Thomas O'Toole

@fouldsy147 That final black!!! Played it like it was off the spot.

Ronnie O’Sullivan has just made a breaking 153 in the opening frame of his #WorldOpen match. Mindblowing 🤯🤯🤯🤯🤯

💯

@levelsio I’m glad I’m not the only one. My guys love it but I just cannot get on with it. Paging the maestro @doodlestein … if he’s not already built it he soon will.

I hate tmux It's so incredibly user unfriendly The shortcuts make no sense I wish someone would make a better tmux Even just logging into tmux attaching the screen is an illogical hell to type Again I hate tmux, it's so shit

@doodlestein You might be unlike Joseph Heller!

@articles_o lol, never

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.

@kezia_noble Parts of it still are. Truly.

Reminder: Britain used to be a wonderful place to live in.

@paulg A Schöffel convert!

Brands I love: Lego, Leuchtturm, Oxford University Press, Pentel, Schöffel, Aqualung, Paradores, Staedtler, Birkenstock, Braun, Knoll, Patagonia, Herman Miller, Iittala, L.A. Burdick, Artemide, Aman, Thames & Hudson, Yeti, Rimowa, L.L.Bean, Timbuk2, Eschenbach, Ridge, Maui Jim.

@Antoine01686702 @JamesLucasIT Sublime, spiritual, other-dimensional music. A contender for the greatest “classical” (or any) composition ever. Repeated listening rewards with infinite layers of revelations.

@JamesLucasIT Bach's Goldberg Variations youtu.be/tISn_L-QnAg?si…

What's the most profoundly beautiful piece of music you have ever listened to?

@Apashe_Music One of many! Listen to the last 2-3 mins of the 1st movement of Beethoven's "pathétique" piano sonata op. 13 and Mozart's fantasie, K. 475. All in C minor of course.

Succession theme song is already a remix of Franz Schubert - Standchen D889. You're welcome.

Any MS product. They are universally awful.

@doodlestein @pvncher I think this is the Clanker version of "“If I had an hour to solve a problem I'd spend 55 minutes thinking about the problem and five minutes thinking about solutions”, often attributed to Einstein.

@pvncher Exactly right. So much of my approach is setting things up on a silver platter so the model can focus its intelligence like a laser beam on the actual problem instead of unrelated sub-problems (aka, nonsense BS).

I like to think of llm intelligence as a fixed quantity, like a glass of water. That intelligence is expended when it has to resolve ambiguity in your query, so there’s less of it remaining to actually solve the problem. Long context adds ambiguity for the model to reason about

@kezia_noble There's also no excuse for bad breath.

It’s better to be ugly than have bad breath. A winning personality can make someone attractive. Good looks and a winning personality is eclipsed by bad breath. My random post of the day. But I stand by this.

@doodlestein @FinFreedom414 They are utterly awesome. Even when teenage and very defiant!!!

@articles_o @FinFreedom414 I have no desire to be childless, even for a day. My kids bring me way more joy than going on some luxury vacation to Mexico or something like that.

Imagine you had to choose your life at age 40: Option A: Single. No kids. $10M net worth. Travel anywhere. Total freedom. Quiet house. Quiet holidays. Option B: Married. 3 kids. $1M net worth. Drive a Toyota. Chaos every morning. Loud house. Full dinner table. Be honest, which life are you choosing?

@FinFreedom414 B. and it is not even close.

@doodlestein LOL. The RAM chad. And the token giga-chad.

@articles_o Yes, I’ve seen this but haven’t really used it yet. I generally just use playwright directly. And yeah, I just get more RAM so I don’t have to worry about it!

@doodlestein I know there's headless browser requirements for some of the tools. Have you seen this? github.com/vercel-labs/ag… Chromium just guzzles RAM ...

@doodlestein @mowten4 That will be this afternoon's project! This morning the garden needs some TLC ... too much clanking.

@articles_o @mowten4 It’s still under development but it’s pretty solid now. All my Rust projects use it now pretty much.

I'm now up to over 5.5k beads for my asupersync project, which is a record for me. The force graph layout of all the beads is truly nuts, and puts into perspective what a massive, sprawling effort it's been. It's now a million lines of code with tests! dicklesworthstone.github.io/beads_for_asup…

@doodlestein "Weapons". I trained Clawdbot's soul.md on British humour and get some top notch bants!

If “clanker” is the slur for AI agents used by humans, then what will the agents use as a slur for humans among themselves to indicate derision? I nominate “meat boys.”