


✝️ “love thy neighbor”



I'm no longer giving a platform for anti ai people or bots to post their comments. Either give useful constructive criticism or move on 😄

agreed, the time the PR is created your agentic workflow should have already reviewed it to the point where it's good for a human just to spot check the high level changes.
Get code review agents off of GitHub! I don't want to see the noise in my PR description. Agents should run through their own internal code review process before a PR ever reaches a teammate.




even people are using scripture to stop me from building on my zombie game...

sorry for the annoying heart beat it tried to sync with the music... fable did a little too much on this one.

used Fable 5.2 to do another pass through to improve the UI for the game and make a montage before / after video.

The AI hate comments I used to get for coding have mostly died down as people realized how powerful these models are. Now I'm building a game with AI, and the "AI slop" comments are back in full force. Feels like I've entered another industry that doesn't realize what's coming.

the crazy part is it works perfectly fine in codex



I think I picked the wrong animation... on a side note @tripoai makes some great models from 1 reference image, pretty crazy.

So basically GitHub.com/agentsystemlabs/b…
I've changed how I work over the last few weeks. I now have one lead agent for each area of focus, running all the time, and a chief of staff agent that oversees them. Each lead manages its own sub-agents that write code, test it, chase reviews, and coordinate with team members. Everything I need to decide or review comes into one prioritized queue, a simple local web app. Each product review includes screenshots and a video demo of the feature. I clear the queue in batches, mostly by voice and keyboard shortcuts. The leads also bring back ideas I hadn't considered. Working from one queue, instead of switching between dozens of chats, has cut a lot of mental overhead. The system keeps learning my preferences and distilling my judgment into a "Brian brain," so its recommendations and first drafts get better before they reach me. The goal is fewer corrections per change. Every change still goes through the same human review and security checks. It is eliminating tasks, not human judgment. What an exciting time to push the frontier of productivity, especially as we build the economy for agents (agentic finance). We should all keep pushing in this direction.