nick@BSLABS

While it's true, consequences follow you... Baggage can be left at the door. Set it down.

big props to Lambda for doing this!

this... invest in yourself if you believe in yourself.

Today I turned a page and resigned from a 20 year career doing identity and access management for BofA. I'm so excited for what comes next.

I was just thinking that if you archive all of your agent sessions for your builds, that would be a hell of a data source for discovery. I would consider proxying your traffic so you get the full depth of logging (exact API calls). I would bet there is a ton of routing (choosing correct model for job) and and context building efficiencies left on the table.

@F_AI_Mouse I’m finishing my FrankenEngine and FrankenNode first so I can build the extension system using it.

People are constantly asking me about my planning and execution methodology for creating software using my Agent Flywheel system of tooling, prompts, and workflows. As a result, I find myself posting the same link, often multiple times in a day, to a post of mine that includes links to 5 other X posts and threads I've made about my methodology. While this "works," in that a motivated person can read through each post and understand my approach pretty well, I realize that it's far from optimal, and a lot of people see that and just give up quickly. So I finally decided to gather together all my materials on my method and turn them into two different articles with different target audiences. Perhaps unsurprisingly, I was able to extensively leverage my own tools to do this effectively. For one, I was able to use my xf tool (for searching your personal X post archive that you can download from X) to pull in all the various posts and my replies to people in those threads into a single large markdown document. Then, I had agents use my cass tool to search for my real-world usage of my various tools and to gain insights into my planning process from firsthand observation. I also had a lot of materials in the tutorials section of the Agent Flywheel website, as well as in various agent skills I've created. All of this was woven together and synthesized into a single comprehensive document, The Flywheel Approach to Planning and Bead Creation: agent-flywheel.com/complete-guide This is the new canonical and complete guide to my approach, with everything in one place and synthesized into a coherent whole so that you don't need to scrounge around for all the different posts. I will also be updating the article as my methodology evolves and in response to reader feedback on what is confusing or unclear (so please let me know in the comments). Incidentally, as I got to the final stages of preparing this document, I found this prompt to be extremely useful: "Read the entire document again with fresh eyes all the way through, putting yourself in the position of a smart software developer who is new to agentic coding and doesn't know how to use the Flywheel or agent swarms effectively yet and who doesn't understand the planning process or beads, etc. What would be most confusing? How could we make it more engaging and intuitive without removing any content and without simplifying anything (think additively)?" Beyond that big comprehensive guide, as the Flywheel system has grown to 20+ tools now, I've heard repeatedly from people that they find the entire system too overwhelming, because there are so many tools to understand. But the truth is, there is a "core" to the Flywheel approach which captures most of the value and just uses 3 tools: * My Agent Mail project for coordination and communication of multiple agents of various types; * beads_rust (br) for task management; and * beads_viewer (bv) for automatically triaging the beads graph so that agents always work on the optimal next bead to maximize overall development velocity. So to that end, I created a separate, shorter, more-focused article for beginners to the system, the Flywheel Core Loop Guide: agent-flywheel.com/core-flywheel If you've previously been interested in the Flywheel but found it to be too hard to understand or had "information overload" (which is totally understandable... this stuff emerged organically over months of working on this stuff, so I'm sure it's a lot to take in all at once like that), I highly recommend checking it out. Once you get the hang of it, you can then layer in additional utilities, starting with destructive_command_guard (dcg) to prevent agents from blowing up your projects or machine; coding_agent_session_search (cass) to search instantly across all your agent sessions, and give this power to your agents themselves; and ultimate_bug_scanner (ubs) for finding bugs and problems across most popular programming languages in a single tool that is heavily optimized for use by agents.

no, unfortunately I missed it the first round. I'll definitely give it a shot and see if it catches anything I missed. The whole experience though, set off a storm of revelations for me that are going to drive me to create my own coding harness (I think)... how far are you on yours? I have an internal drive for efficiency and I can't consider stacking accounts without considering efficient token use first (can't help it, it's just an a part of who I am I guess).

@F_AI_Mouse Hah, awesome. Did you use my xf tool for the X data search?

nostalgia

@yacineMTB have you? or have you only found the limits of it's harness?

I have found the limits of gpt 5.4

It's a big change. It's normal to feel a little 'off'. I'm about to change careers after 20 years of being a corp wage slave. I'm excited, but I'd be lying if I said it wasn't a little scary. Not because I don't believe in what I'm doing, but because my old 'normal' will cease to exist.

Even though I am not a social person, I am feeling pretty alone here in my home town. While things are looking up, there's also a dark cloud of loneliness that seems to take hold here. I didn't feel this way at home. Hopefully it's just a change of scenery at issue. I need to get back to a routine.

@bryan_johnson There is nothing like being the recipient of the full devotion of a cocker spaniel

I'm thinking about getting two dogs. What breeds should I consider?

Codex is a guy and Claude code is a girl I don’t make the rules

@mfranz_on Yes, overall Opus is better as a consultant, not your everyday driver. 5.4 is a good model.

Everybody is using codex while I am still using claude code. Am I missing something?

My gut tells me that Lauren has the potential to do more work on the level of @DataRepublican , I'm just trying to do my part to help out. Watch out kids, she's got 32 cores now!

@sudoingX Which model are you using to identify the bug lists ?

i run every model through octopus invaders. same prompt, same game spec if a model can build this autonomously on a single GPU it passes. if it can't it doesn't. qwen 3.5 9B Q4 on a RTX 3060. first attempt was blank screen built 2,699 lines across 11 files and nothing rendered. i wrote it off as a ceiling. then last night i came back with a precise bug list and the same model on the same card fixed every single one surgically. game came to life. enemies spawning, background rendering, collisions working. but bullets didn't fire and the enemies looked like colored squares instead of octopi. today i pushed again. listed 9 more bugs. the agent read every file, patched across 4 modules, validated syntax and restarted the server on its own. bullets fire. enemies look like actual pixel art. screen shake works. the game is playable and i genuinely enjoyed it. level upgrades still don't trigger and there's more to fix but i'm iterating on a single 12GB card running everything locally. every file, every prompt, every output stays on my machine. 29 tok/s generation, 417 tok/s prefill, 128K context window on a card that most people bought to play warzone. if you use AI in any part of your life and you have a computer with a GPU in it you should not be sleeping on this. the model weights are free. the hermes agent framework is free. your data never leaves your house. own your cognition.

I want to do this just to use it as my clanker's face

yes, this is how to build it

so, my m5 max made it from Hanoi Viet Nam to Louisville KY, and then magically, departed from Hanoi again the same day. Either I'm getting 2 by accident or someone stole the first one 🤷‍♂️

@maietta I absolutely love this for you , I'm celebrating with you!

I guess I'm moving. I just landed a job and an apartment with a view. In my home town. And the company is buying the car for me.

@chongdashu @VictorTaelin I think I remember you trying to do something along these lines awhile back, thought you might be interested.