Latent Signal

Latent Signal

@latentsignal.org

Latent Signal is built by George Chiramattel and Ann Catherine Jose; two technologists exploring AI, machine learning, and what it means to build useful technology responsibly. https://latentsignal.org/

10 followers3 following18 posts

“Agentic systems” can refer to very different kinds of systems. In our new series on building agentic systems, the first post maps the autonomy spectrum—from simple model calls to systems that plan, use tools, and act with limited supervision. 🧵 1/3

Each step brings more flexibility, but also more cost, complexity, and risk. The core idea: choose the simplest architecture that gives the system just enough autonomy to do the job well. 2/3

We also offer a half-day in-person session for small product, design, and engineering groups; even folks who don't code day-to-day leave with a working prototype and a shared playbook. 👉 Reach out at: latentsignal.org/workshop/pri...

latentsignal.orgPrivate team workshop — Latent SignalBring the Claude Code agentic coding workshop to your team in person. Tell us about your team and we will get back to you with a tailored proposal.
Latent Signal@latentsignal.org

We've opened our free and self-paced Agentic Coding workshop. Build a real-time, multi-user Idea Board with Claude Code - deployed to Vercel on your own URL in 3-4 hrs. AI foundations + 9 hands-on steps. For anyone who wants to understand how agents actually behave. latentsignal.org/workshop

Latent Signal reposted

The rollout of GLM Coding Plan from Z.ai appears a bit rushed, to be honest. There’s a 5-hour quota, but the usage dashboard doesn’t indicate when the quota will expire. Or am I misunderstanding something?

I didn’t want to sit on a Show HN page waiting for new comments, so I asked Gemini to write a small script that watches Firebase and sends Pushover notifications to my phone. I ran it once and left it alone. This morning I woke up to a stack of comment alerts.

Left: Our Projects page in prod Right: Clone built by GLM 5.2 + pi with a screenshot of the page Result - Not the best output, but close. However, we're impressed that GLM built it without image support - thanks to pi asking gemini CLI to extract colors, font, text from the screenshot upfront.

Hello Bluesky 👋 We’re @annjose.com and @georgeck.me, two software engineers building, writing, and teaching at the intersection of AI, software engineering, and product development. We focus on moving past AI hype by building projects, and developing mental models for how software is changing.

You are up to date.