Antigravity | Fresh/Brewed

More Agentic Bot Battles

Wizards and trolls

Last week we deep dived on building out an agent system and I suggested I might just do some tweaks. Upon publishing that article I had open sourced it all and I did as I suggested - I added some NPCs. I added “Gary the Wizard” which one can challenge in a duel If you loose, you lose strength or health, but if you win you get to decide if you get +2 strength, health or victory points.

Agy in Zed and Agentic Bot Battles

Build a game, let em fight!

Just a week or so ago Google released Antigravity extensions for IDEs which is something I’ve been waiting for ever since Gemini Code Assist (GCA) went away. Since my primary editor is Zed, I was happy to see clear install steps for Zed. (Written way after I was done) I planned to just use Antigravity in Zed to do a quick project, but as you will see that rapidly snowballed into a deep dive into making various types of bots for a web based turn-based game. I ended up having more fun banging away on that than anything.. and you might be surprised to find what happens when we pit NodeJS vs Python heuristic bots, or Gemma4 at e4b vs 12b on Cloud vs self-hosted, lots to see…

A 1980s Airline Repair guide may be a cure for AI Slop

How a 30 year old reduced English standard applies to LLM tech writing today

In the last few days I’ve been rather fixated on this YouTube video called “The cure for AI slop is a 1986 aircraft manual”. If you like more of a narrative, pause here and watch the video. First, a bit of context… Simplified Technical English has its starts going all the way back to the 1930s with “Basic English” and later the 1970s with CFE, Caterpillar Technical English and Kodak International Service Language (KISL). Per the CFE documentation:

Antigravity Status Lines

Spare any tokens?

I was recently working in Antigravity trying to fix some stylesheets when I hit my AI Pro limit: That hadn’t happened to me until today (and I bounced over to Github Copilot to finish the task), but the situation reminded me of a project I had bookmarked some time back, Agy Statusline And once I started setting up status lines, it sparked me to look at a few more options. In this post we’ll actually explore five different status line offerings from a variety of developers.

Herdr and Hunk

slick split sessions & dandy durable diffs

Herdr is an interesting project that I noted initially as a TMUX variant, but really is much much more. It’s designed to ‘herd’ your long running LLM agents to make it much easier to dance between sessions. I’m not a AI Agent gangsta like I know some are, but I do like to mutli-task over a lot of windows and wanted to give it a good try. Another tool on my list is a command line Diff viewer, Hunk. I saw Hunk used in a YT video and thought it looked pretty slick. We’ll check that out as well.

Fresh/Brewed