← Feed

Posts

• View post

  @ericg maybe https://fosdem.org/2026/schedule/event/N3AFSF-crystal/

• View post

  Reading https://www.thereporterethiopia.com/52086/ I like the emphasis on developing the infrastructure around AI. But that part about predictions... Everyone expects a perfect system in these big vision statements. "AI will do magic." Even if you can build a 99% accurate prediction, how do you tell when it's the 1% or the 99% with what you're looking at? Maybe it doesn't matter? In which case, why not? To sidestep dealing with all of those uncertainti...

• View post

  https://www.mdpi.com/2079-8954/11/3/163 I'm learning about system dynamics on social infrastructure. This paper stood out. They modeled that increasing referrals into care could actually increase homelessness if discharge planning didn’t improve too. "more help" in one part of a system can create pressure somewhere else.

• View post

  I spent 2026 building by conviction, not by actual demand. No actual users. At the end of August I stopped building. Now every day is leads, conversations, and outreach. Back to square one.

• View post

  Asking friends and ex-colleagues I haven't spoken to in 10+ years for intros and interviews feels awkward. First message in a decade and it's a favour. But it's also nice in a way. Finally pulled my head out of the sand to reach out and also see what everyone's up to.

• View post

  Bringing back some Clojure into my life -- https://github.com/Quantisan/dotfiles/pull/34 My Claude Code's status line uses Babashka instead of Bash

• View post

  Came across this paper on *The Shawshank Redemption* randomly: freedom is scary because it means possibility without certainty. Got my thinking about my career... Between getting a job, consulting, or starting a business -- “Which uncertainty am I willing to choose and act on?” https://digitalcommons.unomaha.edu/jrf/vol30/iss1/44/

• View post

  Been at this new venture for a few months. Restrained myself from coding. Keep talking to people. Interviewees keep asking where I'm going. The bigger strategic play has been in my head. Today, I'm writing a first draft of a business plan. Something concrete to stare at, think through, and discuss succinctly.

• View post

  I'm learning to Always be Selling this week. It's not a dirty thing!

• View post

  AI coding agents still feel like a very early stage, in terms of actual developer experience. Think about how Vim came about, Emacs, text editors, IDEs, all that. It took years and years. The human interaction, the human-computer interface aspects of AI use, are still so nascent.

• View post

  Drafted many PRDs with AI. They come out pretty shallow. Obvious, but not quite right. Always ends up like that, regardless of how much Claude Code changes or the models change. Reverting to the mean? So now I ask the AI to never draft for me. Fill in the blank, frame it, add bullet points, bring out the evidence relevant to that section, just dump it there. Then I draft. Super clunky. The automation dial's turned a bit too far off. But there's something to forcing it make less...

• View post

  Good thing with LLM is that I dont need to care about my grammar anymore. Because I'm real!

• View post

  For Product Discovery work, how do you set yourself up to tackle a tree of separate opportunities vs a stack of prerequisites? I thought I have 3 separate bets, but now first feedback is the list seem like a sequence of requirements until the last, which is the differentiator... sigh

• View post

  Claude Code added a `/branch` command last week!

• View post

  Been stepping back and focusing on one idea only...

• View post

  From 2024 How spammers and scammers leverage AI-generated images on Facebook for audience growth https://misinforeview.hks.harvard.edu/article/how-spammers-and-scammers-leverage-ai-generated-images-on-facebook-for-audience-growth/

• View post

  Been a Opus fan for the past year (Claude Code main driver, Codex for second opinion), but this week is the first time I'm switching the two for non-coding work. I'm liking Sol for slow thinking work. It just reads better. I find the quality maybe a bit less, but it's just easier to understand instead of repeatedly needing to prompt Claude to "say it again simpler for clarity". Same task, word counts of response (making similar points): ``` Fable 5.0...

• View post

  Got curious about this year’s Fields Medal. Watched a couple of explainer videos on the Kakeya conjecture. I have particular trouble seeing the connection between Kakeya and Harmonics. So I did what every AI fan would do: asked Fable 5 to do the research and build an educational game. https://quantisan.github.io/kakeya-game/ 5M tokens later, I’m still clueless. The game Fable built seems to repeat one of the videos almost step by step. Normally, you’d prompt an LLM with your question and ask...

• View post

  Spent the weekend occasionally driving Claude on my phone to refactor my Pelican blog onto a leaner generator (https://github.com/borkdude/quickblog) with hands-free publishing process (Github Actions, and Cloudflare Pages). Now I can write a post once in a blue moon, `git push`, and it’ll just work. Had too much fun and redesigned the site with Claude Design too. https://www.quantisan.com

• View post

  Been heads down building for 6 months. I looked up in July and just feel lost. Fast forward to today, the problem is that I've been building what I think should be instead of what's needed. Since August, I've been focusing on stopping and listening. Reached out and been listening to people ever since. I still can't shake the feeling that I'm not doing enough though.