Outermeasure_A

This connection between the Linear Program and what Astra did seems like a jump. Did the author come with the idea on their own, or an LLM figured it out?

Side hobby: Improving the gameplay of a multiplayer browser game. Rimpark (https://rimpark.gg) launched ~1.5y ago.

I'm self hosting a GLM 5.3 Flash, and with it: adding new mechanics, fixing bugs, etc.

It's been a learning journey so far: how to run inference, setup agentic systems, experimental loops, and prevent slop.

This week, I'm happy that my agent system can implement a new feature e2e with not a lot of human intervention in code reviews. Still reading every line, didn't YOLO (yet lol).

1) No subscriptions

2) I self host a Q4 quant of GLM 5.3 flash, at work using Antigravity and Gemini Argon

3) Vanilla Pi cli and running in from a VM. I customized it to work around common LLMism, like intercepting and modifying requests or tool calls.

4) Pi is my agent orchestration, it can run in headless mode recursively. Also most of the things the agent UIs provide can be done via writing to shared files to disk

5) No

Any TV if you disconnect from the network and stream via HDMI instead.

There was an ACM problem a few years ago where it was asked to count the collisions. We implemented the simulation and noticed the digits of PI but we didn't actually proven the fact. Got AC.