You can fine-tune local models using your own data. Unsloth has a guide at https://unsloth.ai/docs/get-started/fine-tuning-llms-guide.

I'm currently experimenting with Tobi's QMD (https://github.com/tobi/qmd) to see how it performances with local models only on my Obsidian Vault.

Right, the technical know-how about fine-tuning isn't the problem here, getting sufficiently high quality session logs without basically giving away my private data for free is the issue.

Today, I can use even the small models of OpenAI and Anthropic to get valuable sessions, but if I wanted to actually use those for fine-tuning a local model, I'd need to actually start sending the data I want to use for fine-tuning to OpenAI and Anthropic, and considering it's private data I'm not willing to share, that's a hard-no.

So then my options are basically using stronger local models so I get valuable sessions I can use for fine-tuning a smaller model. But if those "stronger local models" actually worked in practice to give me those good sessions, then I'd just use those, but I'm unable to get anything good enough to serve as a basis for fine-tuning even from the biggest ones I can run.

Not a scientist, but I assume the signal would degrade or mutate over time due to space radiation and other radio waves.

Electromagnetic waves have perfect/lossless superposition, so radiation can’t really degrade a signal that way.

The big limiting factors are free space path loss and noise.

That's only true in classical electrodynamics, as it happens. If you're in a very strong B-field like you might find near a compact object you'll get nonlinear QED effects.

You can get a low order correction with Euler-Heisenberg: https://en.wikipedia.org/wiki/Euler%E2%80%93Heisenberg_Lagra...

It should be same logic we use for repeaters, so it'll be fine.

The logic we typically use for repeaters (EDFA, erbium-doped fiber amplifiers) for long-distance lines amplifies but does not clean noise (so across the oceans, you are very much bound by SNR). And you need one of them every 80 km or so in typical fiber.

All the talk about "open" standards from AI companies feels like VC-backed public LLM experiments. Even if these standards fade, they help researchers create and validate new tools. I see this especially with local models. The rise of CLI-based LLM coding tools lets me use models like GPT OSS 20B to build apps locally and offline.

Claude Code has subagents as well. I created a workflow with multiple agents to build iOS apps, including agents for orchestration, design, build, and QA.

Claude Code subagents keep their context windows separate from the main agent, sending back only the most relevant context based on the main agent's request.

The UI looks so close to Open WebUI I was shocked this isn't a fork. It even looks like it takes OWUI's unique model customization features, but makes it agents.

Might have to try this out. OWUI's lagging docs has made managing my own self hosted instance a pain.

PS: Your _See All Connectors_ button on the homepage is 404ing.

Haha, yea the UIs certainly have similarities (much of the industry converges to standard places to put different components, since users are familiar).

"Agents" is a particular area where we feel like we're better than the alternatives (especially if you want something that effectively calls multiple tools in sequence). Curious to hear your thoughts after trying it out!