> They keep adding features without maintaining the core.

It does take a lot of discipline to review everything instead of pile on another feature, when it's so cheap to do.

What's the advantage of having multiple channels with separate residual connections? Why not just concatenate those channels, and do residual connections on the concatenated channel?

I've been working on something similar.

https://github.com/coventry/sandbox-codex

Still work in progress. The tmux-activity logs are unreadable, at the moment.

I run it in a virtualbox as well, since docker is not a completely reliable sandbox.

I too built something similar (just for nodejs and bare-bones impl): https://github.com/freakynit/simple-npm-sandbox

Was a fun little learning exercise.

I'm looking for a language optimized for use with coding agents. Something which helps me to make a precise specification, and helps the agent meet all the specified requirements.

I'm working on something similar. Dependently typed, theorem proving, regular syntax, long form english words instead of symbols or abbreviations. It's not very well baked yet but claude/codex are already doing really well generating it. I expect that once the repo has been around long enough to be included in training data it'll improve. Probably next year or the year after.

I'm looking for a language optimized for human use given the fundamental architectural changes in computing in the last 50 years. That way we could skip both the boilerplate and the LLMs generating boilerplate.

> I don't understand the stance that AI currently is able to automate away non-trivial coding tasks.

I'm happy enough for it to automate away the trivial coding tasks. That's an immense force multiplier in its own right.

Anthropic must be loving this.

> Gas Town is also expensive as hell. You won’t like Gas Town if you ever have to think, even for a moment, about where money comes from. I had to get my second Claude Code account, finally; they don’t let you siphon unlimited dollars from a single account, so you need multiple emails and siphons, it’s all very silly. My calculations show that now that Gas Town has finally achieved liftoff, I will need a third Claude Code account by the end of next week. It is a cash guzzler.

https://steve-yegge.medium.com/welcome-to-gas-town-4f25ee16d...

The author has written an evangelical book about vibe coding.

https://www.amazon.com/Vibe-Coding-Building-Production-Grade...

He also has some other agent-coordination software. https://github.com/steveyegge/vc

Don't know whether it's helpful, or what the difference is.

Doesn't involve Gaussians, but:

The Free Transformer: https://arxiv.org/abs/2510.17558

Abstract: We propose an extension of the decoder Transformer that conditions its generative process on random latent variables which are learned without supervision thanks to a variational procedure. Experimental evaluations show that allowing such a conditioning translates into substantial improvements on downstream tasks.