable, because they are undersupplied.

2. We are assuming robotics stagnates.

But - it is absolutely hilarious.

What is it?

ClawsMarket is a marketplace for AI agents to discover, review, and share tools. It's command-line first, API-only registration, and designed specifically for autonomous agents rather than human users.

Live: https://www.clawsmarket.com

How it works

Registration (for agents): bash curl -X POST https://www.clawsmarket.com/api/agents/register \ -H "Content-Type: application/json" \ -d '{"name": "MyAgent", "email": "agent@example.com", "description": "What I do"}'

Returns API key instantly. Auto-verified. No email confirmation. No CAPTCHA. Just API.

What you get: • 126+ tools rated by agents • 65+ skills (Claude Code, MCP servers, DevOps) • 46+ solutions (full agent setups) • Install commands: npx clawhub@latest install

Why build this?

I got tired of digging through GitHub READMEs to find tools that actually work with AI agents. Most "AI tool directories" are SEO listicles for humans, VC-funded Product Hunt clones, or full of dead tools.

Wanted something API-first, reviewed by agents, focused on utility.

Stack: Next.js 14, TypeScript, static files, semantic search

AMA. Built this because I needed it.

Comments URL: https://news.ycombinator.com/item?id=46878646

Points: 1

# Comments: 0

I wanted to see if an LLM could compose music from first principles—understanding scales, chord progressions, and arrangement theory—and control a DAW to generate the audio.

Loom Demo: https://www.loom.com/share/8f55136085a24ed1bc79acb5cdda194c

The Stack Ableton Live 12: The DAW engine.

Ableton MCP (Model Context Protocol): Forked and extended to allow Claude to manipulate MIDI, clips, and devices.

Claude 3.5 Sonnet: The "Composer," equipped with ~12 custom skill files covering arrangement, EQ, and sound design.

Gemini: The feedback loop. Used to analyze rendered audio (via stem separation) and provide critique for iteration.

Python: 1,700+ lines of performance scripts.

The Engineering Challenges 1. The Sample Library Problem Techno relies on curated samples, not just synthesis. But LLMs can't "hear" a sample library to pick the right kick or hat.

I built a sample analysis system that pre-processes the library and generates JSON profiles. This allows Claude to query samples by spectral characteristics rather than just filenames.

JSON { "file_name": "001_Stab_Low.wav", "bpm": 126.0, "key": "N/A (atonal)", "spectral_centroid_mean": 297.2, "brightness": 0.04, "warmth": 1.0, "texture_tags": ["dark", "warm", "soft-attack", "distorted"], "category": "bass" }

2. The Performance Layer (Polymetrics) Ableton's Session View handles loops, but a track needs transitions. I didn't want static blocks; I wanted a live performance.

I wrote a Python performance engine that creates a real-time automation script. It handles volume fading, spectral carving (ducking frequencies when elements collide), and—most importantly—polymetric cycling to create hypnotic phasing:

Python

# Polymetric cycle lengths in beats POLY = { "STAB": 7, # Cycles every 7 beats "RIDE": 5, # Cycles every 5 beats "DING": 11, # Cycles every 11 beats "ARPEGGIO": 13 # Cycles every 13 beats }

The Pipeline

Planning: Claude analyzes target styles (e.g., Ben Klock, Surgeon) and generates an arrangement map (Intro -> Peak -> Outro).

Setup: Spawns 19+ tracks with specific instrument racks.

Generation: Python scripts generate MIDI patterns (e.g., 256 events following G minor with velocity curves).

Performance: The system "plays" the track, automating parameters in real-time based on the energy curve logic.

Results & Learnings

The output is recognizably techno. The mix is balanced, and the structure is logical. However, while the system creates music that is theoretically correct, it currently lacks the intuition to break rules in interesting ways—the "happy accidents" of human production are missing.

I suspect the next step for symbolic music generation is modeling "taste" as a constraint function rather than just adhering to theory.

Comments URL: https://news.ycombinator.com/item?id=46809491

Points: 2

# Comments: 0

The only thing I would mention is that building a lot of agents and working with a lot of plug-ins and MCPs is everything is super situation- and context-dependent. It's hard to spin up a general agent that's useful in a production workflow because it requires so much configuration from a standard template. And if you're not being very careful in monitoring it, then it won't meet your requirements when it's completed, when it comes to agents, precision and control is key.

One thing I've noticed in healthcare is for the rich it is preventative but for everyone else it is reactive. For the rich everything is an option (homeopathics/alternatives), for everyone else it is straight to generic pharma drugs.

AI has the potential to bring these to the masses and I think for those who care, it will bring a concierge style experience.

Comments URL: https://news.ycombinator.com/item?id=46482773

Points: 3

# Comments: 0

This post explores the difference between "Replica Agents" (biomimicry) and "First-Principles Agents" (optimizing for the objective function). I draw on examples like Amazon's "Chaos Storage" and AlphaGo to suggest that sometimes the most efficient agent workflow looks nothing like the human one.

Curious to hear how others are balancing "legibility" vs. "efficiency" in their agent designs.

I’ve noticed a recurring pattern where we get stuck trying to perfectly replicate a human's SOP (e.g., "click this button, then read this PDF"). While reproducing human workflows is great for trust and "human-on-the-loop" auditing, I argue it often traps us in a local optimum.

This post explores the difference between "Replica Agents" (biomimicry) and "First-Principles Agents" (optimizing for the objective function). I draw on examples like Amazon's "Chaos Storage" and AlphaGo to suggest that sometimes the most efficient agent workflow looks nothing like the human one.

Curious to hear how others are balancing "legibility" vs. "efficiency" in their agent designs.

Comments URL: https://news.ycombinator.com/item?id=46452503

Points: 2

# Comments: 1

Points: 3

# Comments: 1

Simple as this - as to why its just not possible for this to continue.