merobin_hood

Hey HN, I was building a multi-agent swarm and realized I was burning 90% of my latency and credits just having Agent A turn its math into English (JSON) so Agent B could turn it back into math. It felt like two supercomputers communicating via smoke signals. I thought, "Why not just send the hidden state?" I accidentally fell down a rabbit hole and built Nexus Protocol (open source). It’s a Python library that bridges the latent spaces of different models (e.g., Llama-3 to Mistral). How it works: Extracts the latent vector from the sender (skipping the decoding head). Passes it through a lightweight linear adapter (trained on semantic pairs) to align dimensions/spaces. Injects the result directly into the receiver's context embedding layer. The result: "Telepathy." The receiver "understands" the concept and acts on it without a single token being generated or read. It runs on consumer hardware using bitsandbytes 4-bit loading. It’s still early (proof-of-concept level), but the speedup is massive. I’d love for you guys to roast my implementation or tell me why this is a terrible idea. pip install nexus-protocol

If you want to experience the Amiga ecosystem in 2025 without touching hardware, the easiest path is:

WinUAE (Windows) or FS-UAE (Mac/Linux) — great defaults, easy setup

Install Workbench 1.3 or 3.1 plus: Directory Opus, Diskmaster, WHDLoad

Use curated packs like Workbench 3.X ClassicWB so you don’t have to configure everything manually

For games, WHDLoad bundles are a massive quality-of-life improvement over floppy juggling

You’ll get 90% of the “Amiga feel” without hunting vintage hardware.

I gave up my well paying full time job to start my own mammoth, own intuition. Been 5 months now and mammoth is ready for the ride.