What’s not intuitive to me is that through pattern matching it’s able to express logic and reasoning.

“Demand is also being intensified by major investments in infrastructure, manufacturing, reshoring, and AI. Data center growth alone has added a net 315,000 skilled-trade workers over the past five years, according to the report, putting additional pressure on an already tight labor market.”

https://www.morningstar.com/news/pr-newswire/20260825cg32433...

We literally do not have enough trades people to build out data centers and their salaries are increasing as a result. These are skilled labor jobs (plumbers, electricians, IT, etc.). Does Bill Gates care about the rest of the economy outside of SWE?

[0]: https://digitaleconomy.stanford.edu/app/uploads/2025/11/Cana...

I think of LLMs as a labor-liberating tool. It's saving me effort so I don't have to drudge through enterprise codebases and memorize company-specific knowledge that is a dead end for my career. Instead I can run an agent while doing chores.

The beauty of the entire LLM stack is that it requires us. It is useless without a human-in-the-loop. The entire stack is designed around human intervention. We will not magically invent a way to remove the human without first removing it from training.

So rest assured, so long as there are humans in the training loop, there's nothing to worry about, because LLMs are a cybernetic enhancement, not a replacement.

This was written in zig and built by vercel. That’s the only notable characteristics about this project.

All code agents look the same and this one is no different.

My general strat with LLMs is to let them do the work and constantly talk to them about their choices and then heavy QA

I just assumed every model manufacturer is distilling from the frontier models. If they aren't they are definitely trying to do it.

I do like Kagi but the Gemini deal was too good to pass up as it also gives my a code agent.

I'm going to spend more time contributing without so much self-promotion.

Thanks for the feedback.

Idk, I already don’t bother with Opus and stick with sonnet med. I really care more about speed. I use qwen3.6 27b for personal projects and I think it works pretty great.

So like the article mentions, if scaling stalls and small models get better it’s not impossible to imagine a convergence and hardware costs drop.

Having said that, self hosting will be a niche thing like it is today for other services.

I just revamped the collaboration portion which is a patchbin service: https://pr.pico.sh

As part of that I work im also iterating on the ci/cd solution we are calling pici: https://ci.pico.sh

AMA

It's spawning PTYs but does it support SSH'ing into a remote session and running commands from a remote shell? That's something I built into zmx in order to scratch that "debugging in a remote VM" itch.

https://zmx.sh